frostbyte_neo/yao-meta-skill
1
0
Fork 0
Code Issues Pull Requests Actions Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: refresh top-level source maturity evidence

Browse Source
This commit is contained in:
yaojingang
2026-06-14 14:01:23 +08:00
parent 88cec0e51e
commit c2f5672b2c
17 changed files with 206 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
registry/index.json
+1 -1
View File
@@ -16,7 +16,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
}
registry/packages/yao-meta-skill.json
+3 -3
View File
@@ -16,8 +16,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
"compatibility": {
"openai": "pass",
@@ -48,7 +48,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
reports/benchmark_reproducibility.json
+35 -19
View File
@@ -3,23 +3,35 @@
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "9067c9e211bd0bde80eb0a65b797d01426c97a81",
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 11,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/package_verification.json",
" M reports/package_verification.md",
" M reports/registry_audit.json",
" M reports/registry_audit.md",
" M reports/security_trust_report.json",
" M reports/security_trust_report.md",
" M reports/upgrade_check.json"
],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf",
"source_contract_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"evidence_bundle_sha256": "4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160",
"source_contract_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -33,15 +45,19 @@
"world_class_open_gap_count": 4,
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 11
},
"public_claim": {
"ready": false,
"scope": "public benchmark or world-class readiness claim",
"blockers": [
"release lock is not clean or commit is unavailable",
"provider-backed model holdout evidence is incomplete",
"human blind-review adjudication is incomplete",
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)"
@@ -49,10 +65,10 @@
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, and accepted world-class evidence."
},
"release_lock": {
"ready": true,
"commit": "9067c9e211bd0bde80eb0a65b797d01426c97a81",
"ready": false,
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
"reason": "working tree was dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -60,7 +76,7 @@
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf"
"sha256": "4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -134,7 +150,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "2991764f1ab41e6b2c37ddffa9b8bb51d967719487d3b4ade408dd077a182d91"
"sha256": "b9e64ef622ca0fa43d26b2da0a5bfa1b948b062ad61de82d65649617f1d4a710"
},
{
"label": "blind_review",
@@ -169,7 +185,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 99433,
"sha256": "016c810beee5c9020f5862ad0a564b5f6d760d8da481e38de9e36ec4a9a89e77"
"sha256": "e369e69ac81535e1034e222feebb3f1ced9e5ddc05cc8dcab3c12cc8ea65b9c2"
},
{
"label": "python_compatibility",
@@ -183,14 +199,14 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "4deadc85347967c1b48b7e0648b4e3e70faa6b9a630fbef2656e039d2d75d26b"
"sha256": "3919aefe4c4de4974f1eee3cb0c6204f3ebcb9e35c7f457a88be4daf381d7468"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "55f5816930f21659000f1eaaea9bdf6d600baf4bee6c1d1c4597714bf6a8c464"
"sha256": "053ec15969107afe103b34b88aeae3755f0ee93bcabd2d814204480caf99e290"
},
{
"label": "install_simulation",
reports/benchmark_reproducibility.md
+17 -15
View File
@@ -1,28 +1,29 @@
# Benchmark Reproducibility
Generated at: `2026-06-14`
Commit: `9067c9e211bd0bde80eb0a65b797d01426c97a81`
Working tree dirty at generation: `false`
Evidence bundle SHA256: `72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf`
Commit: `88cec0e51e828c289294bd50041409262e60a40f`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160`
## Summary
- reproducibility ready: `true`
- release lock ready: `true`
- release lock ready: `false`
- methodology complete: `true`
- required artifacts: `24`
- missing artifacts: `0`
- source contract sha256: `e19dbe7ff577`
- archive sha256: `9bcb614b9c6e`
- source contract sha256: `05cedc73473b`
- archive sha256: `8a35bd4cea27`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `21`
- provider evidence complete: `false`
- human review complete: `false`
- world-class ready: `false`
- world-class source checks: `6` pass / `13` total; `7` blocked
- public claim ready: `false`
- public claim blockers: `3`
- changed files at generation: `0`
- public claim blockers: `4`
- changed files at generation: `11`
This report proves local benchmark reproducibility only. It keeps external provider and human-review gaps visible instead of counting them as complete. The git commit is generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
@@ -34,21 +35,22 @@ This report proves local benchmark reproducibility only. It keeps external provi
| Blocker |
| --- |
| release lock is not clean or commit is unavailable |
| provider-backed model holdout evidence is incomplete |
| human blind-review adjudication is incomplete |
| world-class evidence is not accepted yet (4 open gaps, 4 ledger pending) |
## Release Lock
- ready: `true`
- reason: clean generation-time HEAD
- ready: `false`
- reason: working tree was dirty at generation time
- status scope: generation-time status before this report is written
## Evidence Bundle
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `24` / `24`
- sha256: `72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf`
- sha256: `4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160`
## Methodology Sections
@@ -70,15 +72,15 @@ This report proves local benchmark reproducibility only. It keeps external provi
| output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` |
| output_schema | `evals/output/schema.json` | present | `8ee340c95064` |
| output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` |
| output_execution | `reports/output_execution_runs.json` | present | `2991764f1ab4` |
| output_execution | `reports/output_execution_runs.json` | present | `b9e64ef622ca` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` |
| trust_report | `reports/security_trust_report.json` | present | `016c810beee5` |
| trust_report | `reports/security_trust_report.json` | present | `e369e69ac815` |
| python_compatibility | `reports/python_compatibility.json` | present | `ae16e17266e4` |
| registry_audit | `reports/registry_audit.json` | present | `4deadc853479` |
| package_verification | `reports/package_verification.json` | present | `55f5816930f2` |
| registry_audit | `reports/registry_audit.json` | present | `3919aefe4c4d` |
| package_verification | `reports/package_verification.json` | present | `053ec1596910` |
| install_simulation | `reports/install_simulation.json` | present | `1ed7ce5266c2` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `6bb2dcb0e1e5` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `164803bb1cea` |
reports/output_execution_runs.json
+10 -10
View File
@@ -34,7 +34,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.79,
"duration_ms": 26.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -62,7 +62,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.21,
"duration_ms": 26.0,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -85,7 +85,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.85,
"duration_ms": 25.94,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -113,7 +113,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.27,
"duration_ms": 29.18,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -136,7 +136,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.0,
"duration_ms": 29.65,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -164,7 +164,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.58,
"duration_ms": 26.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -187,7 +187,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.56,
"duration_ms": 25.63,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -214,7 +214,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.01,
"duration_ms": 25.79,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -237,7 +237,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.92,
"duration_ms": 25.67,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -266,7 +266,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.82,
"duration_ms": 25.63,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
reports/output_execution_runs.md
+10 -10
View File
@@ -23,16 +23,16 @@ Command runner evidence is present. This proves the eval harness executed an ext
| Case | Variant | Mode | Model | Duration ms | Tokens | Score | Status |
| --- | --- | --- | --- | ---: | ---: | ---: | --- |
| skill-package-contract | baseline | command | local-output-eval-runner | 25.79 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.21 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 27.85 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 30.27 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 28.0 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.58 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 26.56 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 26.01 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.92 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.82 | 98 | 100.0 | pass |
| skill-package-contract | baseline | command | local-output-eval-runner | 26.17 | 33 | 0.0 | pass |
| skill-package-contract | with_skill | command | local-output-eval-runner | 26.0 | 73 | 100.0 | pass |
| output-eval-expectation | baseline | command | local-output-eval-runner | 25.94 | 36 | 0.0 | pass |
| output-eval-expectation | with_skill | command | local-output-eval-runner | 29.18 | 80 | 100.0 | pass |
| ir-before-packaging | baseline | command | local-output-eval-runner | 29.65 | 33 | 0.0 | pass |
| ir-before-packaging | with_skill | command | local-output-eval-runner | 26.01 | 80 | 100.0 | pass |
| near-neighbor-boundary | baseline | command | local-output-eval-runner | 25.63 | 36 | 0.0 | pass |
| near-neighbor-boundary | with_skill | command | local-output-eval-runner | 25.79 | 65 | 100.0 | pass |
| file-backed-governed-package | baseline | command | local-output-eval-runner | 25.67 | 37 | 0.0 | pass |
| file-backed-governed-package | with_skill | command | local-output-eval-runner | 25.63 | 98 | 100.0 | pass |
## Next Fixes
reports/package_verification.json
+1 -1
View File
@@ -8,7 +8,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
reports/package_verification.md
+1 -1
View File
@@ -4,7 +4,7 @@
- Package directory: `dist`
- Targets: `4 / 4` adapters present
- Archive present: `True`
- Archive SHA256: `9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23`
- Archive SHA256: `8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096`
- Failures: `0`
- Warnings: `0`
reports/registry_audit.json
+4 -4
View File
@@ -21,8 +21,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
"compatibility": {
"openai": "pass",
@@ -53,7 +53,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -78,7 +78,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
},
reports/registry_audit.md
+2 -2
View File
@@ -6,8 +6,8 @@
- Maturity: `governed`
- Owner: `Yao Team`
- License: `MIT`
- Package SHA256: `e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25`
- Archive SHA256: `9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23`
- Package SHA256: `05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80`
- Archive SHA256: `8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096`
- Install simulated: `True`
## Compatibility
reports/review-studio.html
+9 -9
View File
@@ -543,17 +543,17 @@
<section>
<h2>核心指标</h2>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>3 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>98 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>577 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
<div class="metrics"><article class='metric'><span>Skill IR</span><strong>2.0.0</strong><p>5 targets in platform-neutral contract</p></article><article class='metric'><span>Compiler</span><strong>5/5</strong><p>target contracts compiled from Skill IR</p></article><article class='metric'><span>Output Delta</span><strong>100.0</strong><p>5 cases; 1 file-backed</p></article><article class='metric'><span>Exec Runs</span><strong>10</strong><p>command 10; model 0; recorded 0</p></article><article class='metric'><span>Blind A/B</span><strong>5</strong><p>review pairs hide baseline vs with-skill labels</p></article><article class='metric'><span>Review Kit</span><strong>0/5</strong><p>pending 5; answer key hidden</p></article><article class='metric'><span>Review A/B</span><strong>0/5</strong><p>adjudication decisions; pending 5</p></article><article class='metric'><span>Public Claim</span><strong>blocked</strong><p>4 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>20/20</strong><p>2.0 coverage; evidence pending 4</p></article><article class='metric'><span>Runtime</span><strong>5/5</strong><p>target conformance pass rate</p></article><article class='metric'><span>Perm Probe</span><strong>4/4</strong><p>0 native; 4 installer-enforced</p></article><article class='metric'><span>Trust</span><strong>0</strong><p>98 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>159 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>891 largest lines; 34 CLI handlers</p></article><article class='metric'><span>Atlas</span><strong>5</strong><p>12 scanned skills; route collisions</p></article><article class='metric'><span>Drift</span><strong>low</strong><p>1 metadata events; 0 missed triggers</p></article><article class='metric'><span>Waivers</span><strong>0</strong><p>0 gates covered; human risk decisions</p></article><article class='metric'><span>Intake</span><strong>4/4</strong><p>0 valid submissions; 0 invalid</p></article><article class='metric'><span>Claim Guard</span><strong>0</strong><p>73 public surfaces scanned</p></article><article class='metric'><span>Notes</span><strong>0/0</strong><p>0 open blocker annotations</p></article><article class='metric'><span>Registry</span><strong>1.1.0</strong><p>5 targets; MIT license</p></article><article class='metric'><span>Archive</span><strong>pass</strong><p>577 zip entries; package verification</p></article><article class='metric'><span>Install</span><strong>pass</strong><p>4 adapters; 12 permissions enforced; 0 permission failures</p></article><article class='metric'><span>Upgrade</span><strong>minor</strong><p>declared minor; 0 breaking changes</p></article></div>
</section>
<section>
<h2>审查闸门</h2>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 960/1000; deferred 388370/120000; top deferred scripts 340634; resource governance governed; quality density 135.4</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 98 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 159 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>156 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
<div class="gates"><article class='gate pass'><div><span>通过</span><h3>意图画布</h3></div><p>intent confidence 100/100; Intent is clear enough to package the first routeable version.</p><footer>reports/intent-confidence.json <a href='intent-confidence.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>触发实验</h3></div><p>13 trigger cases; 0 misroutes; 0 ambiguous</p><footer>reports/route_scorecard.json <a href='route_scorecard.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>输出实验</h3></div><p>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</p><footer>reports/output_quality_scorecard.json <a href='output_quality_scorecard.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>上下文</h3></div><p>initial load 960/1000; deferred 388370/120000; top deferred scripts 340634; resource governance governed; quality density 135.4</p><footer>reports/context_budget.json <a href='context_budget.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运行矩阵</h3></div><p>5 / 5 targets pass</p><footer>reports/conformance_matrix.json <a href='conformance_matrix.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>信任报告</h3></div><p>0 secrets; 98 scripts; 3 network-capable scripts; 0 help smoke failures</p><footer>reports/security_trust_report.json <a href='security_trust_report.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>Python 兼容</h3></div><p>Python 3.11; 159 files; 0 compatibility issues; 0 syntax; 0 f-string 3.11 hazards</p><footer>reports/python_compatibility.json <a href='python_compatibility.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>架构维护</h3></div><p>156 Python files; 0 hotspots; 0 blockers; largest 891 lines; 34 CLI handlers</p><footer>reports/architecture_maintainability.json <a href='architecture_maintainability.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限批准</h3></div><p>3/3 permissions approved; gaps 0; required file_write, network, subprocess</p><footer>reports/security_trust_report.json + security/permission_policy.json <a href='../security/permission_policy.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>权限探针</h3></div><p>4/4 targets probed; native 0; metadata fallback 4; installer 4; residual risks 4</p><footer>reports/runtime_permission_probes.json <a href='runtime_permission_probes.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>组合治理</h3></div><p>12 skills, 1 actionable; 0 actionable route collisions; 0 actionable owner gaps; 0 actionable stale; 0 actionable drift; 24 scoped non-actionable issues</p><footer>reports/skill_atlas.json <a href='skill_atlas.html'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>运营回路</h3></div><p>1 metadata events; adoption 0; missed 0; bad-output 0; risk low</p><footer>reports/adoption_drift_report.json <a href='adoption_drift_report.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>人工批准</h3></div><p>0 active waivers; 1 warning gates still need reviewer decision</p><footer>reports/review_waivers.json <a href='review_waivers.md'>证据</a></footer></article><article class='gate warn'><div><span>关注</span><h3>世界证据</h3></div><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p><footer>reports/world_class_evidence_ledger.json <a href='world_class_evidence_ledger.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>注册审计</h3></div><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p><footer>reports/registry_audit.json + reports/install_simulation.json <a href='registry_audit.md'>证据</a></footer></article><article class='gate pass'><div><span>通过</span><h3>发布路线</h3></div><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p><footer>reports/promotion_decisions.json + reports/upgrade_check.json + docs/migration-v2.md <a href='promotion_decisions.md'>证据</a></footer></article></div>
</section>
<div class="twocol">
<section><h2>阻断事项</h2><p class='muted'>无。</p></section>
<section><h2>关注事项</h2><ul class='issues'><li><strong>输出实验</strong><span>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</span></li><li><strong>人工批准</strong><span>0 active waivers; 1 warning gates still need reviewer decision</span></li><li><strong>世界证据</strong><span>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</span></li></ul></section>
<section><h2>关注事项</h2><ul class='issues'><li><strong>输出实验</strong><span>5/5 cases; with-skill 100.0; baseline 0.0; file-backed 1; near-neighbor 1; blind A/B 5; exec 10; command 10; model 0; recorded 0; reviewed 0/5; review pending 5</span></li><li><strong>人工批准</strong><span>0 active waivers; 1 warning gates still need reviewer decision</span></li><li><strong>世界证据</strong><span>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</span></li></ul></section>
</div>
<section id="actions">
@@ -615,7 +615,7 @@
</section>
<section id="trust" class="twocol">
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>98</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25</code></dd></div></dl></div>
<div class="panel"><h2>信任报告</h2><dl class='kv-grid'><div><dt>Secret</dt><dd>0</dd></div><div><dt>脚本数</dt><dd>98</dd></div><div><dt>网络脚本</dt><dd>3</dd></div><div><dt>Help 失败</dt><dd>0</dd></div><div><dt>包体哈希</dt><dd><code>05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80</code></dd></div></dl></div>
<div class="panel"><h2>安全边界</h2><p>高风险 secret、远程 inline execution、缺失依赖策略或无法解释的脚本接口应阻断 governed release。</p></div>
</section>
@@ -673,12 +673,12 @@
</section>
<section class="twocol">
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>是</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>3</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li></ul></div>
<div class="panel"><h2>公开声明</h2><dl class='kv-grid'><div><dt>本地复现</dt><dd>是</dd></div><div><dt>发布锁</dt><dd>否</dd></div><div><dt>可公开声明</dt><dd>否</dd></div><div><dt>声明阻断</dt><dd>4</dd></div><div><dt>Provider 证据</dt><dd>否</dd></div><div><dt>人审完成</dt><dd>否</dd></div><div><dt>世界级就绪</dt><dd>否</dd></div></dl></div>
<div class="panel"><h2>声明阻断</h2><ul class='issues'><li><strong>阻断</strong><span>release lock is not clean or commit is unavailable</span></li><li><strong>阻断</strong><span>provider-backed model holdout evidence is incomplete</span></li><li><strong>阻断</strong><span>human blind-review adjudication is incomplete</span></li><li><strong>阻断</strong><span>world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)</span></li></ul></div>
</section>
<section class="twocol">
<div class="panel"><h2>世界证据</h2><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true</p></div>
<div class="panel"><h2>世界证据</h2><p>4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true</p></div>
<div class="panel"><h2>证据台账</h2><dl class='kv-grid'><div><dt>Ledger Entry Count</dt><dd>4</dd></div><div><dt>Accepted Count</dt><dd>0</dd></div><div><dt>待审</dt><dd>4</dd></div><div><dt>Human Pending Count</dt><dd>1</dd></div><div><dt>External Pending Count</dt><dd>3</dd></div><div><dt>Overclaim Guard Active</dt><dd>是</dd></div><div><dt>Ready To Claim World Class</dt><dd>否</dd></div></dl></div>
</section>
@@ -694,12 +694,12 @@
<section id="registry" class="twocol">
<div class="panel"><h2>注册审计</h2><p>yao-meta-skill 1.1.0; 6/6 compatibility entries pass; install pass with 4 adapters; installer permissions 12 enforced / 0 failures</p></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23</code></dd></div></dl></div>
<div class="panel"><h2>包体元数据</h2><dl class='kv-grid'><div><dt>名称</dt><dd>yao-meta-skill</dd></div><div><dt>版本</dt><dd>1.1.0</dd></div><div><dt>Maturity</dt><dd>governed</dd></div><div><dt>Owner</dt><dd>Yao Team</dd></div><div><dt>License</dt><dd>MIT</dd></div><div><dt>信任级别</dt><dd>local</dd></div><div><dt>目标平台</dt><dd>openai, claude, generic, agent-skills-compatible, vscode</dd></div><div><dt>兼容通过</dt><dd>6/6</dd></div><div><dt>归档哈希</dt><dd><code>8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096</code></dd></div></dl></div>
</section>
<section id="release" class="twocol">
<div class="panel"><h2>发布路线</h2><p>0 promote; 3 keep current; 0 blocked; upgrade minor declared / minor recommended</p></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>577</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23</code></dd></div></dl></div>
<div class="panel"><h2>包体验证</h2><dl class='kv-grid'><div><dt>目标数</dt><dd>4</dd></div><div><dt>Adapter</dt><dd>4</dd></div><div><dt>归档存在</dt><dd>是</dd></div><div><dt>Zip 条目</dt><dd>577</dd></div><div><dt>失败数</dt><dd>0</dd></div><div><dt>警告数</dt><dd>0</dd></div><div><dt>归档哈希</dt><dd><code>8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096</code></dd></div></dl></div>
</section>
<section class="twocol">
reports/review-studio.json
+73 -54
View File
@@ -123,7 +123,7 @@
"key": "world-class-evidence",
"label": "世界证据",
"status": "warn",
"detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true",
"detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true",
"evidence": "reports/world_class_evidence_ledger.json",
"link": "world_class_evidence_ledger.md"
},
@@ -166,7 +166,7 @@
"key": "world-class-evidence",
"label": "世界证据",
"status": "warn",
"detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; overclaim guard true",
"detail": "4 pending world-class evidence entries; 1 human pending; 3 external pending; source checks 6/13 pass; 7 blocked; overclaim guard true",
"evidence": "reports/world_class_evidence_ledger.json",
"link": "world_class_evidence_ledger.md"
}
@@ -1332,13 +1332,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf",
"source_contract_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"evidence_bundle_sha256": "4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160",
"source_contract_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -1352,12 +1352,15 @@
"world_class_open_gap_count": 4,
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 11
},
"commit": "9067c9e211bd0bde80eb0a65b797d01426c97a81",
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1462,7 +1465,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
},
"skill_atlas": {
"skill_count": 12,
@@ -1500,8 +1503,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
"compatibility": {
"openai": "pass",
@@ -1532,7 +1535,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1548,7 +1551,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -1627,12 +1630,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"to": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"to": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
},
@@ -3964,7 +3967,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.79,
"duration_ms": 26.17,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -3992,7 +3995,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.21,
"duration_ms": 26.0,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4015,7 +4018,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 27.85,
"duration_ms": 25.94,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4043,7 +4046,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 30.27,
"duration_ms": 29.18,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4066,7 +4069,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 28.0,
"duration_ms": 29.65,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4094,7 +4097,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.58,
"duration_ms": 26.01,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4117,7 +4120,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.56,
"duration_ms": 25.63,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4144,7 +4147,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 26.01,
"duration_ms": 25.79,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4167,7 +4170,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.92,
"duration_ms": 25.67,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4196,7 +4199,7 @@
"execution_mode": "command",
"model_executed": false,
"command_executed": true,
"duration_ms": 25.82,
"duration_ms": 25.63,
"provider": "local-output-eval-runner",
"model": "",
"usage": {
@@ -4917,23 +4920,35 @@
"ok": true,
"generated_at": "2026-06-14",
"skill_dir": ".",
"commit": "9067c9e211bd0bde80eb0a65b797d01426c97a81",
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
"git_status": {
"available": true,
"dirty": false,
"changed_file_count": 0,
"sample": [],
"dirty": true,
"changed_file_count": 11,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/output_execution_runs.json",
" M reports/output_execution_runs.md",
" M reports/package_verification.json",
" M reports/package_verification.md",
" M reports/registry_audit.json",
" M reports/registry_audit.md",
" M reports/security_trust_report.json",
" M reports/security_trust_report.md",
" M reports/upgrade_check.json"
],
"scope": "generation-time status before this report is written"
},
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf",
"source_contract_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"evidence_bundle_sha256": "4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160",
"source_contract_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -4947,15 +4962,19 @@
"world_class_open_gap_count": 4,
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 11
},
"public_claim": {
"ready": false,
"scope": "public benchmark or world-class readiness claim",
"blockers": [
"release lock is not clean or commit is unavailable",
"provider-backed model holdout evidence is incomplete",
"human blind-review adjudication is incomplete",
"world-class evidence is not accepted yet (4 open gaps, 4 ledger pending)"
@@ -4963,10 +4982,10 @@
"policy": "Local reproducibility can pass before public claims; public claims require provider evidence, human adjudication, clean release lock, and accepted world-class evidence."
},
"release_lock": {
"ready": true,
"commit": "9067c9e211bd0bde80eb0a65b797d01426c97a81",
"ready": false,
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
"status_scope": "generation-time status before this report is written",
"reason": "clean generation-time HEAD"
"reason": "working tree was dirty at generation time"
},
"evidence_bundle": {
"algorithm": "sha256(path,label,exists,artifact_sha256)",
@@ -4974,7 +4993,7 @@
"existing_count": 24,
"missing_count": 0,
"missing_paths": [],
"sha256": "72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf"
"sha256": "4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5048,7 +5067,7 @@
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7966,
"sha256": "2991764f1ab41e6b2c37ddffa9b8bb51d967719487d3b4ade408dd077a182d91"
"sha256": "b9e64ef622ca0fa43d26b2da0a5bfa1b948b062ad61de82d65649617f1d4a710"
},
{
"label": "blind_review",
@@ -5083,7 +5102,7 @@
"path": "reports/security_trust_report.json",
"exists": true,
"bytes": 99433,
"sha256": "016c810beee5c9020f5862ad0a564b5f6d760d8da481e38de9e36ec4a9a89e77"
"sha256": "e369e69ac81535e1034e222feebb3f1ced9e5ddc05cc8dcab3c12cc8ea65b9c2"
},
{
"label": "python_compatibility",
@@ -5097,14 +5116,14 @@
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "4deadc85347967c1b48b7e0648b4e3e70faa6b9a630fbef2656e039d2d75d26b"
"sha256": "3919aefe4c4de4974f1eee3cb0c6204f3ebcb9e35c7f457a88be4daf381d7468"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19325,
"sha256": "55f5816930f21659000f1eaaea9bdf6d600baf4bee6c1d1c4597714bf6a8c464"
"sha256": "053ec15969107afe103b34b88aeae3755f0ee93bcabd2d814204480caf99e290"
},
{
"label": "install_simulation",
@@ -10806,7 +10825,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
},
"failures": [],
"warnings": [],
@@ -18401,8 +18420,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
"compatibility": {
"openai": "pass",
@@ -18433,7 +18452,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -18458,7 +18477,7 @@
"vscode"
],
"package_metadata": "registry/packages/yao-meta-skill.json",
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
},
@@ -18481,7 +18500,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -19489,12 +19508,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"to": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"to": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
},
reports/review-viewer.json
+18 -15
View File
@@ -919,13 +919,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf",
"source_contract_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"evidence_bundle_sha256": "4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160",
"source_contract_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -939,12 +939,15 @@
"world_class_open_gap_count": 4,
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 11
},
"commit": "9067c9e211bd0bde80eb0a65b797d01426c97a81",
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1049,7 +1052,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
},
"skill_atlas": {
"skill_count": 12,
@@ -1087,8 +1090,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
"compatibility": {
"openai": "pass",
@@ -1119,7 +1122,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1135,7 +1138,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -1214,12 +1217,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"to": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"to": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
},
reports/security_trust_report.json
+1 -1
View File
@@ -23,7 +23,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
},
"failures": [],
"warnings": [],
reports/security_trust_report.md
+1 -1
View File
@@ -16,7 +16,7 @@
- Interactive scripts: `0`
- Package hash scope: `source-contract-without-generated-reports`
- Package hash files: `182`
- Package SHA256: `e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25`
- Package SHA256: `05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80`
## Failures
reports/skill-overview.json
+18 -15
View File
@@ -918,13 +918,13 @@
"ok": true,
"summary": {
"reproducibility_ready": true,
"release_lock_ready": true,
"release_lock_ready": false,
"methodology_complete": true,
"required_artifact_count": 24,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "72e36f4dcd9333a02663a39c209e26770384f247c6a5ad394b4d76684d04bdaf",
"source_contract_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"evidence_bundle_sha256": "4ce0fa8542a1c30cb1d54d548da4069a4a50414fa5287685fd4c9d448a4b5160",
"source_contract_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 21,
@@ -938,12 +938,15 @@
"world_class_open_gap_count": 4,
"world_class_task_count": 4,
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 6,
"world_class_source_blocked_count": 7,
"public_claim_ready": false,
"public_claim_blocker_count": 3,
"working_tree_dirty": false,
"changed_file_count": 0
"public_claim_blocker_count": 4,
"working_tree_dirty": true,
"changed_file_count": 11
},
"commit": "9067c9e211bd0bde80eb0a65b797d01426c97a81",
"commit": "88cec0e51e828c289294bd50041409262e60a40f",
"missing_artifacts": [],
"limitations": [
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
@@ -1048,7 +1051,7 @@
"interactive_script_count": 0,
"package_hash_scope": "source-contract-without-generated-reports",
"package_hash_file_count": 182,
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
},
"skill_atlas": {
"skill_count": 12,
@@ -1086,8 +1089,8 @@
"trust_level": "local",
"license": "MIT",
"checksums": {
"package_sha256": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25",
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"package_sha256": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
"compatibility": {
"openai": "pass",
@@ -1118,7 +1121,7 @@
},
"distribution": {
"archive_verified": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"package_verification": "reports/package_verification.json",
"install_simulated": true,
"install_simulation": "reports/install_simulation.json"
@@ -1134,7 +1137,7 @@
"target_count": 4,
"adapter_count": 4,
"archive_present": true,
"archive_sha256": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23",
"archive_sha256": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096",
"archive_entry_count": 577,
"failure_count": 0,
"warning_count": 0
@@ -1213,12 +1216,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"to": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"to": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
},
reports/upgrade_check.json
+2 -2
View File
@@ -70,12 +70,12 @@
{
"field": "archive_sha256",
"from": "",
"to": "9bcb614b9c6eb6f38db0ab71019518f3f2320f060237c732d32bfd2c3e01bf23"
"to": "8a35bd4cea27874b716bf3057fbe970284da60681a42bc85868c710be82df096"
},
{
"field": "package_sha256",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "e19dbe7ff57701690de54324ba7f20bca0f7f3715f73f8721fbcc8c33f5b9b25"
"to": "05cedc73473b1c73d331270ff1d7d8fc09eeb3e7289c7ae63dc4fd535e261f80"
}
]
},