Refresh Review Studio release context

This commit is contained in:
yaojingang
2026-06-17 01:55:02 +08:00
parent c8febd1a7b
commit 4047cfdb1a
14 changed files with 93 additions and 113 deletions
+16 -26
View File
@@ -3,24 +3,14 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 31,
"changed_file_count": 2,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget_summary.json",
" M reports/evidence_consistency.json",
" M reports/install_simulation.json",
" M reports/install_simulation.md",
" M reports/output_execution_runs.json"
" M reports/context_budget_summary.json"
],
"scope": "generation-time status before this report is written"
},
@@ -30,9 +20,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e",
"evidence_bundle_sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -52,7 +42,7 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 31
"changed_file_count": 2
},
"public_claim": {
"ready": false,
@@ -68,7 +58,7 @@
},
"release_lock": {
"ready": false,
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"status_scope": "generation-time status before this report is written",
"reason": "working tree was dirty at generation time"
},
@@ -78,7 +68,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e"
"sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -151,8 +141,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7965,
"sha256": "6a1d18e9ff6f3e2461fec034c4fe371d9e9c82ac57c32342d12849fed61ddc4d"
"bytes": 7964,
"sha256": "282122e93b08d73b0c199715c51bc619a95af47d315047fc41dceb31f56a3293"
},
{
"label": "blind_review",
@@ -194,35 +184,35 @@
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29196,
"sha256": "636583616dbcc15fe06d582ff0eda17c08a3d37eae618b03e1ca9c666c5276d2"
"sha256": "f8e498d295db139c49e2ea51bd2cbdd52db61fa2b0bd008ef74135601d691895"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "0412ab0eff34056858b8078f363f6cba2cc46ac294f0a165bfdab388287904f2"
"sha256": "88c94a496b941ef0538a7bab550c85d2fc07487edf35e4cd39bde14b1475108c"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "52f419800aa43fc1c5f0abd465da2ca67640d4f26efb06659534bf73f1480d2c"
"sha256": "f9c6cdf1a7e033b7d80d13f90577f7ae5a269bf2bbb9165bff16d602d01055b7"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8758,
"sha256": "c91884a915384363d4ea0339de5c9a3e37ede4356ad1069edf0ae6f880366cc7"
"bytes": 8604,
"sha256": "044b2cf73dd4559a2a0b2f6cbb5560677d409d4716d135261fac6399012d1abb"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "4f193d15332d6ae7c6df397b0c777219fc9627b61c176ca70f66e43b4e94d08e"
"sha256": "e63bc60e69cdc0e613983edea2a66f6c80d0e4da92efd6f90203c390b813350d"
},
{
"label": "world_class_evidence_plan",
+11 -11
View File
@@ -1,9 +1,9 @@
# Benchmark Reproducibility
Generated at: `2026-06-17`
Commit: `5b52d7db65202d3a5bba4b217aa324cb53a79beb`
Commit: `c8febd1a7b25341fce62fb5154198f4e740fbdbe`
Working tree dirty at generation: `true`
Evidence bundle SHA256: `815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e`
Evidence bundle SHA256: `ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8`
## Summary
@@ -13,7 +13,7 @@ Evidence bundle SHA256: `815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc
- required artifacts: `25`
- missing artifacts: `0`
- source contract sha256: `e9d5b26e20c8`
- archive sha256: `8319a98a3f3c`
- archive sha256: `563d37a1085a`
- output cases: `5`
- disclosed failure cases: `3`
- reproduction commands: `23`
@@ -23,7 +23,7 @@ Evidence bundle SHA256: `815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc
- world-class source checks: `7` pass / `13` total; `6` blocked
- public claim ready: `false`
- public claim blockers: `5`
- changed files at generation: `31`
- changed files at generation: `2`
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.
@@ -51,7 +51,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
- algorithm: `sha256(path,label,exists,artifact_sha256)`
- artifacts: `25` / `25`
- sha256: `815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e`
- sha256: `ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8`
## Methodology Sections
@@ -73,17 +73,17 @@ 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 | `6a1d18e9ff6f` |
| output_execution | `reports/output_execution_runs.json` | present | `282122e93b08` |
| blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` |
| review_adjudication | `reports/output_review_adjudication.json` | present | `bb8c72a9291e` |
| trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` |
| runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
| trust_report | `reports/security_trust_report.json` | present | `d865e5cc97a3` |
| python_compatibility | `reports/python_compatibility.json` | present | `636583616dbc` |
| registry_audit | `reports/registry_audit.json` | present | `0412ab0eff34` |
| package_verification | `reports/package_verification.json` | present | `52f419800aa4` |
| install_simulation | `reports/install_simulation.json` | present | `c91884a91538` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `4f193d15332d` |
| python_compatibility | `reports/python_compatibility.json` | present | `f8e498d295db` |
| registry_audit | `reports/registry_audit.json` | present | `88c94a496b94` |
| package_verification | `reports/package_verification.json` | present | `f9c6cdf1a7e0` |
| install_simulation | `reports/install_simulation.json` | present | `044b2cf73dd4` |
| skill_os2_audit | `reports/skill_os2_audit.json` | present | `e63bc60e69cd` |
| world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `9b74155fb9bf` |
| world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `f6e1a69b0359` |
| world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `46f801051ec0` |
+2 -2
View File
@@ -6,9 +6,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1083725,
"other_text_tokens": 1083667,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1084522,
"estimated_total_text_tokens": 1084464,
"deferred_resource_tokens": 496240,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
+1 -1
View File
@@ -1,5 +1,5 @@
{
"generated_at": "2026-03-31",
"generated_at": "2026-06-17",
"targets": [
{
"label": "root",
+9 -9
View File
@@ -222,7 +222,7 @@
"actual": {
"available": true,
"clean": false,
"changed_file_count": 20
"changed_file_count": 13
},
"paths": [
"reports/benchmark_reproducibility.json"
@@ -263,8 +263,8 @@
"key": "overview-benchmark-commit",
"label": "overview embeds the benchmark commit",
"status": "pass",
"expected": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"actual": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"expected": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"actual": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-overview.json"
@@ -280,7 +280,7 @@
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
@@ -293,7 +293,7 @@
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
@@ -409,8 +409,8 @@
"key": "interpretation-benchmark-commit",
"label": "interpretation embeds the benchmark commit",
"status": "pass",
"expected": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"actual": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"expected": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"actual": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"paths": [
"reports/benchmark_reproducibility.json",
"reports/skill-interpretation.json"
@@ -426,7 +426,7 @@
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
@@ -439,7 +439,7 @@
"required_artifact_count": 25,
"missing_artifact_count": 0,
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"world_class_ledger_pending_count": 4,
"world_class_source_check_count": 13,
"world_class_source_pass_count": 7,
+5 -5
View File
@@ -740,12 +740,12 @@
<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>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; 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>147 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>225 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 2 early; 68 CLI handlers; 18 in entrypoint</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>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock true</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</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>182 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>685 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>5 blockers; local reproducible true</p></article><article class='metric'><span>Blueprint</span><strong>21/21</strong><p>2.0 coverage; extensions partial 0, planned 0; 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>147 scripts scanned; secrets found</p></article><article class='metric'><span>Py Compat</span><strong>0</strong><p>225 files scanned for Python 3.11</p></article><article class='metric'><span>Arch Debt</span><strong>0</strong><p>696 largest lines; 0 watchlist; 2 early; 68 CLI handlers; 18 in entrypoint</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>Daily Ops</span><strong>5</strong><p>proposal-review; approval 0; release lock false</p></article><article class='metric'><span>Weekly Queue</span><strong>5</strong><p>curator-review; ready 1; top score 88</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>182 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>685 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 990/1000; deferred 496240/120000; top deferred scripts 435346; resource governance governed; quality density 131.3</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; 147 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; 225 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>222 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</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 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <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 7/13 pass; 6 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>
<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 990/1000; deferred 496240/120000; top deferred scripts 435346; resource governance governed; quality density 131.3</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; 147 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; 225 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>222 Python files; 0 hotspots; 0 watchlist files; 2 early watch files; 0 blockers; largest 696 lines; 68 CLI handlers; 18 in entrypoint</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 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p><footer>reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly <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 7/13 pass; 6 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>
<section>
@@ -842,14 +842,14 @@
</section>
<section id="telemetry" class="twocol">
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true</p></div>
<div class="panel"><h2>运营回路</h2><p>1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false</p></div>
<div class="panel"><h2>漂移信号</h2><dl class='kv-grid'><div><dt>事件数</dt><dd>1</dd></div><div><dt>采用率</dt><dd>100</dd></div><div><dt>漏触发</dt><dd>0</dd></div><div><dt>Bad Output Count</dt><dd>0</dd></div><div><dt>风险带</dt><dd>low</dd></div></dl></div>
</section>
<section class="twocol">
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>世界级</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>日常运维</h2><dl class='kv-grid'><div><dt>决策</dt><dd>proposal-review</dd></div><div><dt>提案数</dt><dd>5</dd></div><div><dt>Approval Count</dt><dd>0</dd></div><div><dt>Pending Review Count</dt><dd>0</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>世界级</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
<div class="panel"><h2>周度队列</h2><dl class='kv-grid'><div><dt>决策</dt><dd>curator-review</dd></div><div><dt>Week Id</dt><dd>2026-W25</dd></div><div><dt>日报数</dt><dd>2</dd></div><div><dt>唯一机会</dt><dd>5</dd></div><div><dt>待批准复核</dt><dd>1</dd></div><div><dt>提案复核</dt><dd>4</dd></div><div><dt>Top Score</dt><dd>88</dd></div><div><dt>发布锁</dt><dd></dd></div><div><dt>Writes Source Files</dt><dd></dd></div><div><dt>Auto Patch Enabled</dt><dd></dd></div></dl></div>
</section>
+29 -39
View File
@@ -108,7 +108,7 @@
"key": "operations-loop",
"label": "运营回路",
"status": "pass",
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock true; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock true",
"detail": "1 metadata events; adoption 100.0; missed 0; bad-output 0; risk low; daily proposals 5; daily decision proposal-review; daily release lock false; weekly queue 5 unique; weekly ready 1; weekly top 88; weekly release lock false",
"evidence": "reports/adoption_drift_report.json + reports/skillops/daily + reports/skillops/weekly",
"link": "adoption_drift_report.md"
},
@@ -1963,9 +1963,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e",
"evidence_bundle_sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1985,9 +1985,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 31
"changed_file_count": 2
},
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"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.",
@@ -5650,24 +5650,14 @@
"ok": true,
"generated_at": "2026-06-17",
"skill_dir": ".",
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"git_status": {
"available": true,
"dirty": true,
"changed_file_count": 31,
"changed_file_count": 2,
"sample": [
" M registry/index.json",
" M registry/packages/yao-meta-skill.json",
" M reports/adoption_drift_report.json",
" M reports/architecture_maintainability.json",
" M reports/architecture_maintainability.md",
" M reports/compiled_targets.json",
" M reports/context_budget.json",
" M reports/context_budget_summary.json",
" M reports/evidence_consistency.json",
" M reports/install_simulation.json",
" M reports/install_simulation.md",
" M reports/output_execution_runs.json"
" M reports/context_budget_summary.json"
],
"scope": "generation-time status before this report is written"
},
@@ -5677,9 +5667,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e",
"evidence_bundle_sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -5699,7 +5689,7 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 31
"changed_file_count": 2
},
"public_claim": {
"ready": false,
@@ -5715,7 +5705,7 @@
},
"release_lock": {
"ready": false,
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"status_scope": "generation-time status before this report is written",
"reason": "working tree was dirty at generation time"
},
@@ -5725,7 +5715,7 @@
"existing_count": 25,
"missing_count": 0,
"missing_paths": [],
"sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e"
"sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8"
},
"methodology": {
"path": "reports/benchmark_methodology.md",
@@ -5798,8 +5788,8 @@
"label": "output_execution",
"path": "reports/output_execution_runs.json",
"exists": true,
"bytes": 7965,
"sha256": "6a1d18e9ff6f3e2461fec034c4fe371d9e9c82ac57c32342d12849fed61ddc4d"
"bytes": 7964,
"sha256": "282122e93b08d73b0c199715c51bc619a95af47d315047fc41dceb31f56a3293"
},
{
"label": "blind_review",
@@ -5841,35 +5831,35 @@
"path": "reports/python_compatibility.json",
"exists": true,
"bytes": 29196,
"sha256": "636583616dbcc15fe06d582ff0eda17c08a3d37eae618b03e1ca9c666c5276d2"
"sha256": "f8e498d295db139c49e2ea51bd2cbdd52db61fa2b0bd008ef74135601d691895"
},
{
"label": "registry_audit",
"path": "reports/registry_audit.json",
"exists": true,
"bytes": 3183,
"sha256": "0412ab0eff34056858b8078f363f6cba2cc46ac294f0a165bfdab388287904f2"
"sha256": "88c94a496b941ef0538a7bab550c85d2fc07487edf35e4cd39bde14b1475108c"
},
{
"label": "package_verification",
"path": "reports/package_verification.json",
"exists": true,
"bytes": 19338,
"sha256": "52f419800aa43fc1c5f0abd465da2ca67640d4f26efb06659534bf73f1480d2c"
"sha256": "f9c6cdf1a7e033b7d80d13f90577f7ae5a269bf2bbb9165bff16d602d01055b7"
},
{
"label": "install_simulation",
"path": "reports/install_simulation.json",
"exists": true,
"bytes": 8758,
"sha256": "c91884a915384363d4ea0339de5c9a3e37ede4356ad1069edf0ae6f880366cc7"
"bytes": 8604,
"sha256": "044b2cf73dd4559a2a0b2f6cbb5560677d409d4716d135261fac6399012d1abb"
},
{
"label": "skill_os2_audit",
"path": "reports/skill_os2_audit.json",
"exists": true,
"bytes": 14310,
"sha256": "4f193d15332d6ae7c6df397b0c777219fc9627b61c176ca70f66e43b4e94d08e"
"sha256": "e63bc60e69cdc0e613983edea2a66f6c80d0e4da92efd6f90203c390b813350d"
},
{
"label": "world_class_evidence_plan",
@@ -17206,9 +17196,9 @@
"context_budget_tier": "production",
"context_budget_limit": 1000,
"skill_body_tokens": 797,
"other_text_tokens": 1083725,
"other_text_tokens": 1083667,
"estimated_initial_load_tokens": 990,
"estimated_total_text_tokens": 1084522,
"estimated_total_text_tokens": 1084464,
"deferred_resource_tokens": 496240,
"deferred_resource_warn_threshold": 120000,
"deferred_resource_dirs": [
@@ -19276,7 +19266,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -19293,7 +19283,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -19742,7 +19732,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true
},
"actions": [
@@ -19791,7 +19781,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -19811,7 +19801,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -20064,7 +20054,7 @@
"no_route_opportunity_count": 0
},
"release_state": {
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4
+4 -4
View File
@@ -1000,9 +1000,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e",
"evidence_bundle_sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1022,9 +1022,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 31
"changed_file_count": 2
},
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"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.",
+4 -4
View File
@@ -1004,9 +1004,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e",
"evidence_bundle_sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1026,9 +1026,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 31
"changed_file_count": 2
},
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"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.",
+4 -4
View File
@@ -999,9 +999,9 @@
"methodology_complete": true,
"required_artifact_count": 25,
"missing_artifact_count": 0,
"evidence_bundle_sha256": "815615ebd47a05b4054919f5adc0fb7537a1b19746b5ff783867ccc6821c3a3e",
"evidence_bundle_sha256": "ab0eb24139e6364b5ad3a386889269a178f27977569488966ce5fa7c29c2c5f8",
"source_contract_sha256": "e9d5b26e20c81f565271a1ecd793981ee1e56826313b160aebe776d2f89ca995",
"archive_sha256": "8319a98a3f3c325905b1968f9ff68aa072d5e0ab969f19c0a333cb22eb4b5557",
"archive_sha256": "563d37a1085a9b598bca7b132da6c50c1233864855591085b260d4d4bb312a3e",
"output_case_count": 5,
"failure_disclosure_count": 3,
"command_count": 23,
@@ -1021,9 +1021,9 @@
"public_claim_ready": false,
"public_claim_blocker_count": 5,
"working_tree_dirty": true,
"changed_file_count": 31
"changed_file_count": 2
},
"commit": "5b52d7db65202d3a5bba4b217aa324cb53a79beb",
"commit": "c8febd1a7b25341fce62fb5154198f4e740fbdbe",
"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.",
+3 -3
View File
@@ -14,7 +14,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -31,7 +31,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"writes_source_files": false,
"auto_patch_enabled": false,
@@ -480,7 +480,7 @@
"local_blueprint_ready": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true
},
"actions": [
+1 -1
View File
@@ -14,7 +14,7 @@ Generated at: `2026-06-17`
- local blueprint ready: `true`
- public world-class ready: `false`
- world-class pending: `4`
- release lock ready: `true`
- release lock ready: `false`
- evidence consistency ok: `true`
This report is an operations cockpit for explicit-source SkillOps. It does not scan private logs, write source files, apply patches, or count as world-class external or human evidence.
+3 -3
View File
@@ -15,7 +15,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -35,7 +35,7 @@
"top_score": 88,
"skill_count": 12,
"actionable_portfolio_issue_count": 0,
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4,
@@ -288,7 +288,7 @@
"no_route_opportunity_count": 0
},
"release_state": {
"release_lock_ready": true,
"release_lock_ready": false,
"evidence_consistency_ok": true,
"public_world_class_ready": false,
"world_class_pending_count": 4
+1 -1
View File
@@ -13,7 +13,7 @@ Week: `2026-W25`
- top_score: `88`
- skill_count: `12`
- actionable_portfolio_issue_count: `0`
- release_lock_ready: `True`
- release_lock_ready: `False`
- evidence_consistency_ok: `True`
- public_world_class_ready: `False`
- world_class_pending_count: `4`