diff --git a/README.md b/README.md
index a9978de..c7276e6 100644
--- a/README.md
+++ b/README.md
@@ -145,11 +145,12 @@ python3 scripts/yao.py package-verify . --package-dir dist --require-zip
 python3 scripts/yao.py install-simulate . --package-dir dist
 python3 scripts/yao.py upgrade-check . --previous-package-json registry/examples/yao-meta-skill-1.0.0.json
 python3 scripts/yao.py world-class-evidence .
-python3 scripts/yao.py world-class-submission-kit . --output-dir /tmp/yao-world-class-submission-kit
-python3 scripts/yao.py world-class-ledger .
-python3 scripts/yao.py world-class-intake .
-python3 scripts/yao.py world-class-submission-review .
-python3 scripts/yao.py world-class-runbook .
+SUBMISSIONS_DIR="${SUBMISSIONS_DIR:-evidence/world_class/submissions}"
+python3 scripts/yao.py world-class-submission-kit . --output-dir "$SUBMISSIONS_DIR"
+python3 scripts/yao.py world-class-intake . --submissions-dir "$SUBMISSIONS_DIR"
+python3 scripts/yao.py world-class-submission-review . --submissions-dir "$SUBMISSIONS_DIR"
+python3 scripts/yao.py world-class-ledger . --submissions-dir "$SUBMISSIONS_DIR"
+python3 scripts/yao.py world-class-runbook . --submissions-dir "$SUBMISSIONS_DIR"
 python3 scripts/yao.py world-class-claim-guard .
 python3 scripts/yao.py benchmark-reproducibility .
 ```
diff --git a/evidence/world_class/README.md b/evidence/world_class/README.md
index dda9f53..f50106a 100644
--- a/evidence/world_class/README.md
+++ b/evidence/world_class/README.md
@@ -7,9 +7,11 @@ The templates in `templates/` are review aids only. They do not count as accepte
 Run:
 
 ```bash
-python3 scripts/yao.py world-class-submission-kit . --output-dir /tmp/yao-world-class-submission-kit
-python3 scripts/yao.py world-class-intake .
-python3 scripts/yao.py world-class-submission-review .
+SUBMISSIONS_DIR="${SUBMISSIONS_DIR:-evidence/world_class/submissions}"
+python3 scripts/yao.py world-class-submission-kit . --output-dir "$SUBMISSIONS_DIR"
+python3 scripts/yao.py world-class-intake . --submissions-dir "$SUBMISSIONS_DIR"
+python3 scripts/yao.py world-class-submission-review . --submissions-dir "$SUBMISSIONS_DIR"
+python3 scripts/yao.py world-class-ledger . --submissions-dir "$SUBMISSIONS_DIR"
 ```
 
 The intake validator checks:
diff --git a/scripts/render_benchmark_reproducibility.py b/scripts/render_benchmark_reproducibility.py
index ba60929..1ca3f40 100644
--- a/scripts/render_benchmark_reproducibility.py
+++ b/scripts/render_benchmark_reproducibility.py
@@ -126,22 +126,22 @@ REPRODUCTION_COMMANDS = [
     },
     {
         "label": "world-class evidence ledger",
-        "command": "python3 scripts/yao.py world-class-ledger .",
+        "command": "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions",
         "evidence": "reports/world_class_evidence_ledger.json",
     },
     {
         "label": "world-class evidence intake",
-        "command": "python3 scripts/yao.py world-class-intake .",
+        "command": "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
         "evidence": "reports/world_class_evidence_intake.json",
     },
     {
         "label": "world-class submission review",
-        "command": "python3 scripts/yao.py world-class-submission-review .",
+        "command": "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions",
         "evidence": "reports/world_class_submission_review.json",
     },
     {
         "label": "world-class operator runbook",
-        "command": "python3 scripts/yao.py world-class-runbook .",
+        "command": "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions",
         "evidence": "reports/world_class_operator_runbook.json",
     },
     {
diff --git a/scripts/render_review_waivers.py b/scripts/render_review_waivers.py
index fcd6815..5936148 100644
--- a/scripts/render_review_waivers.py
+++ b/scripts/render_review_waivers.py
@@ -201,7 +201,10 @@ def world_class_boundary(skill_dir: Path) -> dict[str, Any] | None:
             "Keep claim guard active until ledger summary.ready_to_claim_world_class is true.",
         ],
         "suggested_evidence": "reports/world_class_evidence_ledger.md",
-        "suggested_command": "python3 scripts/yao.py world-class-ledger . && python3 scripts/yao.py world-class-claim-guard .",
+        "suggested_command": (
+            "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions "
+            "&& python3 scripts/yao.py world-class-claim-guard ."
+        ),
         "world_class_boundary": "Non-waivable completion boundary.",
     }
 
diff --git a/scripts/render_world_class_evidence_plan.py b/scripts/render_world_class_evidence_plan.py
index 31c097e..48d339c 100644
--- a/scripts/render_world_class_evidence_plan.py
+++ b/scripts/render_world_class_evidence_plan.py
@@ -149,7 +149,7 @@ def build_task(item: dict[str, Any]) -> dict[str, Any]:
     )
     intake_runbook = [
         f"Copy evidence/world_class/templates/{item['key']}.intake.json to evidence/world_class/submissions/{item['key']}.json and fill only real evidence fields.",
-        "python3 scripts/yao.py world-class-intake .",
+        "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions",
     ]
     intake_artifacts = [
         "evidence/world_class/intake.schema.json",
diff --git a/scripts/review_studio_actions.py b/scripts/review_studio_actions.py
index e7aa3ef..7f8a2c5 100644
--- a/scripts/review_studio_actions.py
+++ b/scripts/review_studio_actions.py
@@ -220,7 +220,11 @@ ACTION_GUIDANCE: dict[str, dict[str, Any]] = {
             {"path": "reports/runtime_permission_probes.md", "label": "runtime permission probes", "kind": "report", "patterns": ["# Runtime"]},
             {"path": "reports/adoption_drift_report.md", "label": "adoption drift", "kind": "report", "patterns": ["# Adoption"]},
         ],
-        "verification": "python3 scripts/yao.py world-class-runbook . && python3 scripts/yao.py world-class-ledger . && python3 scripts/yao.py review-studio .",
+        "verification": (
+            "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions "
+            "&& python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions "
+            "&& python3 scripts/yao.py review-studio ."
+        ),
     },
     "registry-audit": {
         "summary": "补齐 registry package metadata、checksum、license、owner、review cadence 和 install evidence。",
diff --git a/tests/verify_benchmark_reproducibility.py b/tests/verify_benchmark_reproducibility.py
index 8b9e4f2..5c60bfc 100644
--- a/tests/verify_benchmark_reproducibility.py
+++ b/tests/verify_benchmark_reproducibility.py
@@ -160,10 +160,10 @@ def main() -> None:
     assert artifacts["reports/world_class_claim_guard.json"]["exists"], artifacts
     assert artifacts["reports/python_compatibility.json"]["exists"], artifacts
     assert any(command["command"] == "make ci-test" for command in payload["reproduction_commands"]), payload
-    assert any(command["command"] == "python3 scripts/yao.py world-class-ledger ." for command in payload["reproduction_commands"]), payload
-    assert any(command["command"] == "python3 scripts/yao.py world-class-intake ." for command in payload["reproduction_commands"]), payload
-    assert any(command["command"] == "python3 scripts/yao.py world-class-submission-review ." for command in payload["reproduction_commands"]), payload
-    assert any(command["command"] == "python3 scripts/yao.py world-class-runbook ." for command in payload["reproduction_commands"]), payload
+    assert any(command["command"] == "python3 scripts/yao.py world-class-ledger . --submissions-dir evidence/world_class/submissions" for command in payload["reproduction_commands"]), payload
+    assert any(command["command"] == "python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions" for command in payload["reproduction_commands"]), payload
+    assert any(command["command"] == "python3 scripts/yao.py world-class-submission-review . --submissions-dir evidence/world_class/submissions" for command in payload["reproduction_commands"]), payload
+    assert any(command["command"] == "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions" for command in payload["reproduction_commands"]), payload
     assert any(command["command"] == "python3 scripts/yao.py world-class-claim-guard ." for command in payload["reproduction_commands"]), payload
     assert any(command["command"] == "python3 scripts/yao.py python-compat ." for command in payload["reproduction_commands"]), payload
     assert any("provider-backed" in item for item in payload["limitations"]), payload["limitations"]
@@ -178,7 +178,7 @@ def main() -> None:
     assert "## Evidence Bundle" in markdown, markdown
     assert "reports/benchmark_methodology.md" in markdown, markdown
     assert "reports/world_class_operator_runbook.html" in markdown, markdown
-    assert "python3 scripts/yao.py world-class-runbook ." in markdown, markdown
+    assert "python3 scripts/yao.py world-class-runbook . --submissions-dir evidence/world_class/submissions" in markdown, markdown
     assert "make ci-test" in markdown, markdown
     print(json.dumps({"ok": True}, ensure_ascii=False, indent=2))
 
diff --git a/tests/verify_review_studio.py b/tests/verify_review_studio.py
index 97ac71e..6ee762f 100644
--- a/tests/verify_review_studio.py
+++ b/tests/verify_review_studio.py
@@ -474,6 +474,7 @@ def main() -> None:
     }, world_class_action
     assert all(item["exists"] for item in world_class_action["source_refs"]), world_class_action
     assert "world-class-runbook" in world_class_action["verification_command"], world_class_action
+    assert "--submissions-dir evidence/world_class/submissions" in world_class_action["verification_command"], world_class_action
     assert "reports/world_class_operator_runbook.html" in world_class_action["source_fix"], world_class_action
     assert full_payload["data"]["world_class_evidence_ledger"]["summary"]["pending_count"] == 4, full_payload["data"]["world_class_evidence_ledger"]
     assert full_payload["data"]["world_class_evidence_intake"]["summary"]["decision"] == "awaiting-submissions", full_payload["data"]["world_class_evidence_intake"]
diff --git a/tests/verify_review_waivers.py b/tests/verify_review_waivers.py
index 62b817f..248565c 100644
--- a/tests/verify_review_waivers.py
+++ b/tests/verify_review_waivers.py
@@ -119,6 +119,7 @@ def main() -> None:
     assert candidates["world-class-evidence"]["waiver_allowed"] is False, candidates
     assert candidates["world-class-evidence"]["status"] == "cannot-waive", candidates
     assert "Non-waivable completion boundary" in candidates["world-class-evidence"]["world_class_boundary"], candidates
+    assert "--submissions-dir evidence/world_class/submissions" in candidates["world-class-evidence"]["suggested_command"], candidates
     root_markdown = root_report_md.read_text(encoding="utf-8")
     assert "Candidate Actions" in root_markdown, root_markdown
     assert "World-class evidence completion cannot be waived" in root_markdown, root_markdown
diff --git a/tests/verify_world_class_evidence_intake.py b/tests/verify_world_class_evidence_intake.py
index 4780b04..5e37ea9 100644
--- a/tests/verify_world_class_evidence_intake.py
+++ b/tests/verify_world_class_evidence_intake.py
@@ -100,9 +100,25 @@ def provider_submission(*, valid: bool, artifact_path: str = "reports/output_exe
     }
 
 
+def assert_documented_submission_commands() -> None:
+    expected_fragments = [
+        'SUBMISSIONS_DIR="${SUBMISSIONS_DIR:-evidence/world_class/submissions}"',
+        'world-class-submission-kit . --output-dir "$SUBMISSIONS_DIR"',
+        'world-class-intake . --submissions-dir "$SUBMISSIONS_DIR"',
+        'world-class-submission-review . --submissions-dir "$SUBMISSIONS_DIR"',
+        'world-class-ledger . --submissions-dir "$SUBMISSIONS_DIR"',
+    ]
+    for relative_path in ("README.md", "evidence/world_class/README.md"):
+        text = (ROOT / relative_path).read_text(encoding="utf-8")
+        for fragment in expected_fragments:
+            assert fragment in text, (relative_path, fragment)
+        assert "/tmp/yao-world-class-submission-kit" not in text, relative_path
+
+
 def main() -> None:
     shutil.rmtree(TMP, ignore_errors=True)
     TMP.mkdir(parents=True, exist_ok=True)
+    assert_documented_submission_commands()
     default_json = TMP / "world_class_evidence_intake.json"
     default_md = TMP / "world_class_evidence_intake.md"
     payload = run_intake("--output-json", str(default_json), "--output-md", str(default_md))
diff --git a/tests/verify_world_class_evidence_plan.py b/tests/verify_world_class_evidence_plan.py
index 548eaf1..1e16d69 100644
--- a/tests/verify_world_class_evidence_plan.py
+++ b/tests/verify_world_class_evidence_plan.py
@@ -55,7 +55,7 @@ def main() -> None:
     }, tasks
     assert set(requirements) == set(tasks), requirements
     assert any("--provider-runner openai" in command for command in tasks["provider-holdout"]["runbook"]), tasks["provider-holdout"]
-    assert any("world-class-intake" in command for command in tasks["provider-holdout"]["runbook"]), tasks["provider-holdout"]
+    assert any("world-class-intake . --submissions-dir evidence/world_class/submissions" in command for command in tasks["provider-holdout"]["runbook"]), tasks["provider-holdout"]
     assert any("evidence/world_class/templates/provider-holdout.intake.json" in command for command in tasks["provider-holdout"]["runbook"]), tasks["provider-holdout"]
     assert any("output_review_decisions.json" in command for command in tasks["human-adjudication"]["runbook"]), tasks["human-adjudication"]
     assert any("runtime-permissions" in command for command in tasks["native-permission-enforcement"]["runbook"]), tasks["native-permission-enforcement"]