Merge pull request #10 from yaojingang/codex/meta-skill-entrypoint-clarity

Clarify meta skill workflow boundaries

Author: yaojingang

SKILL.md

@@ -15,28 +15,28 @@ metadata:
 
 ## Modes
 
-- `Scaffold`: exploratory/personal. `Production`: team reuse. `Library`: shared infrastructure. `Governed`: high-trust, policy-sensitive, or release-critical.
+- `Scaffold`: exploratory/personal. `Production`: team reuse. `Library`: shared infra. `Governed`: high-trust/release-critical.
 - Rules: [Method](references/skill-engineering-method.md), [Operating Modes](references/operating-modes.md), [Resource Boundaries](references/resource-boundaries.md).
 
 ## Compact Workflow
 
-1. For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
-2. Capture job, output, exclusions, constraints, standards, and the lightest fit.
-3. Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.
-4. Write `description` early, test route quality, then add only earned folders and gates.
-5. Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful.
+1. One-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.
+2. Capture job, output, exclusions, constraints, standards, lightest fit.
+3. Scan up to `3-5` references: external, user, local; skip tiny edits; surface only uncertainty/conflict.
+4. Write `description` early; route/boundary edits need `trigger_eval.py`; releases need risk-matched gates before folders.
+5. Add output-risk, artifact-design, prompt-quality, system-model, next directions only when earned.
 
 Playbooks: [Method](references/skill-engineering-method.md), [Intent](references/intent-dialogue.md), [Skill IR](references/skill-ir-method.md), [Output Eval](references/output-eval-method.md), [Review Studio](references/review-studio-method.md).
 
 ## Skill OS 2.0 Gates
 
-For production, library, governed, or team-distributed work, run Skill IR, target compiler, trigger + output eval, Skill Atlas, conformance, trust, registry/package/install, upgrade, drift, waiver, and Review Studio gates before release.
+For production/library/governed/team releases, run Skill IR, compiler, trigger/output eval, Skill Atlas, conformance, trust, registry/package/install, upgrade, drift, waiver, Review Studio.
 
 ## Governed Package Boundary
 
-For file-backed, release-critical, or governed packages, name `input_files` as `file-backed fixture` evidence; include `owner`, `review cadence`, `input_files`, `output contract`, `rollback boundary`; require `trust report` and `reports/output_quality_scorecard.md`; mark unavailable telemetry, approvals, metrics, or benchmarks as `missing evidence`; do not fabricate evidence.
+For file-backed/release-critical/governed packages, name `input_files` as `file-backed fixture`; include `owner`, `review cadence`, `input_files`, `output contract`, `rollback boundary`; require `trust report` and `reports/output_quality_scorecard.md`; mark unavailable telemetry/approvals/metrics/benchmarks as `missing evidence`; do not fabricate evidence.
 
-Preserve audit labels literally when they apply: `file-backed fixture`, `input_files`, `output contract`, `rollback boundary`, `trust report`, `reports/output_quality_scorecard.md`, `missing evidence`.
+Preserve labels literally when they apply: `file-backed fixture`, `input_files`, `output contract`, `rollback boundary`, `trust report`, `reports/output_quality_scorecard.md`, `missing evidence`.
 
 ## First-Turn Style
 
@@ -46,8 +46,8 @@ Preserve audit labels literally when they apply: `file-backed fixture`, `input_f
 
 ## Output Contract
 
-Unless asked otherwise, produce `SKILL.md`, aligned `agents/interface.yaml`, justified assets, and a short summary of boundary, exclusions, gates, and next steps.
+Create/refactor/package: produce `SKILL.md`, aligned `agents/interface.yaml`, justified assets, boundary/exclusion/gate summary. Audit/evaluate-only: findings + proposed fixes; edit files only if asked. No-skill: no files.
 
 ## Reference Map
 
-Primary: [Method](references/skill-engineering-method.md), [Artifact Design](references/artifact-design-doctrine.md), [Systems Thinking](references/systems-thinking-doctrine.md), [Governance](references/governance.md), [SkillOps Decision](references/skillops-decision-policy.md).
+Primary: [Method](references/skill-engineering-method.md), [Artifact Design](references/artifact-design-doctrine.md), [Systems](references/systems-thinking-doctrine.md), [Governance](references/governance.md), [SkillOps](references/skillops-decision-policy.md).

registry/index.json

@@ -16,7 +16,7 @@
         "vscode"
       ],
       "package_metadata": "registry/packages/yao-meta-skill.json",
-      "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3"
+      "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c"
     }
   ]
 }

registry/packages/yao-meta-skill.json

@@ -16,7 +16,7 @@
   "trust_level": "local",
   "license": "MIT",
   "checksums": {
-    "package_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3",
+    "package_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
     "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7"
   },
   "compatibility": {

reports/adaptation_proposals.json

@@ -1,7 +1,7 @@
 {
   "schema_version": "1.0",
   "ok": true,
-  "generated_at": "2026-07-02T03:41:56Z",
+  "generated_at": "2026-07-02T06:33:07Z",
   "skill_dir": ".",
   "source_patterns": "reports/user_patterns.json",
   "pattern_count": 5,

reports/adaptation_proposals.md

@@ -1,6 +1,6 @@
 # Adaptation Proposals
 
-- Generated at: `2026-07-02T03:41:56Z`
+- Generated at: `2026-07-02T06:33:07Z`
 - Pattern report: `reports/user_patterns.json`
 - Proposal only: `true`
 - Writes repository files: `false`

reports/adoption_drift_report.json

@@ -1,7 +1,7 @@
 {
   "ok": true,
   "schema_version": "2.0",
-  "generated_at": "2026-07-02T03:42:30Z",
+  "generated_at": "2026-07-02T06:33:44Z",
   "skill_dir": ".",
   "privacy_contract": {
     "storage": "local-first",

reports/benchmark_reproducibility.json

@@ -3,46 +3,45 @@
   "ok": true,
   "generated_at": "2026-07-02",
   "skill_dir": ".",
-  "commit": "1710a5a3e0177313954758908735c147796e8981",
+  "commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
   "git_status": {
     "available": true,
     "dirty": true,
-    "changed_file_count": 84,
+    "changed_file_count": 37,
     "generated_dirty": true,
-    "generated_changed_file_count": 82,
+    "generated_changed_file_count": 36,
     "source_dirty": true,
-    "source_changed_file_count": 2,
+    "source_changed_file_count": 1,
     "sample": [
       " M SKILL.md",
-      " M evals/improved_description.txt",
       " M registry/index.json",
       " M registry/packages/yao-meta-skill.json",
       " M reports/adaptation_proposals.json",
       " M reports/adaptation_proposals.md",
       " M reports/adoption_drift_report.json",
-      " M reports/artifact-design-profile.json",
-      " M reports/artifact-design-profile.md",
-      " M reports/baseline-compare.json",
       " M reports/benchmark_reproducibility.json",
-      " M reports/benchmark_reproducibility.md"
+      " M reports/benchmark_reproducibility.md",
+      " M reports/compiled_targets.json",
+      " M reports/context_budget.json",
+      " M reports/context_budget.md",
+      " M reports/context_budget_summary.json"
     ],
     "source_sample": [
-      " M SKILL.md",
-      " M evals/improved_description.txt"
+      " M SKILL.md"
     ],
     "generated_sample": [
       " M registry/index.json",
       " M registry/packages/yao-meta-skill.json",
       " M reports/adaptation_proposals.json",
       " M reports/adaptation_proposals.md",
       " M reports/adoption_drift_report.json",
-      " M reports/artifact-design-profile.json",
-      " M reports/artifact-design-profile.md",
-      " M reports/baseline-compare.json",
       " M reports/benchmark_reproducibility.json",
       " M reports/benchmark_reproducibility.md",
-      " M reports/candidate_registry.json",
-      " M reports/candidate_registry.md"
+      " M reports/compiled_targets.json",
+      " M reports/context_budget.json",
+      " M reports/context_budget.md",
+      " M reports/context_budget_summary.json",
+      " M reports/evidence_consistency.json"
     ],
     "generated_dirty_prefixes": [
       "dist/",
@@ -60,8 +59,8 @@
     "methodology_complete": true,
     "required_artifact_count": 25,
     "missing_artifact_count": 0,
-    "evidence_bundle_sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873",
-    "source_contract_sha256": "e0863533e0a0f0b5069bace6a24d7adfb43d615453f08cff7578076a3cb1a2a3",
+    "evidence_bundle_sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158",
+    "source_contract_sha256": "db71157184dc649ee72dfcaf399204d44a366d942393d055571e0137d42c9f7c",
     "archive_sha256": "c56a8519244c0bc8ec17c92d4641c832629cc059f4b51fe177a2c039515253a7",
     "output_case_count": 5,
     "failure_disclosure_count": 3,
@@ -85,11 +84,11 @@
     "public_claim_ready": false,
     "public_claim_blocker_count": 4,
     "working_tree_dirty": true,
-    "changed_file_count": 84,
+    "changed_file_count": 37,
     "source_tree_dirty": true,
-    "source_changed_file_count": 2,
+    "source_changed_file_count": 1,
     "generated_tree_dirty": true,
-    "generated_changed_file_count": 82
+    "generated_changed_file_count": 36
   },
   "beta_test_release": {
     "ready": false,
@@ -135,10 +134,10 @@
   },
   "release_lock": {
     "ready": false,
-    "commit": "1710a5a3e0177313954758908735c147796e8981",
+    "commit": "24bea607a2b16e766bc8f2bc8483f22fae1edc61",
     "status_scope": "generation-time status before this report is written",
-    "source_changed_file_count": 2,
-    "generated_changed_file_count": 82,
+    "source_changed_file_count": 1,
+    "generated_changed_file_count": 36,
     "reason": "source files were dirty at generation time"
   },
   "evidence_bundle": {
@@ -147,7 +146,7 @@
     "existing_count": 25,
     "missing_count": 0,
     "missing_paths": [],
-    "sha256": "639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873"
+    "sha256": "6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158"
   },
   "methodology": {
     "path": "reports/benchmark_methodology.md",
@@ -256,7 +255,7 @@
       "path": "reports/security_trust_report.json",
       "exists": true,
       "bytes": 139090,
-      "sha256": "ffe2c88bbdbac4907bf8db8f01b9a6b2da78e83acdffb3d975e99424274cd9f7"
+      "sha256": "108aee597a1f245f73d9b69454b6fa8a144545f905231a7c314364c7066541c6"
     },
     {
       "label": "python_compatibility",
@@ -270,7 +269,7 @@
       "path": "reports/registry_audit.json",
       "exists": true,
       "bytes": 3155,
-      "sha256": "9be6de364d69a2ad40b68b460a35c91476e822eb008cfe4d5e8614c1e989d3d4"
+      "sha256": "d307675d5c6c3cd2f104ce7d963b37d36113f35334e4c6895b55fbb8b255e915"
     },
     {
       "label": "package_verification",
@@ -318,8 +317,8 @@
       "label": "world_class_evidence_preflight",
       "path": "reports/world_class_evidence_preflight.json",
       "exists": true,
-      "bytes": 90852,
-      "sha256": "a0b00eed5450b33ec29fea6652d41db216931452eeddd0d99f2d90aa20c44d95"
+      "bytes": 90854,
+      "sha256": "06e93b1c0c99107002466d9418a4910c82397bce26c3bbdd5b5cc9875eeb65b2"
     },
     {
       "label": "world_class_submission_review",
@@ -353,8 +352,8 @@
       "label": "world_class_claim_guard",
       "path": "reports/world_class_claim_guard.json",
       "exists": true,
-      "bytes": 20102,
-      "sha256": "5eb808496802e8f972e5aa738d99f3b4a37ff34c8ab495f25ff2db3e7237239f"
+      "bytes": 20713,
+      "sha256": "911ba833055ab857250f88d88ccdd0bb652076a81214f725c49d763352035572"
     }
   ],
   "missing_artifacts": [],

reports/benchmark_reproducibility.md

@@ -1,11 +1,11 @@
 # Benchmark Reproducibility
 
 Generated at: `2026-07-02`
-Commit: `1710a5a3e0177313954758908735c147796e8981`
+Commit: `24bea607a2b16e766bc8f2bc8483f22fae1edc61`
 Working tree dirty at generation: `true`
 Source tree dirty at generation: `true`
 Generated evidence dirty at generation: `true`
-Evidence bundle SHA256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873`
+Evidence bundle SHA256: `6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158`
 
 ## Summary
 
@@ -14,7 +14,7 @@ Evidence bundle SHA256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc3
 - methodology complete: `true`
 - required artifacts: `25`
 - missing artifacts: `0`
-- source contract sha256: `e0863533e0a0`
+- source contract sha256: `db71157184dc`
 - archive sha256: `c56a8519244c`
 - output cases: `5`
 - disclosed failure cases: `3`
@@ -28,9 +28,9 @@ Evidence bundle SHA256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc3
 - beta deferred evidence: `4`
 - public claim ready: `false`
 - public claim blockers: `4`
-- changed files at generation: `84`
-- source changed files at generation: `2`
-- generated changed files at generation: `82`
+- changed files at generation: `37`
+- source changed files at generation: `1`
+- generated changed files at generation: `36`
 
 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 and dirty samples are generation-time context; the evidence bundle SHA is the durable anchor for the artifacts listed below.
 
@@ -75,7 +75,7 @@ This report proves local benchmark reproducibility only. It keeps external provi
 
 - algorithm: `sha256(path,label,exists,artifact_sha256)`
 - artifacts: `25` / `25`
-- sha256: `639707e807e5ec8460f6aa6d1e5ba34874bb3228160555d8a01dbc37620d4873`
+- sha256: `6c95043c2d8513102b37bc70a01647246933c84e8a27c2748cc2cae20e040158`
 
 ## Methodology Sections
 
@@ -102,21 +102,21 @@ This report proves local benchmark reproducibility only. It keeps external provi
 | review_adjudication | `reports/output_review_adjudication.json` | present | `91fd88dd9b0f` |
 | trigger_scorecard | `reports/route_scorecard.json` | present | `53fc22d220dc` |
 | runtime_conformance | `reports/conformance_matrix.json` | present | `97f9ba949c23` |
-| trust_report | `reports/security_trust_report.json` | present | `ffe2c88bbdba` |
+| trust_report | `reports/security_trust_report.json` | present | `108aee597a1f` |
 | python_compatibility | `reports/python_compatibility.json` | present | `4d82942052a2` |
-| registry_audit | `reports/registry_audit.json` | present | `9be6de364d69` |
+| registry_audit | `reports/registry_audit.json` | present | `d307675d5c6c` |
 | package_verification | `reports/package_verification.json` | present | `e2ad726ce048` |
 | install_simulation | `reports/install_simulation.json` | present | `65adf51d8c4b` |
 | skill_os2_audit | `reports/skill_os2_audit.json` | present | `150c0027deaa` |
 | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `483ed2b3bd02` |
 | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `b19e7113ec46` |
 | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `885bff9c1c85` |
-| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `a0b00eed5450` |
+| world_class_evidence_preflight | `reports/world_class_evidence_preflight.json` | present | `06e93b1c0c99` |
 | world_class_submission_review | `reports/world_class_submission_review.json` | present | `e8df5c72ade7` |
 | world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `bb67813244d6` |
 | world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `e8d4dee75413` |
 | world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `022594013b24` |
-| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `5eb808496802` |
+| world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `911ba833055a` |
 
 ## Reproduction Commands