[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70H7QYSWS9EQJ8AQDQT8TEX":3,"skill-same:01M70H7QYSWS9EQJ8AQDQT8TEX":82},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M70H7QYSWS9EQJ8AQDQT8TEX","skill-stocktake",null,"Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.","mdnaimul22\u002Fhuman-skills","mdnaimul22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64520358?v=4","01M70FH95MH2H796Q01TYSFZ03","Naimul","01M70FH96798CQR4YHA13F17GA",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fskill-stocktake\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"skill stocktake","batch","Evaluation","subagent","quality","use","only","scan","commands","full","with","quick","for","modes","when","2026-11-10 10:12:30",false,"---\nname: skill-stocktake\ndescription: \"Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.\"\nmetadata:\n  origin: ECC\n---\n\n# skill-stocktake\n\nSlash command (`\u002Fskill-stocktake`) that audits all Claude skills and commands using a quality checklist + AI holistic judgment. Supports two modes: Quick Scan for recently changed skills, and Full Stocktake for a complete review.\n\n## Scope\n\nThe command targets the following paths **relative to the directory where it is invoked**:\n\n| Path | Description |\n|------|-------------|\n| `~\u002F.claude\u002Fskills\u002F` | Global skills (all projects) |\n| `{cwd}\u002F.claude\u002Fskills\u002F` | Project-level skills (if the directory exists) |\n\n**At the start of Phase 1, the command explicitly lists which paths were found and scanned.**\n\nDirectories named `.trash` are excluded from both scan modes: archived skills are not part of the live inventory. If an older `results.json` contains `.trash` entries, start a new Full Stocktake using the cache initialization below before resuming Quick Scan. An ordinary save merges entries and does not remove archived records.\n\n### Targeting a specific project\n\nTo include project-level skills, run from that project's root directory:\n\n```bash\ncd ~\u002Fpath\u002Fto\u002Fmy-project\n\u002Fskill-stocktake\n```\n\nIf the project has no `.claude\u002Fskills\u002F` directory, only global skills and commands are evaluated.\n\n## Modes\n\n| Mode | Trigger | Duration |\n|------|---------|---------|\n| Quick Scan | `results.json` exists (default) | 5–10 min |\n| Full Stocktake | `results.json` absent, or `\u002Fskill-stocktake full` | 20–30 min |\n\nThe shell scripts require Bash, Node.js, and `jq` on `PATH`.\n\n**Results cache:** `~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`\n\n## Quick Scan Flow\n\nRe-evaluate only skills that have changed since the last run (5–10 min).\n\n1. Read `~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`\n2. Run: `bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fquick-diff.sh \\\n         ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`\n   (Project dir is auto-detected from `$PWD\u002F.claude\u002Fskills`; pass it explicitly only if needed)\n3. If output is `[]`: report \"No changes since last run.\" and stop\n4. Re-evaluate only those changed files using the same Phase 2 criteria\n5. Carry forward unchanged skills from previous results\n6. Output only the diff\n7. Run: `bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n         ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json \u003C\u003C\u003C \"$EVAL_RESULTS\"`\n\n## Full Stocktake Flow\n\n### Phase 1 — Inventory\n\nRun this entire block in **one Bash invocation**. It prints the inventory for the agent and initializes a new full run only when there is no unfinished run to resume:\n\n```bash\n(\n  set -euo pipefail\n  SCAN_JSON=$(bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fscan.sh)\n  printf '%s\\n' \"$SCAN_JSON\"\n  RESULTS_JSON=~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json\n\n  CACHE_STATUS=\"\"\n  if [[ -f \"$RESULTS_JSON\" ]]; then\n    CACHE_STATUS=$(jq -r '.batch_progress.status \u002F\u002F \"\"' \"$RESULTS_JSON\")\n  fi\n  if [[ \"$CACHE_STATUS\" == \"in_progress\" ]]; then\n    RESUMED_RESULTS=$(jq --slurpfile saved \"$RESULTS_JSON\" '\n      . as $inventory | $saved[0]\n      | .skills = (.skills | to_entries\n        | map(.key = (.value.path \u002F\u002F .key))\n        | map(select(. as $entry\n          | $entry.value.mtime != null\n            and any($inventory.skills[];\n              .path == $entry.key and .mtime == $entry.value.mtime)))\n        | from_entries)\n      | .mode = \"full\"\n      | .batch_progress = {\n          total: ($inventory.skills | length),\n          evaluated: (.skills | length), status: \"in_progress\"\n        }\n    ' \u003C\u003C\u003C \"$SCAN_JSON\")\n    bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n      \"$RESULTS_JSON\" --replace \u003C\u003C\u003C \"$RESUMED_RESULTS\"\n  else\n    INITIAL_RESULTS=$(printf '%s\\n' \"$SCAN_JSON\" | jq '{\n      mode: \"full\", skills: {},\n      batch_progress: {total: (.skills | length), evaluated: 0, status: \"in_progress\"}\n    }')\n    bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n      \"$RESULTS_JSON\" --replace \u003C\u003C\u003C \"$INITIAL_RESULTS\"\n  fi\n)\n```\n\nThe script enumerates skill files, extracts frontmatter, and collects UTC mtimes.\nProject dir is auto-detected from `$PWD\u002F.claude\u002Fskills`; pass it explicitly only if needed.\nPresent the scan summary and inventory table from the script output:\n\n```\nScanning:\n  ✓ ~\u002F.claude\u002Fskills\u002F         (17 files)\n  ✗ {cwd}\u002F.claude\u002Fskills\u002F    (not found — global skills only)\n```\n\n| Skill | 7d use | 30d use | Description |\n|-------|--------|---------|-------------|\n\nUsage counts come from the optional `~\u002F.claude\u002Fobservations.jsonl` file (overridable with `SKILL_STOCKTAKE_OBSERVATIONS`), which Claude Code does not create by default. When the file is absent, `use_7d` and `use_30d` are JSON `null`; display them as **unmeasured** in inventory and summary tables. A numeric `0` means the file exists but contains no matching Read observations in that window. Missing usage data is never evidence for retiring a skill.\n\n`--replace` writes a complete cache snapshot. A new run starts with an empty evaluation; a resumed run instead keeps a saved evaluation only when its path is still live and its saved, non-null mtime matches the fresh inventory. Changed skills and entries without an mtime require re-evaluation. It removes archived\u002Fdeleted entries and refreshes the progress counts even when no new batch remains. Existing name-keyed entries are normalized using their saved `path`. Never use the empty initialization payload for a resume. Later chunks, completion updates, and Quick Scans must omit `--replace` so they merge into the current run instead of losing earlier results.\n\n### Phase 2 — Quality Evaluation\n\nLaunch an Agent tool subagent (**general-purpose agent**) with the actual JSON emitted by Phase 1 and the checklist below. Copy the inventory values into the prompt itself; shell variables do not carry over into Agent calls. Include the full inventory for overlap checks and explicitly identify the paths in the current batch to evaluate. Do not send literal inventory or checklist placeholders.\n\nThe subagent reads each assigned skill, applies the checklist, and returns a JSON object with a `skills` map keyed by the inventory path. Each entry includes its `path`, scanned `mtime`, `verdict`, and self-contained `reason`. Use the same path keys across all batches so merging results cannot overwrite a different skill with the same name.\n\n**Chunk guidance:** Process ~20 skills per subagent invocation to keep context manageable. After each chunk, wrap its returned `skills` map with `mode: \"full\"` and `batch_progress: {total, evaluated, status: \"in_progress\"}`. Set `total` to the inventory size and `evaluated` to the cumulative number of distinct evaluated paths, including saved batches. Assign this JSON to `CHUNK_RESULTS` and run the following command in the **same Bash invocation as that assignment**:\n\n```bash\nbash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n  ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json \u003C\u003C\u003C \"$CHUNK_RESULTS\"\n```\n\nAfter all skills are evaluated, persist completion before proceeding to Phase 3:\n\n```bash\n(\n  set -euo pipefail\n  RESULTS_JSON=~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json\n  COMPLETED_RESULTS=$(jq -e '\n    if (.skills | length) == .batch_progress.total then\n      {skills: {}, mode: \"full\", batch_progress: (.batch_progress + {\n        evaluated: (.skills | length), status: \"completed\"\n      })}\n    else error(\"Inventory still has unevaluated skills\") end\n  ' \"$RESULTS_JSON\")\n  bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n    \"$RESULTS_JSON\" \u003C\u003C\u003C \"$COMPLETED_RESULTS\"\n)\n```\n\n**Resume detection:** If `status: \"in_progress\"` is found on startup, run Phase 1 to reconcile the saved results with the fresh inventory, then evaluate only paths absent from the reconciled `skills` map. If none remain, persist completion immediately. Completed evaluations are preserved only for surviving paths with matching, non-null mtimes; new or changed skills and entries without an mtime require evaluation.\n\nEach skill is evaluated against this checklist:\n\n```\n- [ ] Content overlap with other skills checked\n- [ ] Overlap with MEMORY.md \u002F CLAUDE.md checked\n- [ ] Freshness of technical references verified (use WebSearch if tool names \u002F CLI flags \u002F APIs are present)\n- [ ] Usage frequency considered when measured; missing observations marked unmeasured, not treated as zero\n```\n\nVerdict criteria:\n\n| Verdict | Meaning |\n|---------|---------|\n| Keep | Useful and current |\n| Improve | Worth keeping, but specific improvements needed |\n| Update | Referenced technology is outdated (verify with WebSearch) |\n| Retire | Low quality, stale, or cost-asymmetric |\n| Merge into [X] | Substantial overlap with another skill; name the merge target |\n\nEvaluation is **holistic AI judgment** — not a numeric rubric. Guiding dimensions:\n- **Actionability**: code examples, commands, or steps that let you act immediately\n- **Scope fit**: name, trigger, and content are aligned; not too broad or narrow\n- **Uniqueness**: value not replaceable by MEMORY.md \u002F CLAUDE.md \u002F another skill\n- **Currency**: technical references work in the current environment\n\n**Reason quality requirements** — the `reason` field must be self-contained and decision-enabling:\n- Do NOT write \"unchanged\" alone — always restate the core evidence\n- For **Retire**: state (1) what specific defect was found, (2) what covers the same need instead\n  - Bad: `\"Superseded\"`\n  - Good: `\"disable-model-invocation: true already set; superseded by continuous-learning-v2 which covers all the same patterns plus confidence scoring. No unique content remains.\"`\n- For **Merge**: name the target and describe what content to integrate\n  - Bad: `\"Overlaps with X\"`\n  - Good: `\"42-line thin content; Step 4 of chatlog-to-article already covers the same workflow. Integrate the 'article angle' tip as a note in that skill.\"`\n- For **Improve**: describe the specific change needed (what section, what action, target size if relevant)\n  - Bad: `\"Too long\"`\n  - Good: `\"276 lines; Section 'Framework Comparison' (L80–140) duplicates ai-era-architecture-principles; delete it to reach ~150 lines.\"`\n- For **Keep** (mtime-only change in Quick Scan): restate the original verdict rationale, do not write \"unchanged\"\n  - Bad: `\"Unchanged\"`\n  - Good: `\"mtime updated but content unchanged. Unique Python reference explicitly imported by rules\u002Fpython\u002F; no overlap found.\"`\n\n### Phase 3 — Summary Table\n\n| Skill | 7d use | Verdict | Reason |\n|-------|--------|---------|--------|\n\n### Phase 4 — Consolidation\n\n1. **Retire \u002F Merge**: present detailed justification per file before confirming with user:\n   - What specific problem was found (overlap, staleness, broken references, etc.)\n   - What alternative covers the same functionality (for Retire: which existing skill\u002Frule; for Merge: the target file and what content to integrate)\n   - Impact of removal (any dependent skills, MEMORY.md references, or workflows affected)\n2. **Improve**: present specific improvement suggestions with rationale:\n   - What to change and why (e.g., \"trim 430→200 lines because sections X\u002FY duplicate python-patterns\")\n   - User decides whether to act\n3. **Update**: present updated content with sources checked\n4. Check MEMORY.md line count; propose compression if >100 lines\n\n## Results File Schema\n\n`~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`:\n\n**`evaluated_at`**: Must be set to the actual UTC time of evaluation completion.\nObtain via Bash: `date -u +%Y-%m-%dT%H:%M:%SZ`. Never use a date-only approximation like `T00:00:00Z`.\n\n```json\n{\n  \"evaluated_at\": \"2026-02-21T10:00:00Z\",\n  \"mode\": \"full\",\n  \"batch_progress\": {\n    \"total\": 80,\n    \"evaluated\": 80,\n    \"status\": \"completed\"\n  },\n  \"skills\": {\n    \"~\u002F.claude\u002Fskills\u002Fskill-name\u002FSKILL.md\": {\n      \"path\": \"~\u002F.claude\u002Fskills\u002Fskill-name\u002FSKILL.md\",\n      \"verdict\": \"Keep\",\n      \"reason\": \"Concrete, actionable, unique value for X workflow\",\n      \"mtime\": \"2026-01-15T08:30:00Z\"\n    }\n  }\n}\n```\n\n## Notes\n\n- Evaluation is blind: the same checklist applies to all skills regardless of origin (ECC, self-authored, auto-extracted)\n- Archive \u002F delete operations always require explicit user confirmation\n- No verdict branching by skill origin\n","# skill-stocktake\n\nSlash command (`\u002Fskill-stocktake`) that audits all Claude skills and commands using a quality checklist + AI holistic judgment. Supports two modes: Quick Scan for recently changed skills, and Full Stocktake for a complete review.\n\n## Scope\n\nThe command targets the following paths **relative to the directory where it is invoked**:\n\n| Path | Description |\n|------|-------------|\n| `~\u002F.claude\u002Fskills\u002F` | Global skills (all projects) |\n| `{cwd}\u002F.claude\u002Fskills\u002F` | Project-level skills (if the directory exists) |\n\n**At the start of Phase 1, the command explicitly lists which paths were found and scanned.**\n\nDirectories named `.trash` are excluded from both scan modes: archived skills are not part of the live inventory. If an older `results.json` contains `.trash` entries, start a new Full Stocktake using the cache initialization below before resuming Quick Scan. An ordinary save merges entries and does not remove archived records.\n\n### Targeting a specific project\n\nTo include project-level skills, run from that project's root directory:\n\n```bash\ncd ~\u002Fpath\u002Fto\u002Fmy-project\n\u002Fskill-stocktake\n```\n\nIf the project has no `.claude\u002Fskills\u002F` directory, only global skills and commands are evaluated.\n\n## Modes\n\n| Mode | Trigger | Duration |\n|------|---------|---------|\n| Quick Scan | `results.json` exists (default) | 5–10 min |\n| Full Stocktake | `results.json` absent, or `\u002Fskill-stocktake full` | 20–30 min |\n\nThe shell scripts require Bash, Node.js, and `jq` on `PATH`.\n\n**Results cache:** `~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`\n\n## Quick Scan Flow\n\nRe-evaluate only skills that have changed since the last run (5–10 min).\n\n1. Read `~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`\n2. Run: `bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fquick-diff.sh \\\n         ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`\n   (Project dir is auto-detected from `$PWD\u002F.claude\u002Fskills`; pass it explicitly only if needed)\n3. If output is `[]`: report \"No changes since last run.\" and stop\n4. Re-evaluate only those changed files using the same Phase 2 criteria\n5. Carry forward unchanged skills from previous results\n6. Output only the diff\n7. Run: `bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n         ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json \u003C\u003C\u003C \"$EVAL_RESULTS\"`\n\n## Full Stocktake Flow\n\n### Phase 1 — Inventory\n\nRun this entire block in **one Bash invocation**. It prints the inventory for the agent and initializes a new full run only when there is no unfinished run to resume:\n\n```bash\n(\n  set -euo pipefail\n  SCAN_JSON=$(bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fscan.sh)\n  printf '%s\\n' \"$SCAN_JSON\"\n  RESULTS_JSON=~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json\n\n  CACHE_STATUS=\"\"\n  if [[ -f \"$RESULTS_JSON\" ]]; then\n    CACHE_STATUS=$(jq -r '.batch_progress.status \u002F\u002F \"\"' \"$RESULTS_JSON\")\n  fi\n  if [[ \"$CACHE_STATUS\" == \"in_progress\" ]]; then\n    RESUMED_RESULTS=$(jq --slurpfile saved \"$RESULTS_JSON\" '\n      . as $inventory | $saved[0]\n      | .skills = (.skills | to_entries\n        | map(.key = (.value.path \u002F\u002F .key))\n        | map(select(. as $entry\n          | $entry.value.mtime != null\n            and any($inventory.skills[];\n              .path == $entry.key and .mtime == $entry.value.mtime)))\n        | from_entries)\n      | .mode = \"full\"\n      | .batch_progress = {\n          total: ($inventory.skills | length),\n          evaluated: (.skills | length), status: \"in_progress\"\n        }\n    ' \u003C\u003C\u003C \"$SCAN_JSON\")\n    bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n      \"$RESULTS_JSON\" --replace \u003C\u003C\u003C \"$RESUMED_RESULTS\"\n  else\n    INITIAL_RESULTS=$(printf '%s\\n' \"$SCAN_JSON\" | jq '{\n      mode: \"full\", skills: {},\n      batch_progress: {total: (.skills | length), evaluated: 0, status: \"in_progress\"}\n    }')\n    bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n      \"$RESULTS_JSON\" --replace \u003C\u003C\u003C \"$INITIAL_RESULTS\"\n  fi\n)\n```\n\nThe script enumerates skill files, extracts frontmatter, and collects UTC mtimes.\nProject dir is auto-detected from `$PWD\u002F.claude\u002Fskills`; pass it explicitly only if needed.\nPresent the scan summary and inventory table from the script output:\n\n```\nScanning:\n  ✓ ~\u002F.claude\u002Fskills\u002F         (17 files)\n  ✗ {cwd}\u002F.claude\u002Fskills\u002F    (not found — global skills only)\n```\n\n| Skill | 7d use | 30d use | Description |\n|-------|--------|---------|-------------|\n\nUsage counts come from the optional `~\u002F.claude\u002Fobservations.jsonl` file (overridable with `SKILL_STOCKTAKE_OBSERVATIONS`), which Claude Code does not create by default. When the file is absent, `use_7d` and `use_30d` are JSON `null`; display them as **unmeasured** in inventory and summary tables. A numeric `0` means the file exists but contains no matching Read observations in that window. Missing usage data is never evidence for retiring a skill.\n\n`--replace` writes a complete cache snapshot. A new run starts with an empty evaluation; a resumed run instead keeps a saved evaluation only when its path is still live and its saved, non-null mtime matches the fresh inventory. Changed skills and entries without an mtime require re-evaluation. It removes archived\u002Fdeleted entries and refreshes the progress counts even when no new batch remains. Existing name-keyed entries are normalized using their saved `path`. Never use the empty initialization payload for a resume. Later chunks, completion updates, and Quick Scans must omit `--replace` so they merge into the current run instead of losing earlier results.\n\n### Phase 2 — Quality Evaluation\n\nLaunch an Agent tool subagent (**general-purpose agent**) with the actual JSON emitted by Phase 1 and the checklist below. Copy the inventory values into the prompt itself; shell variables do not carry over into Agent calls. Include the full inventory for overlap checks and explicitly identify the paths in the current batch to evaluate. Do not send literal inventory or checklist placeholders.\n\nThe subagent reads each assigned skill, applies the checklist, and returns a JSON object with a `skills` map keyed by the inventory path. Each entry includes its `path`, scanned `mtime`, `verdict`, and self-contained `reason`. Use the same path keys across all batches so merging results cannot overwrite a different skill with the same name.\n\n**Chunk guidance:** Process ~20 skills per subagent invocation to keep context manageable. After each chunk, wrap its returned `skills` map with `mode: \"full\"` and `batch_progress: {total, evaluated, status: \"in_progress\"}`. Set `total` to the inventory size and `evaluated` to the cumulative number of distinct evaluated paths, including saved batches. Assign this JSON to `CHUNK_RESULTS` and run the following command in the **same Bash invocation as that assignment**:\n\n```bash\nbash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n  ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json \u003C\u003C\u003C \"$CHUNK_RESULTS\"\n```\n\nAfter all skills are evaluated, persist completion before proceeding to Phase 3:\n\n```bash\n(\n  set -euo pipefail\n  RESULTS_JSON=~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json\n  COMPLETED_RESULTS=$(jq -e '\n    if (.skills | length) == .batch_progress.total then\n      {skills: {}, mode: \"full\", batch_progress: (.batch_progress + {\n        evaluated: (.skills | length), status: \"completed\"\n      })}\n    else error(\"Inventory still has unevaluated skills\") end\n  ' \"$RESULTS_JSON\")\n  bash ~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh \\\n    \"$RESULTS_JSON\" \u003C\u003C\u003C \"$COMPLETED_RESULTS\"\n)\n```\n\n**Resume detection:** If `status: \"in_progress\"` is found on startup, run Phase 1 to reconcile the saved results with the fresh inventory, then evaluate only paths absent from the reconciled `skills` map. If none remain, persist completion immediately. Completed evaluations are preserved only for surviving paths with matching, non-null mtimes; new or changed skills and entries without an mtime require evaluation.\n\nEach skill is evaluated against this checklist:\n\n```\n- [ ] Content overlap with other skills checked\n- [ ] Overlap with MEMORY.md \u002F CLAUDE.md checked\n- [ ] Freshness of technical references verified (use WebSearch if tool names \u002F CLI flags \u002F APIs are present)\n- [ ] Usage frequency considered when measured; missing observations marked unmeasured, not treated as zero\n```\n\nVerdict criteria:\n\n| Verdict | Meaning |\n|---------|---------|\n| Keep | Useful and current |\n| Improve | Worth keeping, but specific improvements needed |\n| Update | Referenced technology is outdated (verify with WebSearch) |\n| Retire | Low quality, stale, or cost-asymmetric |\n| Merge into [X] | Substantial overlap with another skill; name the merge target |\n\nEvaluation is **holistic AI judgment** — not a numeric rubric. Guiding dimensions:\n- **Actionability**: code examples, commands, or steps that let you act immediately\n- **Scope fit**: name, trigger, and content are aligned; not too broad or narrow\n- **Uniqueness**: value not replaceable by MEMORY.md \u002F CLAUDE.md \u002F another skill\n- **Currency**: technical references work in the current environment\n\n**Reason quality requirements** — the `reason` field must be self-contained and decision-enabling:\n- Do NOT write \"unchanged\" alone — always restate the core evidence\n- For **Retire**: state (1) what specific defect was found, (2) what covers the same need instead\n  - Bad: `\"Superseded\"`\n  - Good: `\"disable-model-invocation: true already set; superseded by continuous-learning-v2 which covers all the same patterns plus confidence scoring. No unique content remains.\"`\n- For **Merge**: name the target and describe what content to integrate\n  - Bad: `\"Overlaps with X\"`\n  - Good: `\"42-line thin content; Step 4 of chatlog-to-article already covers the same workflow. Integrate the 'article angle' tip as a note in that skill.\"`\n- For **Improve**: describe the specific change needed (what section, what action, target size if relevant)\n  - Bad: `\"Too long\"`\n  - Good: `\"276 lines; Section 'Framework Comparison' (L80–140) duplicates ai-era-architecture-principles; delete it to reach ~150 lines.\"`\n- For **Keep** (mtime-only change in Quick Scan): restate the original verdict rationale, do not write \"unchanged\"\n  - Bad: `\"Unchanged\"`\n  - Good: `\"mtime updated but content unchanged. Unique Python reference explicitly imported by rules\u002Fpython\u002F; no overlap found.\"`\n\n### Phase 3 — Summary Table\n\n| Skill | 7d use | Verdict | Reason |\n|-------|--------|---------|--------|\n\n### Phase 4 — Consolidation\n\n1. **Retire \u002F Merge**: present detailed justification per file before confirming with user:\n   - What specific problem was found (overlap, staleness, broken references, etc.)\n   - What alternative covers the same functionality (for Retire: which existing skill\u002Frule; for Merge: the target file and what content to integrate)\n   - Impact of removal (any dependent skills, MEMORY.md references, or workflows affected)\n2. **Improve**: present specific improvement suggestions with rationale:\n   - What to change and why (e.g., \"trim 430→200 lines because sections X\u002FY duplicate python-patterns\")\n   - User decides whether to act\n3. **Update**: present updated content with sources checked\n4. Check MEMORY.md line count; propose compression if >100 lines\n\n## Results File Schema\n\n`~\u002F.claude\u002Fskills\u002Fskill-stocktake\u002Fresults.json`:\n\n**`evaluated_at`**: Must be set to the actual UTC time of evaluation completion.\nObtain via Bash: `date -u +%Y-%m-%dT%H:%M:%SZ`. Never use a date-only approximation like `T00:00:00Z`.\n\n```json\n{\n  \"evaluated_at\": \"2026-02-21T10:00:00Z\",\n  \"mode\": \"full\",\n  \"batch_progress\": {\n    \"total\": 80,\n    \"evaluated\": 80,\n    \"status\": \"completed\"\n  },\n  \"skills\": {\n    \"~\u002F.claude\u002Fskills\u002Fskill-name\u002FSKILL.md\": {\n      \"path\": \"~\u002F.claude\u002Fskills\u002Fskill-name\u002FSKILL.md\",\n      \"verdict\": \"Keep\",\n      \"reason\": \"Concrete, actionable, unique value for X workflow\",\n      \"mtime\": \"2026-01-15T08:30:00Z\"\n    }\n  }\n}\n```\n\n## Notes\n\n- Evaluation is blind: the same checklist applies to all skills regardless of origin (ECC, self-authored, auto-extracted)\n- Archive \u002F delete operations always require explicit user confirmation\n- No verdict branching by skill origin\n",{"name":5,"metadata":44,"description":7},{"origin":45},"ECC","main","74715deacdc69119d739f38916f8ee4f0f979ebf","skills\u002Fstorage\u002Faffaan-m_ECC\u002Fskill-stocktake",0,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills","https:\u002F\u002Fgithub.com\u002Fmdnaimul22","AI Agents Workflows Automation | Specializing in Python, FastAPI, MCP Agents & Custom ERP.","2026-11-11 21:16:57",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add mdnaimul22\u002Fhuman-skills --skill skill-stocktake",{"tool":60,"command":61},"bunx","bunx skills add mdnaimul22\u002Fhuman-skills --skill skill-stocktake",{"tool":63,"command":64},"pnpm","pnpm dlx skills add mdnaimul22\u002Fhuman-skills --skill skill-stocktake","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fskill-stocktake\u002FSKILL.md",true,[68,74,78],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fquick-diff.sh","SCRIPT","脚本",4583,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fskill-stocktake\u002Fscripts\u002Fquick-diff.sh",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fsave-results.sh",2764,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fskill-stocktake\u002Fscripts\u002Fsave-results.sh",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fscan.sh",7532,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fskill-stocktake\u002Fscripts\u002Fscan.sh",[83,91,99,106,113,120],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":90},"01M767791C1KRP2ZRW2Z73VZ5Q","system-lifecycle-designer","Universal architectural methodology for designing granular, atomic, and sub-atomic lifecycles and end-to-end workflows for single functionality integrations across any domain (daemons, batch jobs, request transactions, resource pools). Provides patterns for deterministic identity, pre-commit validation, differential reconciliation, sticky leasing, state machines, transactional persistence, and closed-loop feedback.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fmy_skills\u002Fsystem-lifecycle-designer\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":98},"01M748ABPN5F1FANHH6HKZQMXT","style-sampling","Make a new episode in a proven video style - Collage Explainer, Finance Explainer, Animated Science Explainer, 3D Brand Explainer, 3D True Crime - on the person's topic. Use for \"an episode of\", \"in the style of\", \"sample this style\", 「用这个风格做一集」. One video to copy is reverse-any-video.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Fstyle-sampling\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":98},"01M748A59V04PKW4HA0XQ81FGP","reverse-any-video","Rebuild any video file as an editable HyperFrames project - motion graphics, talking heads, live action or AI-generated footage - checked against the original frame by frame. Use to reverse, recreate, remake, replicate or copy a video, or 「复刻这个视频」「照着这个视频做一个」.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fheygen-com_hyperframes\u002Freverse-any-video\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":98},"01M7487T50P55CSXMWXZ0G9KRG","typescript-patterns","TypeScript patterns for strict, type-safe, maintainable code in modern TypeScript and JavaScript applications. Covers strict compiler configuration, type design, narrowing, discriminated unions, generics, async and error handling, module boundaries, dependency hygiene, and type-level testing. Use when writing or reviewing TypeScript or JavaScript code.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftypescript-patterns\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":98},"01M7487ERZRGPC5NJ75077Y238","test-collaboration","Inventory and govern a project's test assets. Connect requirements, business rules, risks, bugs, and cross-boundary contracts to stable TEST-IDs and executable evidence in the repository's existing test registry or TESTS.md. Use for test inventory, test gap analysis, unit\u002Fintegration\u002Fcontract\u002FE2E\u002Fsmoke classification, bug-to-test regression protection, consumer\u002Fprovider contract testing, test-necessity review, and pre-delivery evidence review.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ftest-collaboration\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":98},"01M748721J3GKR2WS6K0QWFC35","story-lifecycle","Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira\u002FLinear\u002FTaiga but needs structured delivery tracking.","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Fstory-lifecycle\u002FSKILL.md",[],[]]