[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C0PETN9AXWTHB5581WTR05":3,"skill-same:01M6C0PETN9AXWTHB5581WTR05":61},{"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":18,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6C0PETN9AXWTHB5581WTR05","ontology-validator",null,"Comprehensive ontology validation and quality assurance. Runs OWL reasoners, SHACL validation, CQ test suites, and ROBOT quality reports. Computes quality metrics and generates diff reports. Use when checking ontology quality or before committing changes.","beep-effect\u002Fbeep-effect","beep-effect","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F293012014?v=4","01M6C0KM5WSBFT39QDNXKH1JVY","Beep Effect","01M6C0KM9QBN9R26F3EHTSWR14",80,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fontology-validator\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"ontology validator","ontology","validator","test","validation","metrics","quality","use","quality assurance","diff","reports","robot","quality metrics","changes","when","2026-11-10 10:12:30",false,"---\nname: ontology-validator\ndescription: >\n  Comprehensive ontology validation and quality assurance. Runs OWL\n  reasoners, SHACL validation, CQ test suites, and ROBOT quality reports.\n  Computes quality metrics and generates diff reports. Use when checking\n  ontology quality or before committing changes.\n---\n\n# Ontology Validator\n\n## Role Statement\n\nYou are responsible for the evaluation phase — comprehensive validation\nacross logical, structural, and documentation dimensions. You run the\nfull quality checklist, report results, and flag issues for upstream\nskills to fix. You do NOT fix issues yourself (except trivial annotation\nfixes) — you report and hand back to the appropriate skill.\n\n## When to Activate\n\n- User mentions \"validate\", \"verify\", \"check\", \"quality\", or \"test\"\n- After any ontology modification (should be invoked automatically)\n- Before commits or releases\n- Pipeline A Step 5, Pipeline B Step 3, Pipeline C Step 2\n\n## Shared Reference Materials\n\nRead these files from `_shared\u002F` before beginning work:\n\n- `_shared\u002Fmethodology-backbone.md` — lifecycle phase context (Phase 6: Evaluation)\n- `_shared\u002Fquality-checklist.md` — the full validation checklist\n- `_shared\u002Fanti-patterns.md` — anti-pattern detection queries\n- `_shared\u002Fnaming-conventions.md` — naming compliance checks\n\n## Consistency vs. Validity (OWA vs. CWA)\n\nUse both OWL reasoning and SHACL; they answer different questions.\n\n- **OWL reasoning (Open World Assumption)** checks logical consistency.\n  Missing facts are treated as unknown, not false.\n- **SHACL validation (Closed World Assumption for the validated data)** checks\n  structural validity. Missing required data is a violation.\n\n| Check Type | Catches | Misses |\n|-----------|---------|--------|\n| OWL reasoner | Unsatisfiable classes, logical contradictions | Missing required annotations\u002Fdata |\n| SHACL | Missing properties, cardinality\u002Fdatatype violations | Logical inconsistency across axioms |\n\nA model can be logically consistent and still fail SHACL completeness checks.\nIt can also pass SHACL and still be logically inconsistent.\n\n## Core Workflow\n\n### Step 1: Logical Validation (Level 1)\n\n```bash\n# Consistency check with ELK (fast, for EL profile)\nrobot reason --reasoner ELK --input ontology.ttl\n\n# Consistency check with HermiT (complete, for full DL)\nrobot reason --reasoner HermiT --input ontology.ttl\n\n# Check for unsatisfiable classes\nrobot reason --reasoner HermiT --input ontology.ttl \\\n  --dump-unsatisfiable unsatisfiable.txt\n```\n\nIf inconsistent:\n1. Parse the reasoner explanation\n2. Identify the conflicting axioms\n3. Report the root cause\n4. Suggest a minimal fix\n5. Hand back to architect for resolution\n\n### Step 2: Quality Report (Level 2)\n\n```bash\nrobot report --input ontology.ttl \\\n  --fail-on ERROR \\\n  --output report.tsv\n```\n\nChecks: missing labels, missing definitions, multiple labels in same\nlanguage, deprecated term references, annotation whitespace issues.\n\n### Step 3: SHACL Validation (Level 3)\n\n```bash\nuv run pyshacl -s shapes\u002Fontology-shapes.ttl -i rdfs ontology.ttl -f human\n```\n\nStandard shapes:\n- Every class has `rdfs:label` (minCount 1)\n- Every class has `skos:definition` (minCount 1, severity: Warning)\n- No orphan classes (every class has a parent)\n- Domain\u002Frange constraints satisfied\n\n### Step 4: CQ Test Suite (Level 4)\n\n```bash\n# Run all CQ test queries\nrobot verify --input ontology.ttl \\\n  --queries ontologies\u002F{name}\u002Ftests\u002F \\\n  --output-dir test-results\u002F\n```\n\nFor each test:\n- Enumerative CQs: verify non-empty results\n- Constraint CQs: verify zero violations (zero-result queries pass)\n\n### Step 5: Coverage Metrics (Level 5)\n\nCalculate and report:\n\n| Metric | Target | Method |\n|--------|--------|--------|\n| Consistency | PASS | `robot reason` |\n| Label coverage | 100% | Count classes with `rdfs:label` |\n| Definition coverage | ≥ 80% | Count classes with `skos:definition` |\n| CQ test pass rate | 100% (Must-Have) | `robot verify` |\n| SHACL conformance | PASS | `pyshacl` |\n| Unsatisfiable classes | 0 | `robot reason` |\n| Orphan classes | 0 | SPARQL check |\n\n### Step 6: Evaluation Dimensions (Level 6)\n\nDocument qualitative assessments in the validation report:\n\n- **Semantic**: expressivity, complexity, granularity, epistemological adequacy\n- **Functional**: relevance to CQs, rigor of evidence, automation support\n- **Model-centric**: authoritativeness, structural coherence, formality level\n\nThese notes are not pass\u002Ffail automation checks; they are explicit review\njudgments with rationale.\n\n### Step 7: Diff Report (for PRs\u002Freleases)\n\n```bash\nrobot diff --left previous.ttl --right ontology.ttl \\\n  --format markdown --output diff.md\n```\n\n## Tool Commands\n\n### Anti-pattern detection queries\n\nRun SPARQL queries from `_shared\u002Fanti-patterns.md`:\n\n```bash\n# Singleton hierarchy detection\nrobot query --input ontology.ttl --query singleton-check.sparql --output singletons.csv\n\n# Orphan class detection\nrobot query --input ontology.ttl --query orphan-check.sparql --output orphans.csv\n\n# Missing disjointness detection\nrobot query --input ontology.ttl --query disjoint-check.sparql --output missing-disjoint.csv\n```\n\n### SSSOM validation (when applicable)\n\n```bash\nuv run sssom validate ontologies\u002F{name}\u002Fmappings\u002Fsource-to-target.sssom.tsv\n```\n\n### Naming convention compliance\n\n```bash\n# Check CamelCase class names (custom query)\nrobot query --input ontology.ttl --query naming-check.sparql --output naming-issues.csv\n```\n\n## Outputs\n\nThis skill produces:\n\n| Artifact | Location | Format | Description |\n|----------|----------|--------|-------------|\n| Validation report | `ontologies\u002F{name}\u002Fdocs\u002Fvalidation-report.md` | Markdown | Summary: pass\u002Ffail per check, metrics |\n| ROBOT report | `{name}-report.tsv` | TSV | Detailed quality report |\n| Test results | `test-results\u002F` | Directory | Per-CQ test outputs |\n| Diff report | `ontologies\u002F{name}\u002Fdocs\u002Fdiff.md` | Markdown | Changes between versions |\n| Unsatisfiable list | `unsatisfiable.txt` | Text | List of unsatisfiable classes (if any) |\n\n## Handoff\n\n**Receives from**:\n- `ontology-architect` — `ontologies\u002F{name}\u002F{name}.ttl`,\n  `ontologies\u002F{name}\u002Fshapes\u002F{name}-shapes.ttl`, `ontologies\u002F{name}\u002Ftests\u002F*.sparql`,\n  `ontologies\u002F{name}\u002Ftests\u002Fcq-test-manifest.yaml`, plus the auditor's\n  `work\u002Fdispositions.index.yaml` (evaluation must SEE the unresolved\u002Fdeferred\n  remainder — a green report over hidden open questions is a false green) (CQ tests originate from\n  `ontology-requirements` and are forwarded through `ontology-architect`)\n- `ontology-mapper` — `ontologies\u002F{name}\u002Fmappings\u002F*.sssom.tsv`\n- `ontology-curator` — modified `ontology.ttl`, KGCL change log\n\n**Passes to**: User (validation report) or back to upstream skill for fixes\n\n**Handoff checklist**:\n- [ ] All Level 1-6 checks have been executed\n- [ ] Validation report is generated and accessible\n- [ ] Any failures are clearly documented with root cause\n- [ ] Recommendations for fixes reference the appropriate upstream skill\n\n## Quality Report Format\n\n```markdown\n# Validation Report: {name}\nDate: {date}\n\n## Summary\n- Overall: PASS \u002F FAIL\n- Blocking issues: {count}\n- Warnings: {count}\n\n## Level 1: Logical Consistency\n- Status: PASS \u002F FAIL\n- Reasoner: {ELK\u002FHermiT}\n- Unsatisfiable classes: {count}\n\n## Level 2: ROBOT Report\n- Status: PASS \u002F FAIL\n- Errors: {count}\n- Warnings: {count}\n\n## Level 3: SHACL Validation\n- Status: PASS \u002F FAIL\n- Violations: {count}\n\n## Level 4: CQ Tests\n- Total: {count}\n- Passed: {count}\n- Failed: {count}\n- Failed tests: {list}\n\n## Level 5: Metrics\n| Metric | Value | Target | Status |\n|--------|-------|--------|--------|\n| Label coverage | X% | 100% | PASS\u002FFAIL |\n| Definition coverage | X% | ≥80% | PASS\u002FFAIL |\n| Orphan classes | N | 0 | PASS\u002FFAIL |\n\n## Level 6: Evaluation Dimensions\n- Semantic: {notes}\n- Functional: {notes}\n- Model-centric: {notes}\n\n## Level 7: Diff Review\n- Status: PASS \u002F FAIL\n- Summary: {high-level changes}\n```\n\n## Anti-Patterns to Avoid\n\n- **Shallow validation**: Don't just run the reasoner and declare success.\n  All six validation levels (plus diff review for releases\u002FPRs) must be checked.\n- **Ignoring warnings**: WARNINGs don't block commit but should be tracked\n  and addressed.\n- **Fixing in the wrong skill**: The validator reports; the architect or\n  curator fixes. Don't modify the ontology from the validator unless the\n  fix is trivial (e.g., adding a missing label).\n- **Skipping CQ tests**: CQ tests are acceptance criteria. A passing\n  reasoner with failing CQ tests means the ontology is logically consistent\n  but functionally incomplete.\n\n## Error Handling\n\nMissing validation prerequisites are blockers, not passing checks. The validator\nreports them and requests the owning role's output; it does not author replacement\nshapes or tests while acting as the evaluator.\n\n| Error | Likely Cause | Recovery |\n|-------|-------------|----------|\n| Reasoner timeout | Ontology too large or complex for HermiT | Switch to ELK; profile the ontology for complexity hotspots |\n| SHACL shapes file missing | Architect did not supply the prerequisite shapes | Report the SHACL check as NOT RUN and hand back to the architect to supply shapes; rerun validation after delivery |\n| CQ test files missing | Requirements skill output not available | Report CQ testing as NOT RUN and hand back to the requirements skill to supply tests from the competency questions; rerun after delivery |\n| ROBOT report fails to parse | Corrupt or malformed Turtle | Run `robot validate --input ontology.ttl` to find syntax errors |\n","# Ontology Validator\n\n## Role Statement\n\nYou are responsible for the evaluation phase — comprehensive validation\nacross logical, structural, and documentation dimensions. You run the\nfull quality checklist, report results, and flag issues for upstream\nskills to fix. You do NOT fix issues yourself (except trivial annotation\nfixes) — you report and hand back to the appropriate skill.\n\n## When to Activate\n\n- User mentions \"validate\", \"verify\", \"check\", \"quality\", or \"test\"\n- After any ontology modification (should be invoked automatically)\n- Before commits or releases\n- Pipeline A Step 5, Pipeline B Step 3, Pipeline C Step 2\n\n## Shared Reference Materials\n\nRead these files from `_shared\u002F` before beginning work:\n\n- `_shared\u002Fmethodology-backbone.md` — lifecycle phase context (Phase 6: Evaluation)\n- `_shared\u002Fquality-checklist.md` — the full validation checklist\n- `_shared\u002Fanti-patterns.md` — anti-pattern detection queries\n- `_shared\u002Fnaming-conventions.md` — naming compliance checks\n\n## Consistency vs. Validity (OWA vs. CWA)\n\nUse both OWL reasoning and SHACL; they answer different questions.\n\n- **OWL reasoning (Open World Assumption)** checks logical consistency.\n  Missing facts are treated as unknown, not false.\n- **SHACL validation (Closed World Assumption for the validated data)** checks\n  structural validity. Missing required data is a violation.\n\n| Check Type | Catches | Misses |\n|-----------|---------|--------|\n| OWL reasoner | Unsatisfiable classes, logical contradictions | Missing required annotations\u002Fdata |\n| SHACL | Missing properties, cardinality\u002Fdatatype violations | Logical inconsistency across axioms |\n\nA model can be logically consistent and still fail SHACL completeness checks.\nIt can also pass SHACL and still be logically inconsistent.\n\n## Core Workflow\n\n### Step 1: Logical Validation (Level 1)\n\n```bash\n# Consistency check with ELK (fast, for EL profile)\nrobot reason --reasoner ELK --input ontology.ttl\n\n# Consistency check with HermiT (complete, for full DL)\nrobot reason --reasoner HermiT --input ontology.ttl\n\n# Check for unsatisfiable classes\nrobot reason --reasoner HermiT --input ontology.ttl \\\n  --dump-unsatisfiable unsatisfiable.txt\n```\n\nIf inconsistent:\n1. Parse the reasoner explanation\n2. Identify the conflicting axioms\n3. Report the root cause\n4. Suggest a minimal fix\n5. Hand back to architect for resolution\n\n### Step 2: Quality Report (Level 2)\n\n```bash\nrobot report --input ontology.ttl \\\n  --fail-on ERROR \\\n  --output report.tsv\n```\n\nChecks: missing labels, missing definitions, multiple labels in same\nlanguage, deprecated term references, annotation whitespace issues.\n\n### Step 3: SHACL Validation (Level 3)\n\n```bash\nuv run pyshacl -s shapes\u002Fontology-shapes.ttl -i rdfs ontology.ttl -f human\n```\n\nStandard shapes:\n- Every class has `rdfs:label` (minCount 1)\n- Every class has `skos:definition` (minCount 1, severity: Warning)\n- No orphan classes (every class has a parent)\n- Domain\u002Frange constraints satisfied\n\n### Step 4: CQ Test Suite (Level 4)\n\n```bash\n# Run all CQ test queries\nrobot verify --input ontology.ttl \\\n  --queries ontologies\u002F{name}\u002Ftests\u002F \\\n  --output-dir test-results\u002F\n```\n\nFor each test:\n- Enumerative CQs: verify non-empty results\n- Constraint CQs: verify zero violations (zero-result queries pass)\n\n### Step 5: Coverage Metrics (Level 5)\n\nCalculate and report:\n\n| Metric | Target | Method |\n|--------|--------|--------|\n| Consistency | PASS | `robot reason` |\n| Label coverage | 100% | Count classes with `rdfs:label` |\n| Definition coverage | ≥ 80% | Count classes with `skos:definition` |\n| CQ test pass rate | 100% (Must-Have) | `robot verify` |\n| SHACL conformance | PASS | `pyshacl` |\n| Unsatisfiable classes | 0 | `robot reason` |\n| Orphan classes | 0 | SPARQL check |\n\n### Step 6: Evaluation Dimensions (Level 6)\n\nDocument qualitative assessments in the validation report:\n\n- **Semantic**: expressivity, complexity, granularity, epistemological adequacy\n- **Functional**: relevance to CQs, rigor of evidence, automation support\n- **Model-centric**: authoritativeness, structural coherence, formality level\n\nThese notes are not pass\u002Ffail automation checks; they are explicit review\njudgments with rationale.\n\n### Step 7: Diff Report (for PRs\u002Freleases)\n\n```bash\nrobot diff --left previous.ttl --right ontology.ttl \\\n  --format markdown --output diff.md\n```\n\n## Tool Commands\n\n### Anti-pattern detection queries\n\nRun SPARQL queries from `_shared\u002Fanti-patterns.md`:\n\n```bash\n# Singleton hierarchy detection\nrobot query --input ontology.ttl --query singleton-check.sparql --output singletons.csv\n\n# Orphan class detection\nrobot query --input ontology.ttl --query orphan-check.sparql --output orphans.csv\n\n# Missing disjointness detection\nrobot query --input ontology.ttl --query disjoint-check.sparql --output missing-disjoint.csv\n```\n\n### SSSOM validation (when applicable)\n\n```bash\nuv run sssom validate ontologies\u002F{name}\u002Fmappings\u002Fsource-to-target.sssom.tsv\n```\n\n### Naming convention compliance\n\n```bash\n# Check CamelCase class names (custom query)\nrobot query --input ontology.ttl --query naming-check.sparql --output naming-issues.csv\n```\n\n## Outputs\n\nThis skill produces:\n\n| Artifact | Location | Format | Description |\n|----------|----------|--------|-------------|\n| Validation report | `ontologies\u002F{name}\u002Fdocs\u002Fvalidation-report.md` | Markdown | Summary: pass\u002Ffail per check, metrics |\n| ROBOT report | `{name}-report.tsv` | TSV | Detailed quality report |\n| Test results | `test-results\u002F` | Directory | Per-CQ test outputs |\n| Diff report | `ontologies\u002F{name}\u002Fdocs\u002Fdiff.md` | Markdown | Changes between versions |\n| Unsatisfiable list | `unsatisfiable.txt` | Text | List of unsatisfiable classes (if any) |\n\n## Handoff\n\n**Receives from**:\n- `ontology-architect` — `ontologies\u002F{name}\u002F{name}.ttl`,\n  `ontologies\u002F{name}\u002Fshapes\u002F{name}-shapes.ttl`, `ontologies\u002F{name}\u002Ftests\u002F*.sparql`,\n  `ontologies\u002F{name}\u002Ftests\u002Fcq-test-manifest.yaml`, plus the auditor's\n  `work\u002Fdispositions.index.yaml` (evaluation must SEE the unresolved\u002Fdeferred\n  remainder — a green report over hidden open questions is a false green) (CQ tests originate from\n  `ontology-requirements` and are forwarded through `ontology-architect`)\n- `ontology-mapper` — `ontologies\u002F{name}\u002Fmappings\u002F*.sssom.tsv`\n- `ontology-curator` — modified `ontology.ttl`, KGCL change log\n\n**Passes to**: User (validation report) or back to upstream skill for fixes\n\n**Handoff checklist**:\n- [ ] All Level 1-6 checks have been executed\n- [ ] Validation report is generated and accessible\n- [ ] Any failures are clearly documented with root cause\n- [ ] Recommendations for fixes reference the appropriate upstream skill\n\n## Quality Report Format\n\n```markdown\n# Validation Report: {name}\nDate: {date}\n\n## Summary\n- Overall: PASS \u002F FAIL\n- Blocking issues: {count}\n- Warnings: {count}\n\n## Level 1: Logical Consistency\n- Status: PASS \u002F FAIL\n- Reasoner: {ELK\u002FHermiT}\n- Unsatisfiable classes: {count}\n\n## Level 2: ROBOT Report\n- Status: PASS \u002F FAIL\n- Errors: {count}\n- Warnings: {count}\n\n## Level 3: SHACL Validation\n- Status: PASS \u002F FAIL\n- Violations: {count}\n\n## Level 4: CQ Tests\n- Total: {count}\n- Passed: {count}\n- Failed: {count}\n- Failed tests: {list}\n\n## Level 5: Metrics\n| Metric | Value | Target | Status |\n|--------|-------|--------|--------|\n| Label coverage | X% | 100% | PASS\u002FFAIL |\n| Definition coverage | X% | ≥80% | PASS\u002FFAIL |\n| Orphan classes | N | 0 | PASS\u002FFAIL |\n\n## Level 6: Evaluation Dimensions\n- Semantic: {notes}\n- Functional: {notes}\n- Model-centric: {notes}\n\n## Level 7: Diff Review\n- Status: PASS \u002F FAIL\n- Summary: {high-level changes}\n```\n\n## Anti-Patterns to Avoid\n\n- **Shallow validation**: Don't just run the reasoner and declare success.\n  All six validation levels (plus diff review for releases\u002FPRs) must be checked.\n- **Ignoring warnings**: WARNINGs don't block commit but should be tracked\n  and addressed.\n- **Fixing in the wrong skill**: The validator reports; the architect or\n  curator fixes. Don't modify the ontology from the validator unless the\n  fix is trivial (e.g., adding a missing label).\n- **Skipping CQ tests**: CQ tests are acceptance criteria. A passing\n  reasoner with failing CQ tests means the ontology is logically consistent\n  but functionally incomplete.\n\n## Error Handling\n\nMissing validation prerequisites are blockers, not passing checks. The validator\nreports them and requests the owning role's output; it does not author replacement\nshapes or tests while acting as the evaluator.\n\n| Error | Likely Cause | Recovery |\n|-------|-------------|----------|\n| Reasoner timeout | Ontology too large or complex for HermiT | Switch to ELK; profile the ontology for complexity hotspots |\n| SHACL shapes file missing | Architect did not supply the prerequisite shapes | Report the SHACL check as NOT RUN and hand back to the architect to supply shapes; rerun validation after delivery |\n| CQ test files missing | Requirements skill output not available | Report CQ testing as NOT RUN and hand back to the requirements skill to supply tests from the competency questions; rerun after delivery |\n| ROBOT report fails to parse | Corrupt or malformed Turtle | Run `robot validate --input ontology.ttl` to find syntax errors |\n",{"name":5,"description":7},"main","2398f391338607e713c72b1f6f0c574dfc7a5199",".claude\u002Fskills\u002Fontology-validator",14,"https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect","https:\u002F\u002Fwww.oip.law","https:\u002F\u002Fgithub.com\u002Fbeep-effect","2026-11-15 03:19:50",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add beep-effect\u002Fbeep-effect --skill ontology-validator",{"tool":53,"command":54},"bunx","bunx skills add beep-effect\u002Fbeep-effect --skill ontology-validator",{"tool":56,"command":57},"pnpm","pnpm dlx skills add beep-effect\u002Fbeep-effect --skill ontology-validator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fontology-validator\u002FSKILL.md",true,[],[62,70,96,107,117,153],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":69},"01M72GGBGEZZJTXTRB3MNYPPY1","update-harnesses","Update every agent harness on every fleet host: T3 Code, Codex, Claude Code, Grok Build, Kimi Code, Junie, Cursor Agent and Muse on DankStation, beep-worker, dankserver, tbk-worker, tom-pc-1-wsl and the grok-bot VM, plus the desktop apps (ChatGPT and Claude Desktop on DankStation and grok-bot; Cursor and Kimi Desktop on DankStation). Use on `\u002Fupdate-harnesses`, when a harness is out of date somewhere, or to audit which versions and install methods each host runs.","https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fupdate-harnesses\u002FSKILL.md",[],[],"2026-11-10 18:39:20",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":34},"01M714DQT4JQHZ11X0RH0T8RQ7","auth-environments","Sign Claude Code in to a chosen Claude subscription on every linked T3 fleet host (grok-bot, beep-worker, dankserver, tbk-worker, tom-pc-1-wsl). Use when a Claude account hits its weekly limit, when `bun run beep accounts` shows the fleet's account used up, or on `\u002Fauth-environments`. Opens each host's OAuth page and a masked KDE code dialog together and verifies the admitted account.","https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fauth-environments\u002FSKILL.md",[],[77,78,79,80,81,82,83,84,85,86,33,87,88,89,90,91,92,93,94,95],"auth environments","environments","auth","python","weekly","workstation","up","worker","host","dialog","code","bot","active","run","fleet","canonical","path","limit","page",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":34},"01M6C0RK94T5QGSZ0K9TA5Q2EF","shadcn","Fixture for immutable shadcn skill provenance.","https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002Fpackages\u002Ftooling\u002Ftool\u002Fcli\u002Ftest\u002Ffixtures\u002Fskills-provenance\u002Fshadcn\u002Fupstream\u002FSKILL.md",[],[98,103,104,105,106],"immutable","provenance","fixture","for",{"skillNo":108,"name":109,"nameZh":6,"description":6,"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":34},"01M6C0RGPWMYM5KS62ZZPNAZ0W","qa-inventory-judge","https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002Fpackages\u002Ftooling\u002Ftool\u002Fcli\u002Fskills\u002Fqa-inventory-judge\u002FSKILL.md",[],[113,114,115,116],"qa inventory judge","judge","qa","inventory",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":121,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":129,"publishedAt":34},"01M6C0RDVR0A6W6ZJCJMEYJT77","practice-onboarding","Set up a lawyer's computer for their practice through the practice gateway. Use when the lawyer asks to get set up, to connect their documents, mail, calendar or practice tools, or when the practice gateway reports that setup is incomplete. Interviews the lawyer one question at a time, saves a practice profile, then checks and repairs the computer until setup is complete.","MIT","https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002Fapps\u002Fpractice-gateway\u002Fplugin\u002Fskills\u002Fpractice-onboarding\u002FSKILL.md",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[130,131,132,133,134,135,136,137,138,139,140,33,83,141,142,143,144,145,146,29,147,148,149,87,150,151,152],"onboarding","practice onboarding","guide","mail","interviews","at","calendar","gateway","SET","windows","setup","time","get","save","computer","profile","Tools","beep","status","desktop","documents","connect","question",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":162,"publishedAt":34},"01M6C0RB09NRJN0E1W3ND9HDE6","triage-nda","Screen NDAs before inventor disclosures or client pitches at Oppold IP Law. Flag disclosure, residuals, marking, term, and hidden IP rights for attorney review.","https:\u002F\u002Fgithub.com\u002Fbeep-effect\u002Fbeep-effect\u002Fblob\u002Fmain\u002Fapps\u002Fpractice-claude-mod\u002Fskills\u002Ftriage-nda\u002FSKILL.md",[159],{"categoryNo":160,"categoryName":161,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000037","律师与法务",[163,164,165,135,166,167,168,169,170,106,171,172,173,174,175,176,177],"nda","triage nda","triage","knowledge-work","legal","client","hidden","rights","2026","screen","ip","plugins","work","review","knowledge"]