{"id":"0ba02b1d-629e-4cd9-9d0a-999a247c7913","shortId":"VhbJ3U","kind":"skill","title":"skill-check","tagline":"Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.","description":"# SkillCheck\n\n## Overview\n\nValidate SKILL.md files against the [agentskills specification](https://agentskills.io) and Anthropic best practices. Catches structural errors, semantic contradictions, naming anti-patterns, and quality gaps in a single read-only pass.\n\n## When to Use This Skill\n\n- Use when user says \"check skill\", \"skillcheck\", or \"validate SKILL.md\"\n- Use when reviewing a skill before publishing to a marketplace\n- Use when debugging why a skill doesn't trigger correctly\n- Use when onboarding a team to skill authoring standards\n- Do NOT use for anti-slop detection, security scanning, or token analysis; use [SkillCheck Pro](https://getskillcheck.com) for those\n\n## How It Works\n\n### Step 1: Parse\n\nRead the target SKILL.md file and extract YAML frontmatter.\n\n### Step 2: Validate\n\nApply all Free tier checks in order:\n\n| Category | Checks | What it catches |\n|----------|--------|----------------|\n| Structure (1.x) | Name format, description WHAT+WHEN, allowed-tools, categories, XML injection | Malformed frontmatter, missing fields |\n| Body (2.x) | Line count, hardcoded paths, stale dates, empty sections, deprecated syntax, MCP tool qualification | Content quality issues |\n| Naming (3.x) | Vague terms, single-word names, gerund suggestions | Poor discoverability |\n| Semantic (4.x) | Contradictions, ambiguous terms, missing output format, wisdom/platitudes, misplaced triggers | Logical inconsistencies |\n| Quality (8.x) | Examples, error handling, triggers, output format, prerequisites, negative triggers | Strengths (positive patterns) |\n\n### Step 3: Score\n\nCalculate overall score (0-100). Penalties: critical = -20, warning = -5, suggestion = -1.\n\n### Step 4: Report\n\nReturn structured results: score, grade (Excellent/Good/Needs Work/Poor), issue list with check IDs, line numbers, messages, and fix suggestions.\n\n## Examples\n\n### Example 1: Validating a skill\n\n```\nUser: check my skill at ~/.claude/skills/weekly-report/SKILL.md\n\nSkillCheck output:\n## weekly-report Check Results [FREE]\n\nScore: 85/100 (Good)\n\n### Warnings (2)\n  - 1.2-desc-when (line 3): Description missing WHEN clause\n  - 4.5-desc-no-triggers (line 3): Description lacks triggering conditions\n\n### Suggestions (1)\n  - 3.4-gerund-naming (line 2): Skill name could use gerund form\n\n### Passed Checks: 28\n```\n\n### Example 2: Clean skill passes all checks\n\n```\nUser: skillcheck ~/.claude/skills/processing-pdfs/SKILL.md\n\nScore: 100/100 (Excellent)\nAll 31 checks passed. No issues found.\n```\n\n## Limitations\n\n- Read-only: does not modify any files\n- Free tier covers structural, semantic, and naming checks only\n- Anti-slop, security, WCAG, token, enterprise, and workflow checks require [SkillCheck Pro](https://getskillcheck.com)\n- Semantic checks (contradiction detection, wisdom/platitude) are heuristic with ~5% false positive rate\n- Does not validate referenced files or scripts; only checks SKILL.md content\n- Single-file validation; does not cross-check against other skills in the same directory\n\n## Best Practices\n\n- Run SkillCheck before submitting skills to any marketplace\n- Fix all critical and warning issues; suggestions are optional\n- Use the check ID (e.g., `1.2-desc-when`) to find the exact rule in the skill body\n- Re-run after fixes to confirm the score improved\n\n## Common Pitfalls\n\n- **Problem:** Score seems low due to many suggestions\n  **Solution:** Suggestions cap at -15 points total. Focus on warnings and criticals first.\n\n- **Problem:** False positive on ambiguous terms inside code blocks\n  **Solution:** SkillCheck skips code blocks and inline code. If you still see false positives, wrap the term in backticks.\n\n- **Problem:** Wisdom/platitude check flags legitimate instructions\n  **Solution:** Rephrase generic advice (\"Remember that testing is important\") as concrete directives (\"Run tests before committing\").","tags":["skill","check","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-skill-check","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/skill-check","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34515 github stars · SKILL.md body (3,847 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T12:51:46.460Z","embedding":null,"createdAt":"2026-04-18T21:44:55.843Z","updatedAt":"2026-04-22T12:51:46.460Z","lastSeenAt":"2026-04-22T12:51:46.460Z","tsv":"'-1':240 '-100':233 '-15':477 '-20':236 '-5':238 '/.claude/skills/processing-pdfs/skill.md':334 '/.claude/skills/weekly-report/skill.md':273 '0':232 '1':121,148,264,309 '1.2':287,440 '100/100':336 '2':133,166,286,315,326 '28':324 '3':185,227,292,303 '3.4':310 '31':339 '4':198,242 '4.5':297 '5':385 '8':212 '85/100':283 'advic':523 'agentskil':10,28 'agentskills.io':30 'allow':156 'allowed-tool':155 'ambigu':201,490 'analysi':110 'anthrop':32 'anti':42,103,364 'anti-pattern':41 'anti-slop':102,363 'appli':135 'author':96 'backtick':513 'best':33,416 'block':494,499 'bodi':165,452 'calcul':229 'cap':475 'catch':12,35,146 'categori':142,158 'check':3,63,139,143,254,269,279,323,331,340,361,372,378,397,408,437,516 'claud':5 'claus':296 'clean':327 'code':6,493,498,502 'commit':535 'common':463 'concret':530 'condit':307 'confirm':459 'content':181,399 'contradict':39,200,379 'correct':88 'could':318 'count':169 'cover':356 'critic':235,428,484 'cross':407 'cross-check':406 'date':173 'debug':81 'deprec':176 'desc':289,299,442 'desc-no-trigg':298 'desc-when':288,441 'descript':152,293,304 'detect':105,380 'direct':531 'directori':415 'discover':196 'doesn':85 'due':469 'e.g':439 'empti':174 'enterpris':369 'error':37,215 'exact':447 'exampl':214,262,263,325 'excel':337 'excellent/good/needs':249 'extract':129 'fals':386,487,507 'field':164 'file':25,127,353,393,402 'find':445 'first':485 'fix':260,426,457 'flag':517 'focus':480 'form':321 'format':151,205,219 'found':344 'free':137,281,354 'frontmatt':131,162 'gap':46 'generic':522 'gerund':193,312,320 'gerund-nam':311 'getskillcheck.com':114,376 'good':284 'grade':248 'handl':216 'hardcod':170 'heurist':383 'id':255,438 'import':528 'improv':462 'inconsist':210 'inject':160 'inlin':501 'insid':492 'instruct':519 'issu':17,183,251,343,431 'lack':305 'legitim':518 'limit':345 'line':168,256,291,302,314 'list':252 'logic':209 'low':468 'malform':161 'mani':471 'marketplac':78,425 'mcp':178 'messag':258 'misplac':207 'miss':163,203,294 'modifi':351 'name':16,40,150,184,192,313,317,360 'negat':221 'number':257 'onboard':91 'option':434 'order':141 'output':204,218,275 'overal':230 'overview':22 'pars':122 'pass':53,322,329,341 'path':171 'pattern':43,225 'penalti':234 'pitfal':464 'point':478 'poor':195 'posit':224,387,488,508 'practic':34,417 'prerequisit':220 'pro':113,375 'problem':465,486,514 'publish':75 'qualif':180 'qualiti':45,182,211 'rate':388 're':454 're-run':453 'read':51,123,347 'read-on':50,346 'referenc':392 'rememb':524 'rephras':521 'report':243,278 'requir':373 'result':246,280 'return':244 'review':71 'rule':448 'run':418,455,532 'say':62 'scan':107 'score':228,231,247,282,335,461,466 'script':395 'section':175 'secur':106,366 'see':506 'seem':467 'semant':14,38,197,358,377 'singl':49,190,401 'single-fil':400 'single-word':189 'skill':2,7,58,64,73,84,95,267,271,316,328,411,422,451 'skill-check':1 'skill-skill-check' 'skill.md':24,68,126,398 'skillcheck':21,65,112,274,333,374,419,496 'skip':497 'slop':104,365 'solut':473,495,520 'source-sickn33' 'specif':11,29 'stale':172 'standard':97 'step':120,132,226,241 'still':505 'strength':223 'structur':13,36,147,245,357 'submit':421 'suggest':194,239,261,308,432,472,474 'syntax':177 'target':125 'team':93 'term':188,202,491,511 'test':526,533 'tier':138,355 'token':109,368 'tool':157,179 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'total':479 'trigger':87,208,217,222,301,306 'use':56,59,69,79,89,100,111,319,435 'user':19,61,268,332 'vagu':187 'valid':4,23,67,134,265,391,403 'warn':237,285,430,482 'wcag':367 'week':277 'weekly-report':276 'wisdom/platitude':381,515 'wisdom/platitudes':206 'word':191 'work':119 'work/poor':250 'workflow':371 'wrap':509 'x':149,167,186,199,213 'xml':159 'yaml':130","prices":[{"id":"6046e6c7-4ee5-4aab-9873-b16161478b08","listingId":"0ba02b1d-629e-4cd9-9d0a-999a247c7913","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:44:55.843Z"}],"sources":[{"listingId":"0ba02b1d-629e-4cd9-9d0a-999a247c7913","source":"github","sourceId":"sickn33/antigravity-awesome-skills/skill-check","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-check","isPrimary":false,"firstSeenAt":"2026-04-18T21:44:55.843Z","lastSeenAt":"2026-04-22T12:51:46.460Z"}],"details":{"listingId":"0ba02b1d-629e-4cd9-9d0a-999a247c7913","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"skill-check","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34515,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-22T06:40:00Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"767e9a52f9375627b4deb35f62f8f03d23f2256a","skill_md_path":"skills/skill-check/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-check"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"skill-check","license":"MIT","description":"Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.","compatibility":"claude-code"},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/skill-check"},"updatedAt":"2026-04-22T12:51:46.460Z"}}