{"id":"d6952250-099f-4726-b3a2-910bf7b1a993","shortId":"YnbtvE","kind":"skill","title":"skill-improver","tagline":"Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improving a skill with multiple quality issues, iterating on a new skill until it meets standards, or automated fix-review cycles instead of manual editing.","description":"# Skill Improvement Methodology\n\nIteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards.\n\n## Prerequisites\n\nRequires the `plugin-dev` plugin which provides the `skill-reviewer` agent.\n\nVerify it's enabled: run `/plugins` — `plugin-dev` should appear in the list. If missing, install from the Trail of Bits plugin repository.\n\n## Core Loop\n\n1. **Review** - Call skill-reviewer on the target skill\n2. **Categorize** - Parse issues by severity\n3. **Fix** - Address critical and major issues\n4. **Evaluate** - Check minor issues for validity before fixing\n5. **Repeat** - Continue until quality bar is met\n\n## When to Use\n- Improving a skill with multiple quality issues\n- Iterating on a new skill until it meets standards\n- Automated fix-review cycles instead of manual editing\n- Consistent quality enforcement across skills\n\n## When NOT to Use\n\n- **One-time review**: Use `/skill-reviewer` directly instead\n- **Quick single fixes**: Edit the file directly\n- **Non-skill files**: Only works on SKILL.md files\n- **Experimental skills**: Manual iteration gives more control during exploration\n\n## Issue Categorization\n\n### Critical Issues (MUST fix immediately)\n\nThese block skill loading or cause runtime failures:\n\n- Missing required frontmatter fields (name, description) — Claude cannot index or trigger the skill\n- Invalid YAML frontmatter syntax — Parsing fails, skill won't load\n- Referenced files that don't exist — Runtime errors when Claude follows links\n- Broken file paths — Same as above, leads to tool failures\n\n### Major Issues (MUST fix)\n\nThese significantly degrade skill effectiveness:\n\n- Weak or vague trigger descriptions — Claude may not recognize when to use the skill\n- Wrong writing voice (second person \"you\" instead of imperative) — Inconsistent with Claude's execution model\n- SKILL.md exceeds 500 lines without using references/ — Overloads context, reduces comprehension\n- Missing \"When to Use\" or \"When NOT to Use\" sections — Required by project quality standards\n- Description doesn't specify when to trigger — Skill may never be selected\n\n### Minor Issues (Evaluate before fixing)\n\nThese are polish items that may or may not improve the skill:\n\n- Subjective style preferences — Reviewer may have different taste than author\n- Optional enhancements — May add complexity without proportional value\n- \"Nice to have\" improvements — Consider cost-benefit before implementing\n- Formatting suggestions — Often valid but low impact\n\n## Minor Issue Evaluation\n\nBefore implementing any minor issue fix, evaluate:\n\n1. **Is this a genuine improvement?** - Does it add real value or just satisfy a preference?\n2. **Could this be a false positive?** - Is the reviewer misunderstanding context?\n3. **Would this actually help Claude use the skill?** - Focus on functional improvements\n\nOnly implement minor fixes that are clearly beneficial. Skill-reviewer may produce false positives.\n\n## Invoking skill-reviewer\n\nUse the skill-reviewer agent from the plugin-dev plugin. Request a review by asking Claude to:\n\n> Review the skill at [SKILL_PATH] using the plugin-dev:skill-reviewer agent. Provide a detailed quality assessment with issues categorized by severity.\n\nReplace `[SKILL_PATH]` with the absolute path to the skill directory (e.g., `/path/to/plugins/my-plugin/skills/my-skill`).\n\n## Example Fix Cycle\n\n**Iteration 1 — skill-reviewer output:**\n```text\nCritical: SKILL.md:1 - Missing required 'name' field in frontmatter\nMajor: SKILL.md:3 - Description uses second person (\"you should use\")\nMajor: Missing \"When NOT to Use\" section\nMinor: Line 45 is verbose\n```\n\n**Fixes applied:**\n- Added name field to frontmatter\n- Rewrote description in third person\n- Added \"When NOT to Use\" section\n\n**Iteration 2 — run skill-reviewer again to verify fixes:**\n```text\nMinor: Line 45 is verbose\n```\n\n**Minor issue evaluation:**\nLine 45 communicates effectively as-is. The verbosity provides useful context. Skip.\n\n**All critical/major issues resolved. Output the completion marker:**\n```\n<skill-improvement-complete>\n```\n\nNote: The marker MUST appear in the output. Statements like \"quality bar met\" or \"looks good\" will NOT stop the loop.\n\n## Completion Criteria\n\n**CRITICAL**: The stop hook ONLY checks for the explicit marker below. No other signal will terminate the loop.\n\nOutput this marker when done:\n\n```\n<skill-improvement-complete>\n```\n\n**When to output the marker:**\n\n1. **skill-reviewer reports \"Pass\"** or **no issues found** → output marker immediately\n2. **All critical and major issues are fixed** AND you've verified the fixes → output marker\n3. **Remaining issues are only minor** AND you've evaluated them as false positives or not worth fixing → output marker\n\n**When NOT to output the marker:**\n\n- Any critical issue remains unfixed\n- Any major issue remains unfixed\n- You haven't run skill-reviewer to verify your fixes worked\n\nThe marker is the ONLY way to complete the loop. Natural language like \"looks good\" or \"quality bar met\" will NOT stop the loop.\n\n## Rationalizations to Reject\n\n- \"I'll just mark it complete and come back later\" - Fix issues now\n- \"This minor issue seems wrong, I'll skip all of them\" - Evaluate each one individually\n- \"The reviewer is being too strict\" - The quality bar exists for a reason\n- \"It's good enough\" - If there are major issues, it's not good enough\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["skill","improver","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-skill-improver","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-improver","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 (5,687 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":"2026-04-22T12:51:46.799Z","embedding":null,"createdAt":"2026-04-18T21:44:58.962Z","updatedAt":"2026-04-22T12:51:46.799Z","lastSeenAt":"2026-04-22T12:51:46.799Z","tsv":"'/path/to/plugins/my-plugin/skills/my-skill':533 '/plugins':88 '/skill-reviewer':191 '1':109,417,538,682 '2':119,433,592,695 '3':125,445,711 '4':132 '45':570,604,611 '5':141 '500':319 'absolut':526 'across':180 'actual':448 'ad':575,585 'add':385,425 'address':127 'agent':15,63,82,482,510 'appear':93,635 'appli':574 'as-i':614 'ask':493,874 'assess':515 'author':381 'autom':40,168 'back':794 'bar':146,642,776,822 'benefici':465 'benefit':397 'bit':104 'block':227 'boundari':882 'broken':269 'call':111 'cannot':241 'categor':120,220,518 'caus':231 'check':134,659 'clarif':876 'claud':7,55,240,266,293,313,450,494 'clear':464,849 'code':8,56 'come':793 'communic':612 'complet':629,652,766,791 'complex':386 'comprehens':327 'consid':394 'consist':177 'context':325,444,621 'continu':143 'control':216 'core':107 'cost':396 'cost-benefit':395 'could':434 'criteria':653,885 'critic':128,221,544,654,697,738 'critical/major':624 'cycl':44,172,536 'degrad':285 'describ':853 'descript':239,292,343,554,581 'detail':513 'dev':74,91,487,506 'differ':378 'direct':192,200 'directori':531 'doesn':344 'done':676 'e.g':532 'edit':48,176,197 'effect':287,613 'enabl':86 'enforc':179 'enhanc':383 'enough':830,840 'environ':865 'environment-specif':864 'error':264 'evalu':133,357,409,416,609,720,810 'exampl':534 'exceed':318 'execut':315 'exist':262,823 'experiment':210 'expert':870 'explicit':662 'explor':218 'fail':252 'failur':233,278 'fals':438,471,723 'field':237,549,577 'file':199,204,209,258,270 'fix':42,126,140,170,196,224,282,359,415,461,535,573,600,702,708,728,757,796 'fix-review':41,169 'focus':454 'follow':267 'format':400 'found':691 'frontmatt':236,249,551,579 'function':456 'genuin':421 'give':214 'good':646,773,829,839 'haven':748 'help':449 'hook':657 'immedi':225,694 'impact':406 'imper':310 'implement':399,411,459 'improv':3,5,23,50,53,152,369,393,422,457 'inconsist':311 'index':242 'individu':813 'input':879 'instal':99 'instead':45,173,193,308 'invalid':247 'invok':473 'issu':29,122,131,136,158,219,222,280,356,408,414,517,608,625,690,700,713,739,744,797,801,835 'item':363 'iter':4,30,52,159,213,537,591 'languag':770 'later':795 'lead':275 'like':640,771 'limit':841 'line':320,569,603,610 'link':268 'list':96 'll':787,805 'load':229,256 'look':645,772 'loop':108,651,671,768,782 'low':405 'major':130,279,552,561,699,743,834 'manual':47,175,212 'mark':789 'marker':630,633,663,674,681,693,710,730,736,760 'match':850 'may':294,351,365,367,376,384,469 'meet':18,37,66,166 'met':148,643,777 'methodolog':51 'minor':135,355,407,413,460,568,602,607,716,800 'miss':98,234,328,546,562,887 'misunderstand':443 'model':316 'multipl':27,156 'must':223,281,634 'name':238,548,576 'natur':769 'never':352 'new':33,162 'nice':390 'non':202 'non-skil':201 'note':631 'often':402 'one':187,812 'one-tim':186 'option':382 'output':542,627,638,672,679,692,709,729,734,859 'overload':324 'pars':121,251 'pass':687 'path':271,501,523,527 'permiss':880 'person':306,557,584 'plugin':73,75,90,105,486,488,505 'plugin-dev':72,89,485,504 'polish':362 'posit':439,472,724 'prefer':374,432 'prerequisit':69 'produc':470 'project':340 'proport':388 'provid':77,511,619 'qualiti':19,28,67,145,157,178,341,514,641,775,821 'quick':194 'ration':783 'real':426 'reason':826 'recogn':296 'reduc':326 'refer':323 'referenc':257 'reject':785 'remain':712,740,745 'repeat':142 'replac':521 'report':686 'repositori':106 'request':489 'requir':70,235,338,547,878 'resolv':626 'review':14,43,62,81,110,114,171,189,375,442,468,476,481,491,496,509,541,596,685,753,815,871 'rewrot':580 'run':87,593,750 'runtim':232,263 'safeti':881 'satisfi':430 'scope':852 'second':305,556 'section':337,567,590 'seem':802 'select':354 'sever':124,520 'signal':667 'signific':284 'singl':195 'skill':2,9,13,25,34,49,57,61,80,113,118,154,163,181,203,211,228,246,253,286,301,350,371,453,467,475,480,498,500,508,522,530,540,595,684,752,844 'skill-improv':1 'skill-review':12,60,79,112,466,474,479,507,539,594,683,751 'skill-skill-improver' 'skill.md':208,317 'skill.md:1':545 'skill.md:3':553 'skip':622,806 'source-sickn33' 'specif':866 'specifi':346 'standard':20,38,68,167,342 'statement':639 'stop':649,656,780,872 'strict':819 'style':373 'subject':372 'substitut':862 'success':884 'suggest':401 'syntax':250 'target':117 'task':848 'tast':379 'termin':669 'test':868 'text':543,601 'third':583 'time':188 'tool':277 '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' 'trail':102 'treat':857 'trigger':244,291,349 'unfix':741,746 'use':10,21,58,151,185,190,299,322,331,336,451,477,502,555,560,566,589,620,842 'vagu':290 'valid':138,403,867 'valu':389,427 've':705,719 'verbos':572,606,618 'verifi':83,599,706,755 'voic':304 'way':764 'weak':288 'without':321,387 'won':254 'work':206,758 'worth':727 'would':446 'write':303 'wrong':302,803 'yaml':248","prices":[{"id":"fe9a220c-1309-4ba8-b01b-d9eb39f5ec79","listingId":"d6952250-099f-4726-b3a2-910bf7b1a993","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":"2026-04-18T21:44:58.962Z"}],"sources":[{"listingId":"d6952250-099f-4726-b3a2-910bf7b1a993","source":"github","sourceId":"sickn33/antigravity-awesome-skills/skill-improver","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-improver","isPrimary":false,"firstSeenAt":"2026-04-18T21:44:58.962Z","lastSeenAt":"2026-04-22T12:51:46.799Z"}],"details":{"listingId":"d6952250-099f-4726-b3a2-910bf7b1a993","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"skill-improver","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":"fcdc752e36e528a3ea24dfa7721cb280e9c139cb","skill_md_path":"skills/skill-improver/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-improver"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"skill-improver","description":"Iteratively improve a Claude Code skill using the skill-reviewer agent until it meets quality standards. Use when improving a skill with multiple quality issues, iterating on a new skill until it meets standards, or automated fix-review cycles instead of manual editing."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/skill-improver"},"updatedAt":"2026-04-22T12:51:46.799Z"}}