{"id":"914ed9cf-1017-42b2-a7ac-e4e9776b0169","shortId":"UkGEHs","kind":"skill","title":"skill-writer","tagline":"Create and improve agent skills following the Agent Skills specification. Use when asked to create, write, or update skills.","description":"# Skill Writer\n\nUse this as the single canonical workflow for skill creation and improvement.\nPrimary success condition: maximize high-value input coverage before authoring so the resulting skill has minimal blind spots.\n\nLoad only the path(s) required for the task:\n\n| Task | Read |\n|------|------|\n| Set skill class and required dimensions | `references/mode-selection.md` |\n| Apply writing constraints for depth vs concision | `references/design-principles.md` |\n| Select structure pattern for this skill | `references/skill-patterns.md` |\n| Select workflow orchestration pattern for process-heavy skills | `references/workflow-patterns.md` |\n| Select output format pattern for deterministic quality | `references/output-patterns.md` |\n| Choose workflow path and required outputs | `references/mode-selection.md` |\n| Load representative synthesis examples by skill type | `references/examples/*.md` |\n| Synthesize external/local sources with depth gates | `references/synthesis-path.md` |\n| Author or update SKILL.md and supporting files | `references/authoring-path.md` |\n| Optimize skill description and trigger precision | `references/description-optimization.md` |\n| Iterate using positive/negative/fix examples | `references/iteration-path.md` |\n| Evaluate behavior and compare baseline vs with-skill (opt-in quantitative) | `references/evaluation-path.md` |\n| Register and validate skill changes | `references/registration-validation.md` |\n\n## Step 1: Resolve target and path\n\n1. Resolve target skill path and intended operation (`create`, `update`, `synthesize`, `iterate`).\n2. Read `references/mode-selection.md` and select the required path(s).\n3. Classify the skill (`workflow-process`, `integration-documentation`, `security-review`, `skill-authoring`, `generic`).\n4. Ask one direct question if class or depth requirements are ambiguous; otherwise state explicit assumptions.\n\n## Step 2: Run synthesis when needed\n\nRead `references/synthesis-path.md`.\n\n1. Collect and score relevant sources with provenance.\n2. Apply trust and safety rules when ingesting external content.\n3. Produce source-backed decisions and coverage/gap status.\n4. Load one or more profiles from `references/examples/*.md` when the skill is hybrid.\n5. Enforce baseline source pack for skill-authoring workflows.\n6. Enforce depth gates before moving to authoring.\n\n## Step 3: Run iteration first when improving from outcomes/examples\n\nRead `references/iteration-path.md` first when selected path includes `iteration` (for example operation `iterate`).\n\n1. Capture and anonymize examples with provenance.\n2. Re-evaluate skill behavior against working and holdout slices.\n3. Propose improvements from positive/negative/fix evidence.\n4. Carry concrete behavior deltas into authoring.\n\nSkip this step when selected path does not include `iteration`.\n\n## Step 4: Author or update skill artifacts\n\nRead `references/authoring-path.md`.\n\n1. Write or update `SKILL.md` in imperative voice with trigger-rich description.\n2. Create focused reference files and scripts only when justified.\n3. Follow `references/skill-patterns.md`, `references/workflow-patterns.md`, and\n   `references/output-patterns.md` for structure and output determinism.\n4. For authoring/generator skills, include transformed examples in references:\n   - happy-path\n   - secure/robust variant\n   - anti-pattern + corrected version\n\n## Step 5: Optimize description quality\n\nRead `references/description-optimization.md`.\n\n1. Validate should-trigger and should-not-trigger query sets.\n2. Reduce false positives and false negatives with targeted description edits.\n3. Keep trigger language generic across Codex and Claude.\n\n## Step 6: Evaluate outcomes\n\nRead `references/evaluation-path.md`.\n\n1. Run a lightweight qualitative check by default (recommended).\n2. For integration/documentation and skill-authoring skills, include the concise depth rubric from `references/evaluation-path.md`.\n3. Run deeper eval playbook and quantitative baseline-vs-with-skill only when requested or risk warrants it.\n4. Record outcomes and unresolved risks.\n\n## Step 7: Register and validate\n\nRead `references/registration-validation.md`.\n\n1. Apply repository registration steps.\n2. Run quick validation with strict depth gates.\n3. Reject shallow outputs that fail depth gates or required artifact checks.\n\n## Output format\n\nReturn:\n\n1. `Summary`\n2. `Changes Made`\n3. `Validation Results`\n4. `Open Gaps`\n\n## When to Use\nUse this skill when tackling tasks related to its primary domain or functionality as described above.\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","writer","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-skill-writer","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-writer","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 (4,864 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":"2026-04-22T12:51:47.547Z","embedding":null,"createdAt":"2026-04-18T21:45:05.103Z","updatedAt":"2026-04-22T12:51:47.547Z","lastSeenAt":"2026-04-22T12:51:47.547Z","tsv":"'1':171,176,238,318,368,428,466,522,550 '2':188,231,246,325,381,440,475,527,552 '3':197,256,298,336,391,451,490,535,555 '4':214,265,342,360,402,509,558 '5':279,422 '6':289,461 '7':516 'across':456 'agent':7,11 'ambigu':225 'anonym':321 'anti':417 'anti-pattern':416 'appli':74,247,523 'artifact':365,545 'ask':16,215,613 'assumpt':229 'author':47,130,212,287,296,348,361,481 'authoring/generator':404 'back':260 'baselin':154,281,498 'baseline-vs-with-skil':497 'behavior':151,330,345 'blind':54 'boundari':621 'canon':30 'captur':319 'carri':343 'chang':168,553 'check':471,546 'choos':107 'clarif':615 'class':69,220 'classifi':198 'claud':459 'clear':588 'codex':457 'collect':239 'compar':153 'concis':80,485 'concret':344 'condit':39 'constraint':76 'content':255 'correct':419 'coverag':45 'coverage/gap':263 'creat':4,18,184,382 'creation':34 'criteria':624 'decis':261 'deeper':492 'default':473 'delta':346 'depth':78,127,222,291,486,533,541 'describ':578,592 'descript':140,380,424,449 'determin':401 'determinist':104 'dimens':72 'direct':217 'document':206 'domain':574 'edit':450 'enforc':280,290 'environ':604 'environment-specif':603 'eval':493 'evalu':150,328,462 'evid':341 'exampl':117,148,315,322,408 'expert':609 'explicit':228 'extern':254 'external/local':124 'fail':540 'fals':442,445 'file':136,385 'first':301,308 'focus':383 'follow':9,392 'format':101,548 'function':576 'gap':560 'gate':128,292,534,542 'generic':213,455 'happi':412 'happy-path':411 'heavi':96 'high':42 'high-valu':41 'holdout':334 'hybrid':278 'imper':374 'improv':6,36,303,338 'includ':312,357,406,483 'ingest':253 'input':44,618 'integr':205 'integration-document':204 'integration/documentation':477 'intend':182 'iter':145,187,300,313,317,358 'justifi':390 'keep':452 'languag':454 'lightweight':469 'limit':580 'load':56,114,266 'made':554 'match':589 'maxim':40 'md':122,273 'minim':53 'miss':626 'move':294 'need':235 'negat':446 'one':216,267 'open':559 'oper':183,316 'opt':160 'opt-in':159 'optim':138,423 'orchestr':91 'otherwis':226 'outcom':463,511 'outcomes/examples':305 'output':100,112,400,538,547,598 'pack':283 'path':59,109,175,180,195,311,354,413 'pattern':84,92,102,418 'permiss':619 'playbook':494 'posit':443 'positive/negative/fix':147,340 'precis':143 'primari':37,573 'process':95,203 'process-heavi':94 'produc':257 'profil':270 'propos':337 'proven':245,324 'qualit':470 'qualiti':105,425 'quantit':162,496 'queri':438 'question':218 'quick':529 're':327 're-evalu':326 'read':66,189,236,306,366,426,464,520 'recommend':474 'record':510 'reduc':441 'refer':384,410 'references/authoring-path.md':137,367 'references/description-optimization.md':144,427 'references/design-principles.md':81 'references/evaluation-path.md':163,465,489 'references/examples':121,272 'references/iteration-path.md':149,307 'references/mode-selection.md':73,113,190 'references/output-patterns.md':106,396 'references/registration-validation.md':169,521 'references/skill-patterns.md':88,393 'references/synthesis-path.md':129,237 'references/workflow-patterns.md':98,394 'regist':164,517 'registr':525 'reject':536 'relat':570 'relev':242 'repositori':524 'repres':115 'request':504 'requir':61,71,111,194,223,544,617 'resolv':172,177 'result':50,557 'return':549 'review':209,610 'rich':379 'risk':506,514 'rubric':487 'rule':251 'run':232,299,467,491,528 'safeti':250,620 'scope':591 'score':241 'script':387 'secur':208 'secure/robust':414 'security-review':207 'select':82,89,99,192,310,353 'set':67,439 'shallow':537 'should-not-trigg':434 'should-trigg':430 'singl':29 'skill':2,8,12,22,23,33,51,68,87,97,119,139,158,167,179,200,211,276,286,329,364,405,480,482,501,566,583 'skill-author':210,285,479 'skill-skill-writer' 'skill-writ':1 'skill.md':133,372 'skip':349 'slice':335 'sourc':125,243,259,282 'source-back':258 'source-sickn33' 'specif':13,605 'spot':55 'state':227 'status':264 'step':170,230,297,351,359,421,460,515,526 'stop':611 'strict':532 'structur':83,398 'substitut':601 'success':38,623 'summari':551 'support':135 'synthes':123,186 'synthesi':116,233 'tackl':568 'target':173,178,448 'task':64,65,569,587 'test':607 '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' 'transform':407 'treat':596 'trigger':142,378,432,437,453 'trigger-rich':377 'trust':248 'type':120 'unresolv':513 'updat':21,132,185,363,371 'use':14,25,146,563,564,581 'valid':166,429,519,530,556,606 'valu':43 'variant':415 'version':420 'voic':375 'vs':79,155,499 'warrant':507 'with-skil':156 'work':332 'workflow':31,90,108,202,288 'workflow-process':201 'write':19,75,369 'writer':3,24","prices":[{"id":"6127730f-175d-42b4-a2e9-585ac59d4691","listingId":"914ed9cf-1017-42b2-a7ac-e4e9776b0169","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":"2026-04-18T21:45:05.103Z"}],"sources":[{"listingId":"914ed9cf-1017-42b2-a7ac-e4e9776b0169","source":"github","sourceId":"sickn33/antigravity-awesome-skills/skill-writer","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-writer","isPrimary":false,"firstSeenAt":"2026-04-18T21:45:05.103Z","lastSeenAt":"2026-04-22T12:51:47.547Z"}],"details":{"listingId":"914ed9cf-1017-42b2-a7ac-e4e9776b0169","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"skill-writer","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":"9edb83b49011d79987e78f86003b6e254fd8aedb","skill_md_path":"skills/skill-writer/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-writer"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"skill-writer","description":"Create and improve agent skills following the Agent Skills specification. Use when asked to create, write, or update skills."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/skill-writer"},"updatedAt":"2026-04-22T12:51:47.547Z"}}