{"id":"9fbd050d-d26f-4fe9-9c3f-82325be1627c","shortId":"W4wshk","kind":"skill","title":"blueprint","tagline":"Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.","description":"# Blueprint — Construction Plan Generator\n\nTurn a one-line objective into a step-by-step plan any coding agent can execute cold.\n\n## Overview\n\nBlueprint is for multi-session, multi-agent engineering projects where each step must be independently executable by a fresh agent that has never seen the conversation history. Install it once, invoke it with `/blueprint <project> <objective>`.\n\n## When to Use This Skill\n\n- Use when the task requires multiple PRs or sessions\n- Use when multiple agents or team members need to share execution\n- Use when you want adversarial review of the plan before execution\n- Use when parallel step detection and dependency graphs matter\n\n## How It Works\n\n1. **Research** — Scans the codebase, reads project memory, runs pre-flight checks\n2. **Design** — Breaks the objective into one-PR-sized steps, identifies parallelism, assigns model tiers\n3. **Draft** — Generates the plan from a structured template with branch workflow rules, CI policy, and rollback strategies inline\n4. **Review** — Delegates adversarial review to a strongest-model sub-agent (falls back to default model if unavailable)\n5. **Register** — Saves the plan and updates project memory\n\n## Examples\n\n### Example 1: Database migration\n```\n/blueprint myapp \"migrate database to PostgreSQL\"\n```\n\n### Example 2: Plugin extraction\n```\n/blueprint antbot \"extract providers into plugins\"\n```\n\n## Best Practices\n\n- ✅ Use for tasks requiring 3+ PRs or multiple sessions\n- ✅ Let Blueprint auto-detect git/gh availability — it degrades gracefully\n- ❌ Don't invoke for tasks completable in a single PR\n- ❌ Don't invoke when the user says \"just do it\"\n\n## Key Differentiators\n\n- **Cold-start execution**: Every step has a self-contained context brief\n- **Adversarial review gate**: Strongest-model review before execution\n- **Zero runtime risk**: Pure markdown — no hooks, no scripts, no executable code\n- **Plan mutation protocol**: Steps can be split, inserted, skipped with audit trail\n\n## Installation\n\n```bash\nmkdir -p ~/.claude/skills\ngit clone https://github.com/antbotlab/blueprint.git ~/.claude/skills/blueprint\n```\n\n## Additional Resources\n\n- [GitHub Repository](https://github.com/antbotlab/blueprint)\n- [Examples: small plan](https://github.com/antbotlab/blueprint/blob/main/examples/small-plan.md)\n- [Examples: large plan](https://github.com/antbotlab/blueprint/blob/main/examples/large-plan.md)\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":["blueprint","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity-skills"],"capabilities":["skill","source-sickn33","skill-blueprint","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/blueprint","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 · 34882 github stars · SKILL.md body (2,716 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":"2026-04-24T12:50:41.262Z","embedding":null,"createdAt":"2026-04-18T21:33:39.252Z","updatedAt":"2026-04-24T12:50:41.262Z","lastSeenAt":"2026-04-24T12:50:41.262Z","tsv":"'/.claude/skills':346 '/.claude/skills/blueprint':352 '/antbotlab/blueprint)':359 '/antbotlab/blueprint.git':351 '/antbotlab/blueprint/blob/main/examples/large-plan.md)':371 '/antbotlab/blueprint/blob/main/examples/small-plan.md)':365 '/blueprint':106,237,247 '1':155,234 '2':168,244 '3':184,259 '4':203 '5':223 'addit':353 'adversari':136,206,309 'agent':18,33,66,79,92,124,215 'antbot':248 'ask':405 'assign':181 'audit':340 'auto':267 'auto-detect':266 'avail':270 'back':217 'bash':343 'best':253 'blueprint':1,47,71,265 'boundari':413 'branch':194 'break':170 'brief':30,308 'check':167 'ci':197 'clarif':407 'clear':380 'clone':348 'code':17,65,329 'codebas':159 'cold':21,69,297 'cold-start':296 'complet':279 'construct':14,48 'contain':28,306 'context':29,307 'convers':98 'criteria':416 'databas':235,240 'default':219 'degrad':272 'deleg':205 'depend':149 'describ':384 'design':169 'detect':147,268 'differenti':295 'draft':185 'engin':80 'environ':396 'environment-specif':395 'everi':300 'exampl':232,233,243,360,366 'execut':20,68,88,131,142,299,317,328 'expert':401 'extract':246,249 'fall':216 'flight':166 'fresh':32,91 'gate':311 'generat':50,186 'git':347 'git/gh':269 'github':355 'github.com':350,358,364,370 'github.com/antbotlab/blueprint)':357 'github.com/antbotlab/blueprint.git':349 'github.com/antbotlab/blueprint/blob/main/examples/large-plan.md)':369 'github.com/antbotlab/blueprint/blob/main/examples/small-plan.md)':363 'grace':273 'graph':150 'histori':99 'hook':324 'identifi':179 'independ':87 'inlin':202 'input':410 'insert':337 'instal':100,342 'invok':103,276,286 'key':294 'larg':367 'let':264 'limit':372 'line':6,55 'markdown':322 'match':381 'matter':151 'member':127 'memori':162,231 'migrat':236,239 'miss':418 'mkdir':344 'model':182,212,220,314 'multi':75,78 'multi-ag':77 'multi-sess':74 'multipl':117,123,262 'must':85 'mutat':331 'myapp':238 'need':128 'never':95 'new':36 'object':7,56,172 'one':5,54,175 'one-lin':4,53 'one-pr-s':174 'output':390 'overview':70 'p':345 'parallel':145,180 'permiss':411 'pick':39 'plan':15,49,63,140,188,227,330,362,368 'plugin':245,252 'polici':198 'postgresql':242 'pr':176,283 'practic':254 'pre':165 'pre-flight':164 'prior':45 'project':81,161,230 'protocol':332 'provid':250 'prs':118,260 'pure':321 'read':44,160 'regist':224 'repositori':356 'requir':116,258,409 'research':156 'resourc':354 'review':137,204,207,310,315,402 'risk':320 'rollback':200 'rule':196 'run':163 'runtim':319 'safeti':412 'save':225 'say':290 'scan':157 'scope':383 'script':326 'seen':96 'self':27,305 'self-contain':26,304 'session':37,76,120,263 'share':130 'singl':282 'size':177 'skill':111,375 'skill-blueprint' 'skip':338 'small':361 'source-sickn33' 'specif':397 'split':336 'start':298 'step':11,13,23,42,46,60,62,84,146,178,301,333 'step-by-step':10,59 'stop':403 'strategi':201 'strongest':211,313 'strongest-model':210,312 'structur':191 'sub':214 'sub-ag':213 'substitut':393 'success':415 'task':115,257,278,379 'team':126 'templat':192 'test':399 'tier':183 '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':341 'treat':388 'turn':2,51 'unavail':222 'updat':229 'use':109,112,121,132,143,255,373 'user':289 'valid':398 'want':135 'without':43 'work':154 'workflow':195 'zero':318","prices":[{"id":"55198bfe-0038-445c-8d76-881b561252f6","listingId":"9fbd050d-d26f-4fe9-9c3f-82325be1627c","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":"2026-04-18T21:33:39.252Z"}],"sources":[{"listingId":"9fbd050d-d26f-4fe9-9c3f-82325be1627c","source":"github","sourceId":"sickn33/antigravity-awesome-skills/blueprint","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/blueprint","isPrimary":false,"firstSeenAt":"2026-04-18T21:33:39.252Z","lastSeenAt":"2026-04-24T12:50:41.262Z"}],"details":{"listingId":"9fbd050d-d26f-4fe9-9c3f-82325be1627c","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"blueprint","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34882,"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":"2026-04-24T06:41:17Z","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":"c119653388198e96470266fd1c55cdd038b04e6a","skill_md_path":"skills/blueprint/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/blueprint"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"blueprint","description":"Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/blueprint"},"updatedAt":"2026-04-24T12:50:41.262Z"}}