{"id":"d05f7148-445d-470b-9698-ae156c338085","shortId":"qMzfWA","kind":"skill","title":"skillpack-creator","tagline":"Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with `skillpack.json`, local skills under `skills/`, starter prompts, start scripts, and","description":"# Skillpack Creator\n\n## Overview\n\nTurn a successful task into a reusable SkillPack. Extract the stable workflow, decide what belongs in a local skill versus pack-level prompts, generate the pack structure, and package it only after the workflow is explicit and repeatable.\n\n## Workflow\n\n### 1. Normalize the source task\n\nReduce the finished task into a clean execution spec:\n\n- Capture the user goal, concrete deliverable, and the final successful workflow (not the full exploratory transcript).\n- List required skills, tools, files, secrets, and environment assumptions.\n- Separate deterministic steps from heuristic steps; remove dead ends and debugging noise.\n- If the task is still too broad, narrow the scope instead of writing a vague mega-skill. If key success conditions depend on hidden human judgment, mark the pack as a best-effort assistant workflow.\n\nAsk for missing stable facts or infer only the low-risk pieces.\n\n### 2. Decide what the pack should contain\n\n- **Local skill** (`skills/`): reusable procedural knowledge. Keep scripts minimal unless reproducibility depends on exact file generation or repetitive shell steps.\n- **Scripts** (`scripts/`): repeated shell or file-generation logic where reliability matters.\n- **References** (`references/`): detailed schemas, API notes, or conventions that should not bloat `SKILL.md`.\n- **Prompts** (`skillpack.json`): 1–3 pack-level starter inputs for the UI — not a DAG or state machine. See `references/skillpack-format.md` for exact pack semantics.\n\n### 3. Create the pack specification\n\nBefore writing files, define the pack spec. Prefer one local orchestrator skill plus a small number of external skills. Example minimal manifest:\n\n```json\n{\n  \"name\": \"company-research\",\n  \"description\": \"Research a company and produce a summary report\",\n  \"version\": \"1.0.0\",\n  \"prompts\": [\"Research {company} and create a report with financials and competitors\"],\n  \"skills\": [\n    { \"name\": \"research-orchestrator\", \"source\": \"./skills/research-orchestrator\", \"description\": \"Orchestrate company research across multiple sources\" }\n  ]\n}\n```\n\n### 4. Create the local orchestrator skill\n\nCreate `skills/<skill-name>/SKILL.md` with frontmatter and imperative workflow instructions:\n\n```yaml\n---\nname: research-orchestrator\ndescription: \"Orchestrate multi-source company research. Use when the user wants a structured company report covering financials, competitors, and market position.\"\n---\n```\n\n- Write the stable workflow as imperative steps in the body.\n- Add `scripts/` only for fragile or repeated operations; add `references/` only for detailed information.\n\n### 5. Materialize the pack\n\nUse `scripts/scaffold_skillpack.py` when you have the pack spec:\n\n```bash\n# Basic\npython3 skills/skillpack-creator/scripts/scaffold_skillpack.py \\\n  --manifest /tmp/skillpack.json \\\n  --output /absolute/path/to/output-pack\n\n# With zip\npython3 skills/skillpack-creator/scripts/scaffold_skillpack.py \\\n  --manifest /tmp/skillpack.json \\\n  --output /absolute/path/to/output-pack \\\n  --zip\n```\n\nThe script validates the manifest, writes `skillpack.json`, creates `skills/`, copies `start.sh`/`start.bat` from `templates/`, and optionally runs `npx -y @cremini/skillpack zip`.\n\n### 6. Validate the result\n\nBefore handing the pack back, confirm:\n\n- The manifest matches the intended pack scope\n- Every declared skill has a valid `name`, `source`, and `description`\n- Local skills are present under the target pack's `skills/`\n- Starter prompts are concrete enough to reproduce the workflow\n- Zip only after the pack runs as a directory\n\n## Output Standard\n\nProduce:\n\n1. A short summary of the stabilized workflow.\n2. The target pack structure and skill inventory.\n3. The created or updated local skill files.\n4. The generated `skillpack.json`.\n5. Whether the pack was zipped and where the zip lives.","tags":["skillpack","creator","creminiai","agent","agent-skills","agentic","agentic-ai","agentic-workflow","ai-skills"],"capabilities":["skill","source-creminiai","skill-skillpack-creator","topic-agent","topic-agent-skills","topic-agentic","topic-agentic-ai","topic-agentic-workflow","topic-ai-skills"],"categories":["skillpack"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/CreminiAI/skillpack/skillpack-creator","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add CreminiAI/skillpack","source_repo":"https://github.com/CreminiAI/skillpack","install_from":"skills.sh"}},"qualityScore":"0.585","qualityRationale":"deterministic score 0.58 from registry signals: · indexed on github topic:agent-skills · 271 github stars · SKILL.md body (3,842 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":"2026-05-02T12:53:56.304Z","embedding":null,"createdAt":"2026-04-18T22:09:03.272Z","updatedAt":"2026-05-02T12:53:56.304Z","lastSeenAt":"2026-05-02T12:53:56.304Z","tsv":"'/absolute/path/to/output-pack':419,427 '/skill.md':342 '/skills/research-orchestrator':326 '/tmp/skillpack.json':417,425 '1':89,244,508 '1.0.0':308 '2':190,516 '3':245,266,524 '4':334,532 '5':400,536 '6':450 'across':331 'add':386,394 'analysi':26 'api':233 'ask':177 'assist':175 'assumpt':127 'back':458 'bash':412 'basic':413 'belong':63 'best':173 'best-effort':172 'bloat':240 'bodi':385 'broad':146 'captur':103 'clean':100 'code':25 'compani':296,301,311,329,359,368 'company-research':295 'competitor':319,372 'complet':11 'concret':107,490 'condit':161 'confirm':459 'contain':196 'content':28 'convent':236 'convert':19 'copi':438 'cover':370 'creat':4,267,313,335,340,436,526 'creator':3,47 'cremini/skillpack':448 'dag':256 'dead':135 'debug':138 'decid':61,191 'declar':468 'defin':274 'deliver':108 'depend':162,208 'descript':298,327,354,476 'detail':231,398 'determinist':129 'directori':504 'distribut':32 'effort':174 'end':136 'enough':491 'environ':126 'everi':467 'exact':210,263 'exampl':290 'execut':101 'explicit':85 'exploratori':117 'extern':288 'extract':57 'fact':181 'file':123,211,223,273,531 'file-gener':222 'final':111 'financi':317,371 'finish':96 'fragil':390 'frontmatt':344 'full':116 'generat':73,212,224,534 'goal':106 'hand':455 'heurist':132 'hidden':164 'human':165 'imper':346,381 'infer':183 'inform':399 'input':250 'instead':150 'instruct':348 'intend':464 'inventori':523 'json':293 'judgment':166 'keep':203 'key':159 'knowledg':202 'level':71,248 'list':119 'live':546 'local':33,37,66,197,280,337,477,529 'logic':225 'low':187 'low-risk':186 'machin':259 'manifest':292,416,424,433,461 'mark':167 'market':374 'match':462 'materi':401 'matter':228 'mega':156 'mega-skil':155 'minim':205,291 'miss':179 'multi':357 'multi-sourc':356 'multipl':332 'name':294,321,350,473 'narrow':147 'nois':139 'normal':90 'note':234 'npx':446 'number':286 'one':22,279 'one-off':21 'oper':393 'option':444 'orchestr':281,324,328,338,353,355 'output':418,426,505 'overview':48 'pack':70,75,169,194,247,264,269,276,403,410,457,465,484,500,519,539 'pack-level':69,246 'packag':78 'piec':189 'plus':283 'posit':375 'prefer':278 'present':480 'procedur':201 'produc':303,507 'prompt':42,72,242,309,488 'python3':414,422 'reduc':94 'refer':229,230,395 'references/skillpack-format.md':261 'reliabl':227 'remov':134 'repeat':87,219,392 'repetit':214 'report':306,315,369 'reproduc':207,493 'requir':120 'research':24,297,299,310,323,330,352,360 'research-orchestr':322,351 'result':453 'reusabl':6,55,200 'risk':188 'run':445,501 'schema':232 'scope':149,466 'script':44,204,217,218,387,430 'scripts/scaffold_skillpack.py':405 'secret':124 'see':260 'semant':265 'separ':128 'shell':215,220 'short':510 'skill':38,40,67,121,157,198,199,282,289,320,339,341,437,469,478,486,522,530 'skill-skillpack-creator' 'skill.md':241 'skillpack':2,7,34,46,56 'skillpack-cr':1 'skillpack.json':36,243,435,535 'skills/skillpack-creator/scripts/scaffold_skillpack.py':415,423 'small':285 'sourc':92,325,333,358,474 'source-creminiai' 'spec':102,277,411 'specif':270 'stabil':514 'stabl':59,180,378 'standard':506 'start':43 'start.bat':440 'start.sh':439 'starter':41,249,487 'state':258 'step':130,133,216,382 'still':144 'structur':76,367,520 'success':10,51,112,160 'summari':305,511 'target':483,518 'task':12,52,93,97,142 'templat':442 'tool':122 'topic-agent' 'topic-agent-skills' 'topic-agentic' 'topic-agentic-ai' 'topic-agentic-workflow' 'topic-ai-skills' 'transcript':118 'turn':49 'ui':253 'unless':206 'updat':528 'use':13,361,404 'user':16,105,364 'vagu':154 'valid':431,451,472 'version':307 'versus':68 'want':17,365 'whether':537 'workflow':29,60,83,88,113,176,347,379,495,515 'write':152,272,376,434 'y':447 'yaml':349 'zip':421,428,449,496,541,545","prices":[{"id":"cec76d9c-43b1-49e2-a795-35e6b002cd34","listingId":"d05f7148-445d-470b-9698-ae156c338085","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"CreminiAI","category":"skillpack","install_from":"skills.sh"},"createdAt":"2026-04-18T22:09:03.272Z"}],"sources":[{"listingId":"d05f7148-445d-470b-9698-ae156c338085","source":"github","sourceId":"CreminiAI/skillpack/skillpack-creator","sourceUrl":"https://github.com/CreminiAI/skillpack/tree/main/skills/skillpack-creator","isPrimary":false,"firstSeenAt":"2026-04-18T22:09:03.272Z","lastSeenAt":"2026-05-02T12:53:56.304Z"}],"details":{"listingId":"d05f7148-445d-470b-9698-ae156c338085","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"CreminiAI","slug":"skillpack-creator","github":{"repo":"CreminiAI/skillpack","stars":271,"topics":["agent","agent-skills","agentic","agentic-ai","agentic-workflow","ai-skills"],"license":"mit","html_url":"https://github.com/CreminiAI/skillpack","pushed_at":"2026-04-28T08:19:57Z","description":"Pack and deploy local AI agents for your team in minutes","skill_md_sha":"c8a48159b8459b62c152d3d3ca9f1c7793c1bca9","skill_md_path":"skills/skillpack-creator/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/CreminiAI/skillpack/tree/main/skills/skillpack-creator"},"layout":"multi","source":"github","category":"skillpack","frontmatter":{"name":"skillpack-creator","description":"Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with `skillpack.json`, local skills under `skills/`, starter prompts, start scripts, and an optional zip package."},"skills_sh_url":"https://skills.sh/CreminiAI/skillpack/skillpack-creator"},"updatedAt":"2026-05-02T12:53:56.304Z"}}