{"id":"edf017ad-54f5-4682-a665-e131f47f3408","shortId":"xeLN4E","kind":"skill","title":"skill-miner","tagline":"Use when mining coding-agent session history, archived transcripts, memories, or repeated local work to discover recurring workflows that should become new Agent Skills.","description":"# Skill Miner\n\n## Overview\n\nMine real agent usage for new skill opportunities. The goal is to find repeated workflows, extract the reusable technique, and turn strong candidates into draft skills with evidence.\n\n## When To Use\n\n- A user wants to scan past coding-agent sessions for repeated workflows.\n- The user suspects they keep asking agents to do similar tasks manually.\n- A team wants a backlog of candidate skills based on actual work rather than brainstorming.\n- Existing memories, session logs, or project notes contain recurring procedures that have not been packaged.\n\nDo not use to tune an existing skill; use `skill-personalizer`. Do not use to publish a private skill publicly; use `skill-generalizer`.\n\n## Workflow\n\n1. Locate real evidence: session JSONL, memory summaries, repo notes, repeated scripts, and recent project folders.\n2. Run `scripts/scan_sessions.py` for a first-pass sanitized cluster report when local session files or exported transcripts are available.\n3. Cluster repeated work by intent, trigger phrasing, tools used, files touched, and verification pattern.\n4. Filter out one-off tasks, ordinary coding knowledge, and project-specific instructions better suited for `AGENTS.md`.\n5. Score candidates by recurrence, friction, risk, portability, and future value.\n6. For each strong candidate, draft a concise skill name, trigger description, workflow outline, bundled-resource needs, and validation prompts.\n7. Recommend whether each candidate should stay personal, become a public skill via `skill-generalizer`, or be skipped.\n8. If the user asks to proceed, create the selected skill folders and verify frontmatter/layout.\n\n## Evidence Rules\n\n- Quote or summarize enough source evidence to justify each candidate.\n- Do not expose sensitive transcript content unless the user explicitly asks for raw evidence.\n- Avoid turning every repeated task into a skill; prefer workflows where guidance changes future behavior.\n- Treat broad intent clusters as navigation hints, not skill drafts.\n- Check sampled positives and near misses before trusting a regex-based workflow candidate.\n- If session access is incomplete, label findings as partial and list what was scanned.\n\n## References\n\nRead [discovery-rubric.md](references/discovery-rubric.md) before doing a full session-history scan or creating candidate skill drafts.\n\nUse `scripts/scan_sessions.py --help` for the deterministic scanner. It supports native Codex/Claude/Gemini-style local evidence, `--export` inputs for other agents, and `--patterns` for personalized workflow definitions. Treat its output as evidence for review, not as an automatic decision to create skills.","tags":["skill","miner","optimizer","hqhq1025","agent-skills","agentskills","ai-visibility","claude-code","claude-code-skills","claude-skill","codex","codex-skills"],"capabilities":["skill","source-hqhq1025","skill-skill-miner","topic-agent-skills","topic-agentskills","topic-ai-visibility","topic-claude-code","topic-claude-code-skills","topic-claude-skill","topic-codex","topic-codex-skills","topic-cursor-skills","topic-gemini-cli","topic-github-pages","topic-llm-agents"],"categories":["skill-optimizer"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/hqhq1025/skill-optimizer/skill-miner","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add hqhq1025/skill-optimizer","source_repo":"https://github.com/hqhq1025/skill-optimizer","install_from":"skills.sh"}},"qualityScore":"0.489","qualityRationale":"deterministic score 0.49 from registry signals: · indexed on github topic:agent-skills · 79 github stars · SKILL.md body (2,663 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":"2026-05-18T18:56:46.976Z","embedding":null,"createdAt":"2026-05-14T12:57:29.456Z","updatedAt":"2026-05-18T18:56:46.976Z","lastSeenAt":"2026-05-18T18:56:46.976Z","tsv":"'1':144 '2':160 '3':180 '4':195 '5':214 '6':225 '7':246 '8':265 'access':347 'actual':98 'agent':9,27,34,71,82,393 'agents.md':213 'archiv':12 'ask':81,269,302 'automat':410 'avail':179 'avoid':306 'backlog':92 'base':96,342 'becom':25,254 'behavior':320 'better':210 'brainstorm':102 'broad':322 'bundl':240 'bundled-resourc':239 'candid':54,94,216,229,250,291,344,373 'chang':318 'check':331 'cluster':169,181,324 'code':8,70,203 'codex/claude/gemini-style':386 'coding-ag':7,69 'concis':232 'contain':110 'content':297 'creat':272,372,413 'decis':411 'definit':399 'descript':236 'determinist':381 'discov':20 'discovery-rubric.md':361 'draft':56,230,330,375 'enough':285 'everi':308 'evid':59,147,280,287,305,388,404 'exist':103,124 'explicit':301 'export':176,389 'expos':294 'extract':47 'file':174,190 'filter':196 'find':44,351 'first':166 'first-pass':165 'folder':159,276 'friction':219 'frontmatter/layout':279 'full':366 'futur':223,319 'general':142,261 'goal':41 'guidanc':317 'help':378 'hint':327 'histori':11,369 'incomplet':349 'input':390 'instruct':209 'intent':185,323 'jsonl':149 'justifi':289 'keep':80 'knowledg':204 'label':350 'list':355 'local':17,172,387 'locat':145 'log':106 'manual':87 'memori':14,104,150 'mine':6,32 'miner':3,30 'miss':336 'name':234 'nativ':385 'navig':326 'near':335 'need':242 'new':26,37 'note':109,153 'one':199 'one-off':198 'opportun':39 'ordinari':202 'outlin':238 'output':402 'overview':31 'packag':117 'partial':353 'pass':167 'past':68 'pattern':194,395 'person':129,253,397 'phrase':187 'portabl':221 'posit':333 'prefer':314 'privat':136 'procedur':112 'proceed':271 'project':108,158,207 'project-specif':206 'prompt':245 'public':138,256 'publish':134 'quot':282 'rather':100 'raw':304 'read':360 'real':33,146 'recent':157 'recommend':247 'recur':21,111 'recurr':218 'refer':359 'references/discovery-rubric.md':362 'regex':341 'regex-bas':340 'repeat':16,45,74,154,182,309 'repo':152 'report':170 'resourc':241 'reusabl':49 'review':406 'risk':220 'rule':281 'run':161 'sampl':332 'sanit':168 'scan':67,358,370 'scanner':382 'score':215 'script':155 'scripts/scan_sessions.py':162,377 'select':274 'sensit':295 'session':10,72,105,148,173,346,368 'session-histori':367 'similar':85 'skill':2,28,29,38,57,95,125,128,137,141,233,257,260,275,313,329,374,414 'skill-gener':140,259 'skill-min':1 'skill-person':127 'skill-skill-miner' 'skip':264 'sourc':286 'source-hqhq1025' 'specif':208 'stay':252 'strong':53,228 'suit':211 'summar':284 'summari':151 'support':384 'suspect':78 'task':86,201,310 'team':89 'techniqu':50 'tool':188 'topic-agent-skills' 'topic-agentskills' 'topic-ai-visibility' 'topic-claude-code' 'topic-claude-code-skills' 'topic-claude-skill' 'topic-codex' 'topic-codex-skills' 'topic-cursor-skills' 'topic-gemini-cli' 'topic-github-pages' 'topic-llm-agents' 'touch':191 'transcript':13,177,296 'treat':321,400 'trigger':186,235 'trust':338 'tune':122 'turn':52,307 'unless':298 'usag':35 'use':4,62,120,126,132,139,189,376 'user':64,77,268,300 'valid':244 'valu':224 'verif':193 'verifi':278 'via':258 'want':65,90 'whether':248 'work':18,99,183 'workflow':22,46,75,143,237,315,343,398","prices":[{"id":"bd02255f-322a-4990-9a4a-dbb21b10974c","listingId":"edf017ad-54f5-4682-a665-e131f47f3408","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"hqhq1025","category":"skill-optimizer","install_from":"skills.sh"},"createdAt":"2026-05-14T12:57:29.456Z"}],"sources":[{"listingId":"edf017ad-54f5-4682-a665-e131f47f3408","source":"github","sourceId":"hqhq1025/skill-optimizer/skill-miner","sourceUrl":"https://github.com/hqhq1025/skill-optimizer/tree/main/skills/skill-miner","isPrimary":false,"firstSeenAt":"2026-05-14T12:57:29.456Z","lastSeenAt":"2026-05-18T18:56:46.976Z"}],"details":{"listingId":"edf017ad-54f5-4682-a665-e131f47f3408","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"hqhq1025","slug":"skill-miner","github":{"repo":"hqhq1025/skill-optimizer","stars":79,"topics":["agent-skills","agentskills","ai-visibility","claude-code","claude-code-skills","claude-skill","codex","codex-skills","cursor-skills","gemini-cli","github-pages","llm-agents","llms-txt","opencode-skills","prompt-engineering","skill-generalizer","skill-miner","skill-optimizer","skill-personalizer"],"license":"mit","html_url":"https://github.com/hqhq1025/skill-optimizer","pushed_at":"2026-05-14T07:25:31Z","description":"Agent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for public release.","skill_md_sha":"59eeb65b1bd8d07562b52a44fb8b4868c44c1275","skill_md_path":"skills/skill-miner/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/hqhq1025/skill-optimizer/tree/main/skills/skill-miner"},"layout":"multi","source":"github","category":"skill-optimizer","frontmatter":{"name":"skill-miner","description":"Use when mining coding-agent session history, archived transcripts, memories, or repeated local work to discover recurring workflows that should become new Agent Skills."},"skills_sh_url":"https://skills.sh/hqhq1025/skill-optimizer/skill-miner"},"updatedAt":"2026-05-18T18:56:46.976Z"}}