{"id":"749d8a7c-e3e5-4271-9dcd-3933cfcf29b1","shortId":"vK7tFd","kind":"skill","title":"workbench-research","tagline":"Evidence-first research, architecture discovery, vendor documentation review, benchmark reading, and unknown-system analysis.","description":"# Workbench Research\n\nUse this skill for research, architecture discovery, vendor docs, benchmark reading, and unknown-system analysis.\n\n## Research Standard\n\n- Read the real system first when local state exists.\n- Prefer primary sources, live commands, local files, and official docs.\n- Separate confirmed facts, source claims, and inference.\n- Treat current software behavior, API shape, prices, versions, and docs as drift-prone.\n- Cite file paths, command names, issue/comment IDs, or source URLs when they support a claim.\n- Use targeted reads first: indexes, `rg`, `jq`, table summaries, and exact IDs before full documents or full histories.\n- Summarize large sources before handing them to another agent.\n\n## Research Output\n\nReturn:\n\n- `QUESTION`: what was investigated.\n- `CONFIRMED`: facts with evidence.\n- `UNCERTAIN`: assumptions or unresolved gaps.\n- `OPTIONS`: viable paths with tradeoffs.\n- `RECOMMENDATION`: the smallest next action.\n- `SOURCES`: local paths, commands, issue IDs, or URLs used.\n\n## Research Boundaries\n\n- Do not present speculation as fact.\n- Do not copy secrets or private tokens into reports.\n- Do not rewrite working architecture while researching it.\n- If source material conflicts, explain the conflict and prefer live runtime evidence.\n- Stop if the next read would be broad and low-yield; report the smaller evidence query needed instead.","tags":["workbench","research","multica","ultimate","fearvox","agent-skills","ai-agents","claude-code","codex","hermes-agent","sdd","skills-sh"],"capabilities":["skill","source-fearvox","skill-workbench-research","topic-agent-skills","topic-ai-agents","topic-claude-code","topic-codex","topic-hermes-agent","topic-multica","topic-sdd","topic-skills-sh"],"categories":["multica-ultimate-workbench"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-research","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Fearvox/multica-ultimate-workbench","source_repo":"https://github.com/Fearvox/multica-ultimate-workbench","install_from":"skills.sh"}},"qualityScore":"0.456","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 12 github stars · SKILL.md body (1,379 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":"2026-05-18T19:07:14.409Z","embedding":null,"createdAt":"2026-05-13T01:05:03.806Z","updatedAt":"2026-05-18T19:07:14.409Z","lastSeenAt":"2026-05-18T19:07:14.409Z","tsv":"'action':147 'agent':121 'analysi':19,37 'anoth':120 'api':70 'architectur':8,27,178 'assumpt':134 'behavior':69 'benchmark':13,31 'boundari':158 'broad':201 'cite':80 'claim':63,94 'command':53,83,151 'confirm':60,129 'conflict':185,188 'copi':167 'current':67 'discoveri':9,28 'doc':30,58,75 'document':11,109 'drift':78 'drift-pron':77 'evid':5,132,193,209 'evidence-first':4 'exact':105 'exist':48 'explain':186 'fact':61,130,164 'file':55,81 'first':6,44,98 'full':108,111 'gap':137 'hand':117 'histori':112 'id':86,106,153 'index':99 'infer':65 'instead':212 'investig':128 'issu':152 'issue/comment':85 'jq':101 'larg':114 'live':52,191 'local':46,54,149 'low':204 'low-yield':203 'materi':184 'name':84 'need':211 'next':146,197 'offici':57 'option':138 'output':123 'path':82,140,150 'prefer':49,190 'present':161 'price':72 'primari':50 'privat':170 'prone':79 'queri':210 'question':125 'read':14,32,40,97,198 'real':42 'recommend':143 'report':173,206 'research':3,7,21,26,38,122,157,180 'return':124 'review':12 'rewrit':176 'rg':100 'runtim':192 'secret':168 'separ':59 'shape':71 'skill':24 'skill-workbench-research' 'smaller':208 'smallest':145 'softwar':68 'sourc':51,62,88,115,148,183 'source-fearvox' 'specul':162 'standard':39 'state':47 'stop':194 'summar':113 'summari':103 'support':92 'system':18,36,43 'tabl':102 'target':96 'token':171 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-codex' 'topic-hermes-agent' 'topic-multica' 'topic-sdd' 'topic-skills-sh' 'tradeoff':142 'treat':66 'uncertain':133 'unknown':17,35 'unknown-system':16,34 'unresolv':136 'url':89,155 'use':22,95,156 'vendor':10,29 'version':73 'viabl':139 'work':177 'workbench':2,20 'workbench-research':1 'would':199 'yield':205","prices":[{"id":"8542ca00-afa9-4540-951e-a71169880838","listingId":"749d8a7c-e3e5-4271-9dcd-3933cfcf29b1","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Fearvox","category":"multica-ultimate-workbench","install_from":"skills.sh"},"createdAt":"2026-05-13T01:05:03.806Z"}],"sources":[{"listingId":"749d8a7c-e3e5-4271-9dcd-3933cfcf29b1","source":"github","sourceId":"Fearvox/multica-ultimate-workbench/workbench-research","sourceUrl":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-research","isPrimary":false,"firstSeenAt":"2026-05-13T01:05:03.806Z","lastSeenAt":"2026-05-18T19:07:14.409Z"}],"details":{"listingId":"749d8a7c-e3e5-4271-9dcd-3933cfcf29b1","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Fearvox","slug":"workbench-research","github":{"repo":"Fearvox/multica-ultimate-workbench","stars":12,"topics":["agent-skills","ai-agents","claude-code","codex","hermes-agent","multica","sdd","skills-sh"],"license":null,"html_url":"https://github.com/Fearvox/multica-ultimate-workbench","pushed_at":"2026-05-14T23:12:50Z","description":"Public multi-agent workbench skill pack for SDD, review gates, context discipline, VM lanes, Sanity context, and autonomous agent coordination.","skill_md_sha":"cf9c95cebc260849e7ac03ce127559e32ed2064e","skill_md_path":"skills/workbench-research/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-research"},"layout":"multi","source":"github","category":"multica-ultimate-workbench","frontmatter":{"name":"workbench-research","description":"Evidence-first research, architecture discovery, vendor documentation review, benchmark reading, and unknown-system analysis."},"skills_sh_url":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-research"},"updatedAt":"2026-05-18T19:07:14.409Z"}}