{"id":"286acc59-d831-433c-ae8f-00d1fa9424fa","shortId":"8LyGSJ","kind":"skill","title":"workbench-review-qa","tagline":"PASS, FLAG, and BLOCK review discipline for workflow review, QA verification, release checks, and issue closeout.","description":"# Workbench Review QA\n\nUse this skill for code review, workflow review, QA verification, release checks, and issue closeout.\n\n## Verdicts\n\n- `PASS`: objective is met and evidence is sufficient.\n- `FLAG`: useful progress, but a non-blocking issue or missing evidence remains.\n- `BLOCK`: objective is not met, unsafe, unverifiable, or materially wrong.\n\n## Review Method\n\n1. Identify the promised objective.\n2. Inspect the real output, diff, issue comments, runtime state, or checked-out repo.\n3. Compare evidence against the objective.\n4. Verify the smallest real path that proves the claim.\n5. Report findings first, ordered by severity.\n6. Check command syntax and live-resource ownership when the work involves Multica CLI mutations.\n7. If duplicate comments or artifacts exist, identify the primary artifact and explain why.\n8. For `GOAL_MODE: yes` or `/goal` work, compare the closeout against the locked objective and every required closeout gate.\n\n## Findings Format\n\nFor problems, return:\n\n- severity,\n- location or evidence,\n- why it matters,\n- required fix or next verification.\n\nFor clean reviews, return:\n\n- verdict,\n- `VERDICT_SUMMARY`: three lines or fewer,\n- evidence checked,\n- residual risk or test gap.\n\nEvery SDD review should include `VERDICT_SUMMARY` so the next agent can continue from the review header without re-reading the full review body.\n\n## Auto Review Sweeper\n\nFor automatic `in_review` handoffs, use this exact block on each reviewed target:\n\n```text\nAUTO_REVIEW\nTARGET: <identifier>\nVERDICT: PASS | FLAG | BLOCK\nVERDICT_SUMMARY: three lines or fewer\nEVIDENCE: concrete issue/comment/run IDs, commands, or file paths checked\nSTATUS_ACTION: done | kept in_review | blocked | no_change\nNEXT_ACTION: exact next owner/action, or none\n```\n\n- `PASS` may move the target issue to `done` only when the original goal is satisfied and no required follow-up remains.\n- `FLAG` leaves the issue in `in_review` with a bounded next action.\n- `BLOCK` sets the issue to `blocked` with blocking evidence.\n- If evidence is still arriving, leave the issue unchanged and mark it pending in the sweep summary.\n\n## QA Rules\n\n- Do not accept `done` based on paraphrase alone.\n- Distinguish content failures from workflow/tooling failures.\n- If repo access is needed, prefer the issue's project-bound GitHub repo resource and report the commit/branch inspected.\n- For Goal Mode tasks, `PASS` requires evidence for the locked objective plus all relevant build/test/help-smoke/docs-or-report/git-status gates, or an explicit rationale for each non-applicable gate.\n- Treat `file://<LOCAL_WORKBENCH_REPO>` as laptop-local fallback only; remote runtimes must flag it as invalid unless explicitly mounted.\n- Keep evidence concise and reproducible.\n- Verify `Workbench Max` remains untouched when a task says it must be preserved.","tags":["workbench","review","multica","ultimate","fearvox","agent-skills","ai-agents","claude-code","codex","hermes-agent","sdd","skills-sh"],"capabilities":["skill","source-fearvox","skill-workbench-review-qa","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-review-qa","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 (2,830 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":"2026-05-18T19:07:14.504Z","embedding":null,"createdAt":"2026-05-13T01:05:03.929Z","updatedAt":"2026-05-18T19:07:14.504Z","lastSeenAt":"2026-05-18T19:07:14.504Z","tsv":"'/goal':152 '1':73 '2':78 '3':93 '4':99 '5':109 '6':116 '7':132 '8':146 'accept':345 'access':359 'action':266,275,314 'agent':211 'alon':350 'applic':401 'arriv':328 'artifact':137,142 'auto':226,243 'automat':230 'base':347 'block':8,55,61,237,249,271,315,320,322 'bodi':225 'bound':312,368 'build/test/help-smoke/docs-or-report/git-status':391 'chang':273 'check':17,35,90,117,195,264 'checked-out':89 'claim':108 'clean':184 'cli':130 'closeout':20,38,156,164 'code':28 'command':118,260 'comment':85,135 'commit/branch':375 'compar':94,154 'concis':422 'concret':257 'content':352 'continu':213 'diff':83 'disciplin':10 'distinguish':351 'done':267,288,346 'duplic':134 'everi':162,201 'evid':45,59,95,174,194,256,323,325,383,421 'exact':236,276 'exist':138 'explain':144 'explicit':395,418 'failur':353,356 'fallback':408 'fewer':193,255 'file':262 'find':111,166 'first':112 'fix':179 'flag':6,48,248,303,413 'follow':300 'follow-up':299 'format':167 'full':223 'gap':200 'gate':165,392,402 'github':369 'goal':148,293,378 'handoff':233 'header':217 'id':259 'identifi':74,139 'includ':205 'inspect':79,376 'invalid':416 'involv':128 'issu':19,37,56,84,286,306,318,331,364 'issue/comment/run':258 'keep':420 'kept':268 'laptop':406 'laptop-loc':405 'leav':304,329 'line':191,253 'live':122 'live-resourc':121 'local':407 'locat':172 'lock':159,386 'mark':334 'materi':69 'matter':177 'max':427 'may':282 'met':43,65 'method':72 'miss':58 'mode':149,379 'mount':419 'move':283 'multica':129 'must':412,435 'mutat':131 'need':361 'next':181,210,274,277,313 'non':54,400 'non-applic':399 'non-block':53 'none':280 'object':41,62,77,98,160,387 'order':113 'origin':292 'output':82 'owner/action':278 'ownership':124 'paraphras':349 'pass':5,40,247,281,381 'path':104,263 'pend':336 'plus':388 'prefer':362 'preserv':437 'primari':141 'problem':169 'progress':50 'project':367 'project-bound':366 'promis':76 'prove':106 'qa':4,14,23,32,341 'rational':396 're':220 're-read':219 'read':221 'real':81,103 'releas':16,34 'relev':390 'remain':60,302,428 'remot':410 'repo':92,358,370 'report':110,373 'reproduc':424 'requir':163,178,298,382 'residu':196 'resourc':123,371 'return':170,186 'review':3,9,13,22,29,31,71,185,203,216,224,227,232,240,244,270,309 'risk':197 'rule':342 'runtim':86,411 'satisfi':295 'say':433 'sdd':202 'set':316 'sever':115,171 'skill':26 'skill-workbench-review-qa' 'smallest':102 'source-fearvox' 'state':87 'status':265 'still':327 'suffici':47 'summari':189,207,251,340 'sweep':339 'sweeper':228 'syntax':119 'target':241,245,285 'task':380,432 'test':199 'text':242 'three':190,252 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-codex' 'topic-hermes-agent' 'topic-multica' 'topic-sdd' 'topic-skills-sh' 'treat':403 'unchang':332 'unless':417 'unsaf':66 'untouch':429 'unverifi':67 'use':24,49,234 'verdict':39,187,188,206,246,250 'verif':15,33,182 'verifi':100,425 'without':218 'work':127,153 'workbench':2,21,426 'workbench-review-qa':1 'workflow':12,30 'workflow/tooling':355 'wrong':70 'yes':150","prices":[{"id":"6bbe1a02-c285-4ae5-9c97-275e13590c1b","listingId":"286acc59-d831-433c-ae8f-00d1fa9424fa","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":"2026-05-13T01:05:03.929Z"}],"sources":[{"listingId":"286acc59-d831-433c-ae8f-00d1fa9424fa","source":"github","sourceId":"Fearvox/multica-ultimate-workbench/workbench-review-qa","sourceUrl":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-review-qa","isPrimary":false,"firstSeenAt":"2026-05-13T01:05:03.929Z","lastSeenAt":"2026-05-18T19:07:14.504Z"}],"details":{"listingId":"286acc59-d831-433c-ae8f-00d1fa9424fa","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Fearvox","slug":"workbench-review-qa","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":"71f1511d7af1033ffae21bb83512972ab44451ca","skill_md_path":"skills/workbench-review-qa/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-review-qa"},"layout":"multi","source":"github","category":"multica-ultimate-workbench","frontmatter":{"name":"workbench-review-qa","description":"PASS, FLAG, and BLOCK review discipline for workflow review, QA verification, release checks, and issue closeout."},"skills_sh_url":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-review-qa"},"updatedAt":"2026-05-18T19:07:14.504Z"}}