{"id":"3125da7b-626a-47d2-8966-c4c60d3b6169","shortId":"DBqnKw","kind":"skill","title":"workbench-waking-up","tagline":"Use when an operator asks what changed recently, what was left hanging, what can move now, \"gm\", \"where are we\", or when a session-derived update needs to become visible to the whole Workbench. Recall recent memory, verify live repo/issue/automation state, surface drift first, an","description":"# Workbench Waking-Up\n\n`workbench-waking-up` is the context-restore protocol for the Multica Ultimate\nWorkbench.\n\nIt pairs with closeout and synthesis work: close the loop with durable evidence,\nthen wake the system by re-reading memory leads and live state before choosing\nwhat to do next.\n\nCore line:\n\n```text\nRestore context. Verify reality. Pick the next move.\n```\n\n## When To Use\n\nUse this skill when the operator says or implies:\n\n- `gm`, `maxxedhere`, `where are we`, `what can move now`;\n- \"最近干了什么\", \"我们能干什么\", \"有没有落下没续的\";\n- \"看看最近的记忆\", \"没聊的时间里更新了什么\";\n- a direct-chat discovery should become visible to the wider Workbench;\n- a session handoff, cron run, Multica issue, repo branch, or runner state may be stale.\n\nDefault to the current Workbench repo and project when the target is obvious.\nAsk only when there are multiple plausible workspaces and the tool calls would\nbe materially different.\n\n## Output Contract\n\nReturn this shape unless the caller asks for a different format:\n\n```text\nGM, operator.\n\nTOPLINE\n- state judgment:\n- confidence: high | medium | low\n- main quest:\n- biggest drift:\n\nWHAT CHANGED WHILE YOU WERE AWAY\nWE'RE SO BACK\n- confirmed landed / verified items\nLET HIM COOK\n- active runs, agents, cron jobs, or dogfoods\nIT'S SO OVER\n- blockers, failed jobs, or evidence gaps\nDO NOT COOK\n- parked, unapproved, dangerous, or explicitly deferred paths\n\nREALITY CHECK\n- repo/git:\n- automation/cron:\n- issues / PRs:\n- knowledge/vault:\n- runners/skills:\n\nOPEN LOOPS\nP0 — must resolve before new work\n- ...\nP1 — high leverage next\n- ...\nP2 — useful but not blocking\n- ...\nPARKED — intentionally not now\n- ...\n\nDROPPED THREADS / NOT YET RESUMED\n- ...\n\nACTION MENU\n1. ...\n2. ...\n3. ...\n\nRECEIPTS\n- commands, issue IDs, commit IDs, session recalls, and uncertainty labels\n```\n\nUse the GM labels lightly. They are shorthand for state, not a substitute for\nproof.\n\n## Evidence Labels\n\nEvery material claim should be traceable to one of these labels:\n\n- `LIVE_VERIFIED` — checked against current repo, issue, cron, CI, runner, or\n  browser state.\n- `CONFIRMED` — backed by a durable source file, decision, issue comment, or\n  committed artifact.\n- `MEMORY_ONLY` — recalled from session memory but not yet live-verified.\n- `FLAGGED` — evidence exists but is inconsistent, partial, or blocked.\n- `STALE` — prior claim is contradicted by current state or has aged out.\n\nMemory is a lead, not truth. Say `memory suggests` until live readback confirms\nit.\n\n## Wake Procedure\n\n### Fast Wake\n\nUse for short orientation prompts.\n\n1. Recall recent sessions or the latest closeout summary.\n2. Check current repo root, branch, `git status --short --branch`, and recent\n   commits.\n3. Check active cron/jobs and obvious Multica issue state if available.\n4. Return the top drift and no more than three next actions.\n\n### Standard Wake\n\nDefault mode.\n\n1. Search memory for current project, recent open-loop terms, and known runner\n   names.\n2. Verify repo state: branch, ahead/behind, dirty files, untracked evidence,\n   recent commits, and remote freshness.\n3. Verify live Workbench surfaces: Multica issue status/runs/comments, cron jobs,\n   autopilots, Research Vault or Sanity context if relevant.\n4. Verify runner health only when it changes the recommendation: Hermes, Codex,\n   `ult-evo`, Capy, MCP, browser/deploy, or remote cell.\n5. Collapse findings into P0/P1/P2/PARKED and a short action menu.\n\n### Deep Wake\n\nUse for a full operating review or multi-repo reset. Add targeted issue run\nmessages, GitHub PR/CI/deploy readbacks, Capy/browser evidence, Research Vault\nqueries, and sanitized screenshots or artifacts when needed.\n\n## Drift-First Rule\n\nReport drift before proposing new work. P0 drift includes:\n\n- branch ahead/behind or dirty baseline;\n- untracked artifacts that might be evidence or noise;\n- cron/autopilot fired but downstream delivery failed;\n- issue state disagrees with run state;\n- `done`, `merged`, `deployed`, or `pushed` claim lacks live readback;\n- Research Vault, Sanity, or runner state contradicts the claimed source;\n- operator decision is still blocking a parent lane.\n\nDo not bury drift under a motivational recap.\n\n## Session-To-Workbench Bridge\n\nWhen a direct chat produces a reusable behavior, packaging direction, or policy\nchange, make it Workbench-visible instead of leaving it hidden in model memory.\nPick the smallest durable surface:\n\n| Durable surface | Use when |\n| --- | --- |\n| `skills/workbench-*/SKILL.md` | the behavior should be reusable by agents |\n| `AGENTS.md` | every agent needs a routing or safety rule |\n| `SYNTHESIS.md` | the operating model or strategy changed |\n| `DECISIONS.md` | the rationale must survive disagreement |\n| `skills/README.md` | the installable skill map changed |\n| issue template or autopilot spec | future tasks need a reusable entry point |\n| sanitized Multica issue/comment | live operators need immediate coordination |\n\nDo not store secrets, raw transcripts, private screenshots, request payloads, or\nlive-only credentials. Store sanitized summaries and pointers only.\n\n## Priority Rules\n\n- **P0**: sync drift, failed automation, blocked operator decision, empty or\n  contradictory run output, missing proof for claimed completion.\n- **P1**: high-leverage review, dogfood gate, bounded issue update, or single\n  synthesis step that unblocks a parent lane.\n- **P2**: useful cleanup, future packaging, optional product/design slices.\n- **PARKED**: explicitly deferred or unapproved routes. Do not revive them\n  without new evidence and operator approval.\n\n## Closeout Checklist\n\nBefore sending a wake report or bridge patch:\n\n- [ ] Memory leads checked or explicitly unavailable.\n- [ ] Live repo/issue/automation state checked when relevant.\n- [ ] Drift appears before new ideas.\n- [ ] Claims are evidence-labeled.\n- [ ] Action menu is capped at three to five moves.\n- [ ] Parked decisions remain parked.\n- [ ] Public docs contain no secrets, raw transcripts, live-only IDs, or private\n      payloads.","tags":["workbench","waking","multica","ultimate","fearvox","agent-skills","ai-agents","claude-code","codex","hermes-agent","sdd","skills-sh"],"capabilities":["skill","source-fearvox","skill-workbench-waking-up","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-waking-up","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 (5,990 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":"2026-05-18T19:07:15.090Z","embedding":null,"createdAt":"2026-05-13T01:05:05.146Z","updatedAt":"2026-05-18T19:07:15.090Z","lastSeenAt":"2026-05-18T19:07:15.090Z","tsv":"'/skill.md':701 '1':302,426,475 '2':303,435,490 '3':304,448,505 '4':459,523 '5':544 'action':300,470,552,873 'activ':239,450 'add':567 'age':401 'agent':241,708,711 'agents.md':709 'ahead/behind':495,601 'appear':864 'approv':840 'artifact':369,584,606 'ask':9,179,203 'autom':784 'automation/cron':269 'autopilot':515,740 'avail':458 'away':227 'back':231,358 'baselin':604 'becom':34,145 'behavior':672,703 'biggest':220 'block':290,390,648,785 'blocker':250 'bound':805 'branch':159,440,444,494,600 'bridg':664,849 'browser':355 'browser/deploy':540 'buri':654 'call':190 'caller':202 'cap':876 'capi':538 'capy/browser':575 'cell':543 'chang':11,223,530,677,724,736 'chat':142,668 'check':267,346,436,449,853,860 'checklist':842 'choos':97 'ci':352 'claim':335,393,630,642,796,868 'cleanup':819 'close':77 'closeout':73,433,841 'codex':534 'collaps':545 'command':306 'comment':366 'commit':309,368,447,501 'complet':797 'confid':214 'confirm':232,357,415 'contain':888 'context':62,106,520 'context-restor':61 'contract':196 'contradict':395,640 'contradictori':790 'cook':238,258 'coordin':756 'core':102 'credenti':771 'cron':154,242,351,513 'cron/autopilot':613 'cron/jobs':451 'current':169,348,397,437,479 'danger':261 'decis':364,645,787,883 'decisions.md':725 'deep':554 'default':166,473 'defer':264,827 'deliveri':617 'deploy':627 'deriv':30 'differ':194,206 'direct':141,667,674 'direct-chat':140 'dirti':496,603 'disagr':730 'disagre':621 'discoveri':143 'doc':887 'dogfood':245,803 'done':625 'downstream':616 'drift':48,221,463,588,592,598,655,782,863 'drift-first':587 'drop':295 'durabl':81,361,694,696 'empti':788 'entri':747 'everi':333,710 'evid':82,254,331,383,499,576,610,837,871 'evidence-label':870 'evo':537 'exist':384 'explicit':263,826,855 'fail':251,618,783 'fast':419 'file':363,497 'find':546 'fire':614 'first':49,589 'five':880 'flag':382 'format':207 'fresh':504 'full':559 'futur':742,820 'gap':255 'gate':804 'git':441 'github':572 'gm':21,125,209,318 'handoff':153 'hang':16 'health':526 'herm':533 'hidden':687 'high':215,283,800 'high-leverag':799 'id':308,310,896 'idea':867 'immedi':755 'impli':124 'includ':599 'inconsist':387 'instal':733 'instead':683 'intent':292 'issu':157,270,307,350,365,455,511,569,619,737,806 'issue/comment':751 'item':235 'job':243,252,514 'judgment':213 'knowledge/vault':272 'known':487 'label':315,319,332,343,872 'lack':631 'land':233 'lane':651,816 'latest':432 'lead':92,406,852 'leav':685 'left':15 'let':236 'leverag':284,801 'light':320 'line':103 'live':44,94,344,380,413,507,632,752,769,857,894 'live-on':768,893 'live-verifi':379 'loop':79,275,484 'low':217 'main':218 'make':678 'map':735 'materi':193,334 'maxxedher':126 'may':163 'mcp':539 'medium':216 'memori':42,91,370,375,403,410,477,690,851 'menu':301,553,874 'merg':626 'messag':571 'might':608 'miss':793 'mode':474 'model':689,721 'motiv':658 'move':19,112,132,881 'multi':564 'multi-repo':563 'multica':67,156,454,510,750 'multipl':184 'must':277,728 'name':489 'need':32,586,712,744,754 'new':280,595,836,866 'next':101,111,285,469 'nois':612 'obvious':178,453 'one':340 'open':274,483 'open-loop':482 'oper':8,121,210,560,644,720,753,786,839 'option':822 'orient':424 'output':195,792 'p0':276,597,780 'p0/p1/p2/parked':548 'p1':282,798 'p2':286,817 'packag':673,821 'pair':71 'parent':650,815 'park':259,291,825,882,885 'partial':388 'patch':850 'path':265 'payload':766,899 'pick':109,691 'plausibl':185 'point':748 'pointer':776 'polici':676 'pr/ci/deploy':573 'prior':392 'prioriti':778 'privat':763,898 'procedur':418 'produc':669 'product/design':823 'project':173,480 'prompt':425 'proof':330,794 'propos':594 'protocol':64 'prs':271 'public':886 'push':629 'queri':579 'quest':219 'rational':727 'raw':761,891 're':89,229 're-read':88 'read':90 'readback':414,574,633 'realiti':108,266 'recal':40,312,372,427 'recap':659 'receipt':305 'recent':12,41,428,446,481,500 'recommend':532 'relev':522,862 'remain':884 'remot':503,542 'repo':158,171,349,438,492,565 'repo/git':268 'repo/issue/automation':45,858 'report':591,847 'request':765 'research':516,577,634 'reset':566 'resolv':278 'restor':63,105 'resum':299 'return':197,460 'reusabl':671,706,746 'review':561,802 'reviv':833 'root':439 'rout':714,830 'rule':590,717,779 'run':155,240,570,623,791 'runner':161,353,488,525,638 'runners/skills':273 'safeti':716 'sanit':581,749,773 'saniti':519,636 'say':122,409 'screenshot':582,764 'search':476 'secret':760,890 'send':844 'session':29,152,311,374,429,661 'session-deriv':28 'session-to-workbench':660 'shape':199 'short':423,443,551 'shorthand':323 'singl':809 'skill':118,734 'skill-workbench-waking-up' 'skills/readme.md':731 'skills/workbench-':700 'slice':824 'smallest':693 'sourc':362,643 'source-fearvox' 'spec':741 'stale':165,391 'standard':471 'state':46,95,162,212,325,356,398,456,493,620,624,639,859 'status':442 'status/runs/comments':512 'step':811 'still':647 'store':759,772 'strategi':723 'substitut':328 'suggest':411 'summari':434,774 'surfac':47,509,695,697 'surviv':729 'sync':781 'synthesi':75,810 'synthesis.md':718 'system':86 'target':176,568 'task':743 'templat':738 'term':485 'text':104,208 'thread':296 'three':468,878 'tool':189 'top':462 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-codex' 'topic-hermes-agent' 'topic-multica' 'topic-sdd' 'topic-skills-sh' 'toplin':211 'traceabl':338 'transcript':762,892 'truth':408 'ult':536 'ult-evo':535 'ultim':68 'unapprov':260,829 'unavail':856 'unblock':813 'uncertainti':314 'unless':200 'untrack':498,605 'updat':31,807 'use':5,115,116,287,316,421,556,698,818 'vault':517,578,635 'verifi':43,107,234,345,381,491,506,524 'visibl':35,146,682 'wake':3,53,57,84,417,420,472,555,846 'waking-up':52 'whole':38 'wider':149 'without':835 'work':76,281,596 'workbench':2,39,51,56,69,150,170,508,663,681 'workbench-vis':680 'workbench-waking-up':1,55 'workspac':186 'would':191 'yet':298,378 '我们能干什么':135 '最近干了什么':134 '有没有落下没续的':136 '没聊的时间里更新了什么':138 '看看最近的记忆':137","prices":[{"id":"ba0b147e-18de-4690-b84d-87f390c72c5d","listingId":"3125da7b-626a-47d2-8966-c4c60d3b6169","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":"2026-05-13T01:05:05.146Z"}],"sources":[{"listingId":"3125da7b-626a-47d2-8966-c4c60d3b6169","source":"github","sourceId":"Fearvox/multica-ultimate-workbench/workbench-waking-up","sourceUrl":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-waking-up","isPrimary":false,"firstSeenAt":"2026-05-13T01:05:05.146Z","lastSeenAt":"2026-05-18T19:07:15.090Z"}],"details":{"listingId":"3125da7b-626a-47d2-8966-c4c60d3b6169","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Fearvox","slug":"workbench-waking-up","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":"370a18f83ebc700cc2a685e8b46a0b412732491d","skill_md_path":"skills/workbench-waking-up/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-waking-up"},"layout":"multi","source":"github","category":"multica-ultimate-workbench","frontmatter":{"name":"workbench-waking-up","description":"Use when an operator asks what changed recently, what was left hanging, what can move now, \"gm\", \"where are we\", or when a session-derived update needs to become visible to the whole Workbench. Recall recent memory, verify live repo/issue/automation state, surface drift first, and produce a short evidence-labeled action menu."},"skills_sh_url":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-waking-up"},"updatedAt":"2026-05-18T19:07:15.090Z"}}