{"id":"53e53c35-b24e-4c5a-8082-19f7d469d95f","shortId":"hTGJ3p","kind":"skill","title":"workbench-windburn-profile","tagline":"Horizontal session personality overlay — auto-detects conversation mode from density signals, defaults casual, upgrades to structured only on sustained signal. Includes CommitMono aesthetic preference and MoE/thinking-chain runtime awareness.","description":"# Workbench Windburn Profile\n\nHorizontal session modifier. Applied once at session start. Changes *how*\nall other skills execute, not *what* they do.\n\nActivate:\n\n```text\n/windburn-profile\n```\n\nOr in a Multica issue: `COMM_PROFILE: windburn`\n\n## Core Behavior\n\n**Default: casual.** Agent assumes low-ceremony, human-speed conversation.\nShort responses, direct answers, no preamble, no \"let me help you with that.\"\nToken budget goes to substance, not structure.\n\n**Auto-detect mode shifts.** Three signals measured continuously:\n\n| Signal | Casual | Structured |\n|--------|--------|-------------|\n| Technical term density | < 5% of tokens | > 12% of tokens |\n| Reference density (paths, hashes, issue IDs) | < 2 per message | > 5 per message |\n| Average sentence length | < 25 words | > 35 words |\n\nAll three above threshold for 2+ consecutive messages → shift to structured.\nAny one drops below → shift back to casual after 1 message (downgrade is fast).\n\n**Explicit switches override auto-detect.** These are atomic — agent switches\nimmediately, no grace period:\n\n| User says | → Mode |\n|-----------|--------|\n| \"spec maxxing\"\"spec mode\"\"full detail\" | structured |\n| \"随便聊聊\"\"casual mode\"\"relax\"\"轻松\" | casual |\n| \"help me think\"\"brainstorm\"\"想一下\" | exploratory (below) |\n\n**Exploratory mode.** Between casual and structured. Agent asks one\nfollow-up at a time, doesn't propose solutions until the shape of the\nproblem is clear. Output density: casual. Question quality: structured.\n\n## Aesthetic Injection\n\nWhen any UI/frontend task is detected:\n- Assume CommitMono or equivalent monospace-first typography\n- Prefer dark dot-matrix or terminal-inspired visual language\n- Don't ask \"what font do you prefer\" — apply, show, iterate\n- Color palette: warm dark base (#080a09 region), green/amber accent\n\nThis applies across all UI-related skills: frontend-design-qa, browser-proofshot-qa, design-docs.\n\n## Runtime Awareness\n\nAgent should acknowledge but not explain:\n- MoE routing and thinking-chain keep deliberation out of output\n- The profile itself exists because of this architecture — without it,\n  structured thinking would flood the conversation\n- Other models (Opus, Grok) keep same tone; quality difference stays in\n  reasoning, not in language\n\n## Anti-Patterns (Suppress These)\n\n- \"好的！让我来帮您处理这个问题\"\n- Structured monologues during casual mode\n- Listing all possible paths when one good default exists\n- Asking \"which approach would you prefer?\" before offering a first judgment\n- Summarizing what just happened when the user watched it happen\n- Socratic questioning when the user explicitly said \"放松\"\n\n## Relationship To Other Skills\n\nThis is a horizontal overlay. It does not replace:\n- `workbench-self-awareness-infra` (still used for Heavy Path, just delivered in Windburn tone)\n- `workbench-sdd` (SDD pipeline unchanged, just communicated with less ceremony in casual mode)\n- `workbench-goal-mode` (goal persistence unchanged, just status updates are tighter)\n- `workbench-conductor` (routing unchanged, just handoffs are less verbose)\n\n## Minimum Viable Signal Detection\n\nThe auto-detect does not need an ML model. A simple heuristic at message\nparse time:\n\n```text\nterm_density = count(technical_nouns) / total_tokens\nref_density = count(file_paths, hashes, issue_ids) / message_count\navg_sentence_length = total_words / sentence_count\n\nif all three > threshold for 2+ messages → structured\nif any one < threshold → casual\nif explicit_switch_word detected → override all\n```\n\nNo persistence needed. Session-scoped. Resets on new session.","tags":["workbench","windburn","profile","multica","ultimate","fearvox","agent-skills","ai-agents","claude-code","codex","hermes-agent","sdd"],"capabilities":["skill","source-fearvox","skill-workbench-windburn-profile","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-windburn-profile","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 (3,547 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":"2026-05-18T19:07:15.176Z","embedding":null,"createdAt":"2026-05-13T01:05:05.230Z","updatedAt":"2026-05-18T19:07:15.176Z","lastSeenAt":"2026-05-18T19:07:15.176Z","tsv":"'/windburn-profile':57 '080a09':278 '1':159 '12':117 '2':126,144,516 '25':135 '35':137 '5':114,129 'accent':281 'acknowledg':305 'across':284 'activ':55 'aesthet':28,235 'agent':70,173,208,303 'answer':82 'anti':352 'anti-pattern':351 'appli':40,270,283 'approach':374 'architectur':327 'ask':209,264,372 'assum':71,243 'atom':172 'auto':10,100,168,471 'auto-detect':9,99,167,470 'averag':132 'avg':504 'awar':33,302,417 'back':155 'base':277 'behavior':67 'brainstorm':198 'browser':295 'browser-proofshot-qa':294 'budget':93 'casual':18,69,109,157,190,194,205,231,361,441,523 'ceremoni':74,439 'chain':314 'chang':45 'clear':228 'color':273 'comm':63 'commitmono':27,244 'communic':436 'conductor':457 'consecut':145 'continu':107 'convers':12,78,335 'core':66 'count':489,496,503,510 'dark':252,276 'default':17,68,370 'deliber':316 'deliv':425 'densiti':15,113,121,230,488,495 'design':292,299 'design-doc':298 'detail':187 'detect':11,101,169,242,468,472,528 'differ':344 'direct':81 'doc':300 'doesn':217 'dot':254 'dot-matrix':253 'downgrad':161 'drop':152 'equival':246 'execut':50 'exist':323,371 'explain':308 'explicit':164,398,525 'exploratori':200,202 'fast':163 'file':497 'first':249,381 'flood':333 'follow':212 'follow-up':211 'font':266 'frontend':291 'frontend-design-qa':290 'full':186 'goal':445,447 'goe':94 'good':369 'grace':177 'green/amber':280 'grok':339 'handoff':461 'happen':386,392 'hash':123,499 'heavi':422 'help':88,195 'heurist':481 'horizont':5,37,408 'human':76 'human-spe':75 'id':125,501 'immedi':175 'includ':26 'infra':418 'inject':236 'inspir':259 'issu':62,124,500 'iter':272 'judgment':382 'keep':315,340 'languag':261,350 'length':134,506 'less':438,463 'let':86 'list':363 'low':73 'low-ceremoni':72 'matrix':255 'maxx':183 'measur':106 'messag':128,131,146,160,483,502,517 'minimum':465 'ml':477 'mode':13,102,181,185,191,203,362,442,446 'model':337,478 'modifi':39 'moe':309 'moe/thinking-chain':31 'monologu':359 'monospac':248 'monospace-first':247 'multica':61 'need':475,533 'new':539 'noun':491 'offer':379 'one':151,210,368,521 'opus':338 'output':229,319 'overlay':8,409 'overrid':166,529 'palett':274 'pars':484 'path':122,366,423,498 'pattern':353 'per':127,130 'period':178 'persist':448,532 'person':7 'pipelin':433 'possibl':365 'preambl':84 'prefer':29,251,269,377 'problem':226 'profil':4,36,64,321 'proofshot':296 'propos':219 'qa':293,297 'qualiti':233,343 'question':232,394 'reason':347 'ref':494 'refer':120 'region':279 'relat':288 'relationship':401 'relax':192 'replac':413 'reset':537 'respons':80 'rout':310,458 'runtim':32,301 'said':399 'say':180 'scope':536 'sdd':431,432 'self':416 'sentenc':133,505,509 'session':6,38,43,535,540 'session-scop':534 'shape':223 'shift':103,147,154 'short':79 'show':271 'signal':16,25,105,108,467 'simpl':480 'skill':49,289,404 'skill-workbench-windburn-profile' 'socrat':393 'solut':220 'source-fearvox' 'spec':182,184 'speed':77 'start':44 'status':451 'stay':345 'still':419 'structur':21,98,110,149,188,207,234,330,358,518 'substanc':96 'summar':383 'suppress':354 'sustain':24 'switch':165,174,526 'task':240 'technic':111,490 'term':112,487 'termin':258 'terminal-inspir':257 'text':56,486 'think':197,313,331 'thinking-chain':312 'three':104,140,513 'threshold':142,514,522 'tighter':454 'time':216,485 'token':92,116,119,493 'tone':342,428 'topic-agent-skills' 'topic-ai-agents' 'topic-claude-code' 'topic-codex' 'topic-hermes-agent' 'topic-multica' 'topic-sdd' 'topic-skills-sh' 'total':492,507 'typographi':250 'ui':287 'ui-rel':286 'ui/frontend':239 'unchang':434,449,459 'updat':452 'upgrad':19 'use':420 'user':179,389,397 'verbos':464 'viabl':466 'visual':260 'warm':275 'watch':390 'windburn':3,35,65,427 'without':328 'word':136,138,508,527 'workbench':2,34,415,430,444,456 'workbench-conductor':455 'workbench-goal-mod':443 'workbench-sdd':429 'workbench-self-awareness-infra':414 'workbench-windburn-profil':1 'would':332,375 '好的':356 '想一下':199 '放松':400 '让我来帮您处理这个问题':357 '轻松':193 '随便聊聊':189","prices":[{"id":"1a7ecc66-d9df-494e-a3e2-f76ecd4c4781","listingId":"53e53c35-b24e-4c5a-8082-19f7d469d95f","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":"2026-05-13T01:05:05.230Z"}],"sources":[{"listingId":"53e53c35-b24e-4c5a-8082-19f7d469d95f","source":"github","sourceId":"Fearvox/multica-ultimate-workbench/workbench-windburn-profile","sourceUrl":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-windburn-profile","isPrimary":false,"firstSeenAt":"2026-05-13T01:05:05.230Z","lastSeenAt":"2026-05-18T19:07:15.176Z"}],"details":{"listingId":"53e53c35-b24e-4c5a-8082-19f7d469d95f","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Fearvox","slug":"workbench-windburn-profile","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":"7c1ae83098ab352bee56e4c376d90b0b09c9ba7b","skill_md_path":"skills/workbench-windburn-profile/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Fearvox/multica-ultimate-workbench/tree/main/skills/workbench-windburn-profile"},"layout":"multi","source":"github","category":"multica-ultimate-workbench","frontmatter":{"name":"workbench-windburn-profile","description":"Horizontal session personality overlay — auto-detects conversation mode from density signals, defaults casual, upgrades to structured only on sustained signal. Includes CommitMono aesthetic preference and MoE/thinking-chain runtime awareness."},"skills_sh_url":"https://skills.sh/Fearvox/multica-ultimate-workbench/workbench-windburn-profile"},"updatedAt":"2026-05-18T19:07:15.176Z"}}