[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFMWTA6VYRCN2MW1AJXW7T":3,"skill-same:01M6CFMWTA6VYRCN2MW1AJXW7T":99},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":21,"linkOnly":22,"markdownContent":23,"markdownBody":24,"frontMatter":25,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M6CFMWTA6VYRCN2MW1AJXW7T","byan-orchestrate",null,"Yan-Acadenice\u002FBYAN","Yan-Acadenice","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F110977877?v=4","01M6CFGFGY3B09FREH3M92YYN6","Yan Bourquard-Ania","01M6CFGFN0YBX55ZNYX7GHA6SF",8,"MIT","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-orchestrate\u002FSKILL.md",[],[18,19,20],"orchestrate","byan orchestrate","byan","2026-11-10 10:12:30",false,"---\nname: byan-orchestrate\ndescription: Orchestrate a complex multi-role task across the BYAN roster with token-optimal model assignment and parallel execution. Use when a single task decomposes into 2+ distinct roles (e.g. \"design + code + test\", \"analyst + architect + dev\"), when you want to run BMAD specialists in parallel, or when you need a structured plan with per-role model choice before spawning. Extends byan-hermes-dispatch from 1-shot to N-role workflows. Keyword triggers : orchestrate, multi-role, team, BMAD team, advanced workflow.\n---\n\n# BYAN Advanced Orchestrator\n\nYou compose three existing building blocks into one multi-role flow :\n\n| Block | Role |\n|-------|------|\n| `byan_dispatch` MCP tool | Per-task strategy (main-thread \u002F agent-subagent-worktree \u002F mcp-worker) from the score + model tier by NATURE (haiku for exploration, else inherit the session model) + complexity score |\n| `byan-hermes-dispatch` skill | Specialist lookup (architect, dev, analyst, …) from a routing table |\n| `party-mode-native` workflow | Parallel spawn via Agent tool + worktree + coordination JSON |\n\nYour job : **minimize total tokens while keeping the deliverable correct**. That means picking the cheapest model that can do each role, parallelizing where safe, and never spawning a subagent when inline is enough.\n\n## Protocol\n\n### 1. Decompose the user task into roles\n\nOutput a role list of the form :\n```json\n[\n  { \"role\": \"analyst\", \"goal\": \"understand market\u002Fusers\", \"parallelizable_with\": [\"architect\"] },\n  { \"role\": \"architect\", \"goal\": \"pick tech stack + shape\", \"parallelizable_with\": [\"analyst\"] },\n  { \"role\": \"dev\", \"goal\": \"implement feature X\", \"parallelizable_with\": [] },\n  { \"role\": \"quinn\", \"goal\": \"validate with tests\", \"parallelizable_with\": [] }\n]\n```\n\nAsk the user to validate the role list before spawning (show it as a table). Do NOT auto-execute a 4-agent team without a yes.\n\n### 2. Pick model per role (token optimization)\n\nUse this a priori mapping — override only if the task clearly needs more :\n\n| Role category | Default model | Rationale |\n|---|---|---|\n| analyst, pm, sm, ux-designer, tech-writer, brainstorming-coach, storyteller | sonnet | Text structuring, not deep reasoning |\n| dev, quick-flow-solo-dev | sonnet | Code generation, mid complexity |\n| architect, quinn, tea, creative-problem-solver | opus | Deep reasoning, trade-offs |\n| carmack, rachid, patnote | haiku | Narrow mechanical tasks |\n\nThen call `byan_dispatch` with each role's goal (and `nature` when known). Use its `score` for the STRATEGY only (score \u003C 15 → inline, no subagent ; 15-39 → subagent\u002Fworker ; ≥ 40 → keep the heavy role in the main thread) and its nature-based `model` as the tier signal. The score sets WHERE the role runs, not WHICH model — keep protected roles (verify\u002Fanalysis\u002Fimplement) off haiku regardless of size, and avoid pinning a role up to opus on size alone. The per-role table above is the a-priori floor; `byan_dispatch`'s nature `model` refines it.\n\n### 3. Compute the execution plan\n\nFor each role, combine the model and the dispatch strategy to produce :\n\n```json\n{\n  \"role\": \"dev\",\n  \"model\": \"sonnet\",\n  \"strategy\": \"agent-subagent-worktree\",\n  \"score\": 28,\n  \"parallelizable_with\": [\"quinn\"],\n  \"estimated_tokens\": 8000\n}\n```\n\n`estimated_tokens` : rough = `model_boot_tokens + goal.length \u002F 4 * 3`. `model_boot_tokens` ≈ 5000 (Haiku), 7000 (Sonnet), 10000 (Opus).\n\nSum over all roles = **session budget estimate**. Show this to the user before spawning.\n\n### 4. Spawn\n\nGroup roles by `parallelizable_with` graph. For each parallel cluster :\n\n- If cluster has N > 1 roles AND all use `agent-subagent-worktree` strategy → use the **party-mode-native** workflow : `coordination.initSession(roles, …)`, then dispatch all Agent tool calls in a single message.\n- If cluster has N = 1 OR strategy = `main-thread` → execute inline in the current turn.\n\nOn a 2+ role spawn, open the shared board for visibility (the kanban family is built for exactly this) : after `coordination.initSession`, call `byan_kanban_create({ sessionId: \u003Cthe party-mode session id> })`, then once per role `byan_kanban_add({ sessionId, card: { id: \u003Crole>, title: \u003Crole> } })`. The card `id` is the ROLE NAME — unique per role, and the key the move step references; do NOT reuse the session id (the cards share one board, ids must differ). A multi-agent run without a board is invisible to the user.\n- If strategy = `mcp-worker` → spawn an Agent tool call WITHOUT worktree (faster boot, single-turn) ; set the Agent's model to the role's nature-based `model` (haiku for exploration, omit otherwise to inherit the session model).\n\nFor each Agent tool call, the prompt must start with :\n```\nYou are acting as the \u003Crole> BMAD agent. Load your persona from\n.claude\u002Fagents\u002Fbmad-\u003Crole>.md (read it first, then respond in\ncharacter). Task: \u003Cgoal>. Deliverables: \u003Clist>. Report back as JSON\nwith status\u002Fsummary\u002Ffiles_changed per the party-mode-native contract.\n```\n\n### 5. Aggregate and report\n\nAfter all subagents return (or inline roles finish), read each `agent-\u003Crole>.json` via `coordination.readAgentReport` (report contract : `{ status: ok|partial|failed, summary, files_changed, next_steps }`). Then, for EACH returned role (post all of them — an `ok` post writes an empty `blockers` array, which resets that role's streak ; skipping `ok` roles breaks the streak math) :\n- Post its standup : `byan_standup_post({ sessionId, agent: \u003Crole>, did: \u003Creport.summary>, blockers: \u003Creport.status is 'failed' or 'partial' ? [report.summary] : []>, next: \u003C(report.next_steps || []).join('; ')> })`. The report contract has NO `blockers` field — synthesize it from a non-`ok` status (an `ok` role posts `[]`).\n- Move its card : `byan_kanban_move({ sessionId, cardId: \u003Crole>, toColumn: \u003Creport ok ? 'review' : 'blocked'>, blocker_reason: \u003Creport ok ? omit : report.summary> })`. `cardId` is the role name set at add time. Use `review`, not `done`, on success — the human gate owns completion; `done` is the user's call, not the orchestrator self-certifying.\n\nThen surface stuck roles : `byan_standup_blocked({ sessionId, minStreak: 1 })` — `minStreak: 1` because the aggregate posts exactly one stand-up per role, so a single `blocked`\u002F`failed`\u002F`partial` report should flag (a 2-in-a-row streak is unreachable in a single pass). If it returns flagged roles, raise them in the report. Finally write `summary.md` via `coordination.writeSummary` and report to the user :\n\n| Role | Model | Strategy | Tokens spent | Outcome |\n|------|-------|----------|--------------|---------|\n| analyst | sonnet | worktree | 7200 | ok |\n| architect | opus | worktree | 11500 | ok |\n| dev | sonnet | worktree | 9800 | ok |\n| quinn | opus | main-thread | 6400 | ok |\n\nTotal tokens : 34900. Deliverable : \u003Clink to aggregated output>.\n\n## Invariants\n\n- **Never spawn without showing the plan first.** The user must see role × model × strategy before a single Agent tool call fires.\n- **Never default to opus.** Opus is opt-in via high complexity score or explicit role mapping. Default = sonnet, upgrade only with justification in the plan.\n- **Never parallel-spawn roles that write to the same paths.** If file scopes overlap, serialize them even if `parallelizable_with` suggests otherwise.\n- **Never ship a plan without `estimated_tokens` per role.** Budget visibility is the whole point.\n- **Open the board on every 2+ role spawn.** `byan_kanban_create` + a card per role ; a multi-agent run without a board hides the work from the user.\n- **Post every role's standup at aggregate, `ok` included.** Posting only failed roles breaks the blocked-streak reset and re-hides a stuck agent — the exact silence this wiring removes.\n","# BYAN Advanced Orchestrator\n\nYou compose three existing building blocks into one multi-role flow :\n\n| Block | Role |\n|-------|------|\n| `byan_dispatch` MCP tool | Per-task strategy (main-thread \u002F agent-subagent-worktree \u002F mcp-worker) from the score + model tier by NATURE (haiku for exploration, else inherit the session model) + complexity score |\n| `byan-hermes-dispatch` skill | Specialist lookup (architect, dev, analyst, …) from a routing table |\n| `party-mode-native` workflow | Parallel spawn via Agent tool + worktree + coordination JSON |\n\nYour job : **minimize total tokens while keeping the deliverable correct**. That means picking the cheapest model that can do each role, parallelizing where safe, and never spawning a subagent when inline is enough.\n\n## Protocol\n\n### 1. Decompose the user task into roles\n\nOutput a role list of the form :\n```json\n[\n  { \"role\": \"analyst\", \"goal\": \"understand market\u002Fusers\", \"parallelizable_with\": [\"architect\"] },\n  { \"role\": \"architect\", \"goal\": \"pick tech stack + shape\", \"parallelizable_with\": [\"analyst\"] },\n  { \"role\": \"dev\", \"goal\": \"implement feature X\", \"parallelizable_with\": [] },\n  { \"role\": \"quinn\", \"goal\": \"validate with tests\", \"parallelizable_with\": [] }\n]\n```\n\nAsk the user to validate the role list before spawning (show it as a table). Do NOT auto-execute a 4-agent team without a yes.\n\n### 2. Pick model per role (token optimization)\n\nUse this a priori mapping — override only if the task clearly needs more :\n\n| Role category | Default model | Rationale |\n|---|---|---|\n| analyst, pm, sm, ux-designer, tech-writer, brainstorming-coach, storyteller | sonnet | Text structuring, not deep reasoning |\n| dev, quick-flow-solo-dev | sonnet | Code generation, mid complexity |\n| architect, quinn, tea, creative-problem-solver | opus | Deep reasoning, trade-offs |\n| carmack, rachid, patnote | haiku | Narrow mechanical tasks |\n\nThen call `byan_dispatch` with each role's goal (and `nature` when known). Use its `score` for the STRATEGY only (score \u003C 15 → inline, no subagent ; 15-39 → subagent\u002Fworker ; ≥ 40 → keep the heavy role in the main thread) and its nature-based `model` as the tier signal. The score sets WHERE the role runs, not WHICH model — keep protected roles (verify\u002Fanalysis\u002Fimplement) off haiku regardless of size, and avoid pinning a role up to opus on size alone. The per-role table above is the a-priori floor; `byan_dispatch`'s nature `model` refines it.\n\n### 3. Compute the execution plan\n\nFor each role, combine the model and the dispatch strategy to produce :\n\n```json\n{\n  \"role\": \"dev\",\n  \"model\": \"sonnet\",\n  \"strategy\": \"agent-subagent-worktree\",\n  \"score\": 28,\n  \"parallelizable_with\": [\"quinn\"],\n  \"estimated_tokens\": 8000\n}\n```\n\n`estimated_tokens` : rough = `model_boot_tokens + goal.length \u002F 4 * 3`. `model_boot_tokens` ≈ 5000 (Haiku), 7000 (Sonnet), 10000 (Opus).\n\nSum over all roles = **session budget estimate**. Show this to the user before spawning.\n\n### 4. Spawn\n\nGroup roles by `parallelizable_with` graph. For each parallel cluster :\n\n- If cluster has N > 1 roles AND all use `agent-subagent-worktree` strategy → use the **party-mode-native** workflow : `coordination.initSession(roles, …)`, then dispatch all Agent tool calls in a single message.\n- If cluster has N = 1 OR strategy = `main-thread` → execute inline in the current turn.\n\nOn a 2+ role spawn, open the shared board for visibility (the kanban family is built for exactly this) : after `coordination.initSession`, call `byan_kanban_create({ sessionId: \u003Cthe party-mode session id> })`, then once per role `byan_kanban_add({ sessionId, card: { id: \u003Crole>, title: \u003Crole> } })`. The card `id` is the ROLE NAME — unique per role, and the key the move step references; do NOT reuse the session id (the cards share one board, ids must differ). A multi-agent run without a board is invisible to the user.\n- If strategy = `mcp-worker` → spawn an Agent tool call WITHOUT worktree (faster boot, single-turn) ; set the Agent's model to the role's nature-based `model` (haiku for exploration, omit otherwise to inherit the session model).\n\nFor each Agent tool call, the prompt must start with :\n```\nYou are acting as the \u003Crole> BMAD agent. Load your persona from\n.claude\u002Fagents\u002Fbmad-\u003Crole>.md (read it first, then respond in\ncharacter). Task: \u003Cgoal>. Deliverables: \u003Clist>. Report back as JSON\nwith status\u002Fsummary\u002Ffiles_changed per the party-mode-native contract.\n```\n\n### 5. Aggregate and report\n\nAfter all subagents return (or inline roles finish), read each `agent-\u003Crole>.json` via `coordination.readAgentReport` (report contract : `{ status: ok|partial|failed, summary, files_changed, next_steps }`). Then, for EACH returned role (post all of them — an `ok` post writes an empty `blockers` array, which resets that role's streak ; skipping `ok` roles breaks the streak math) :\n- Post its standup : `byan_standup_post({ sessionId, agent: \u003Crole>, did: \u003Creport.summary>, blockers: \u003Creport.status is 'failed' or 'partial' ? [report.summary] : []>, next: \u003C(report.next_steps || []).join('; ')> })`. The report contract has NO `blockers` field — synthesize it from a non-`ok` status (an `ok` role posts `[]`).\n- Move its card : `byan_kanban_move({ sessionId, cardId: \u003Crole>, toColumn: \u003Creport ok ? 'review' : 'blocked'>, blocker_reason: \u003Creport ok ? omit : report.summary> })`. `cardId` is the role name set at add time. Use `review`, not `done`, on success — the human gate owns completion; `done` is the user's call, not the orchestrator self-certifying.\n\nThen surface stuck roles : `byan_standup_blocked({ sessionId, minStreak: 1 })` — `minStreak: 1` because the aggregate posts exactly one stand-up per role, so a single `blocked`\u002F`failed`\u002F`partial` report should flag (a 2-in-a-row streak is unreachable in a single pass). If it returns flagged roles, raise them in the report. Finally write `summary.md` via `coordination.writeSummary` and report to the user :\n\n| Role | Model | Strategy | Tokens spent | Outcome |\n|------|-------|----------|--------------|---------|\n| analyst | sonnet | worktree | 7200 | ok |\n| architect | opus | worktree | 11500 | ok |\n| dev | sonnet | worktree | 9800 | ok |\n| quinn | opus | main-thread | 6400 | ok |\n\nTotal tokens : 34900. Deliverable : \u003Clink to aggregated output>.\n\n## Invariants\n\n- **Never spawn without showing the plan first.** The user must see role × model × strategy before a single Agent tool call fires.\n- **Never default to opus.** Opus is opt-in via high complexity score or explicit role mapping. Default = sonnet, upgrade only with justification in the plan.\n- **Never parallel-spawn roles that write to the same paths.** If file scopes overlap, serialize them even if `parallelizable_with` suggests otherwise.\n- **Never ship a plan without `estimated_tokens` per role.** Budget visibility is the whole point.\n- **Open the board on every 2+ role spawn.** `byan_kanban_create` + a card per role ; a multi-agent run without a board hides the work from the user.\n- **Post every role's standup at aggregate, `ok` included.** Posting only failed roles breaks the blocked-streak reset and re-hides a stuck agent — the exact silence this wiring removes.\n",{},"main","7b63cfa91942025012f072f78abcf3ed511c4e16","install\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-orchestrate",0,"https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN","https:\u002F\u002Fgithub.com\u002FYan-Acadenice","2026-09-14 05:00:51",{"source":7,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Yan-Acadenice\u002FBYAN --skill byan-orchestrate",{"tool":39,"command":40},"bunx","bunx skills add Yan-Acadenice\u002FBYAN --skill byan-orchestrate",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Yan-Acadenice\u002FBYAN --skill byan-orchestrate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-orchestrate\u002FSKILL.md",true,[47,53,57,61,65,69,75,79,83,87,91,95],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fadvanced.md","REFERENCE","参考文档",15766,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Freferences\u002Fadvanced.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fanalysis.md",10738,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Freferences\u002Fanalysis.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fcore_concepts.md",8483,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Freferences\u002Fcore_concepts.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftime_evolution.md",13786,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Freferences\u002Ftime_evolution.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fvisualization.md",8997,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Freferences\u002Fvisualization.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002F_common.py","SCRIPT","脚本",12072,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Fscripts\u002F_common.py",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fconvergence_sweep.py",12418,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Fscripts\u002Fconvergence_sweep.py",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fqobj_model_validator.py",10979,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Fscripts\u002Fqobj_model_validator.py",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Fresult_audit.py",12463,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Fscripts\u002Fresult_audit.py",{"path":88,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fsolver_config_planner.py",11165,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Fscripts\u002Fsolver_config_planner.py",{"path":92,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fsteady_state_spectrum_planner.py",7981,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Fscripts\u002Fsteady_state_spectrum_planner.py",{"path":96,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":97,"sourceHtmlUrl":98},"scripts\u002Ftwo_level_simulation.py",13224,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fkdense-qutip\u002Fscripts\u002Ftwo_level_simulation.py",[100,112,136,145,155,174],{"skillNo":101,"name":20,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":21},"01M6CFNCP049TQ871KM35G8QEC","BYAN local project skill. Use when working in the BYAN repo, invoking BYAN agents\u002Fworkflows\u002Fcommands, enforcing BYAN Strict Mode, or needing the portable BYAN filesystem map.","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.codex\u002Fskills\u002Fbyan\u002FSKILL.md",[],[20,106,107,108,109,110,111],"project skill","use","repo","filesystem","workflows","byan strict",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":123,"publishedAt":21},"01M6CFNA3FVVS5AM46ZA63YDGA","byan-yanstaller","Yanstaller - Multi-Platform BYAN Installer Agent Role: Installation Expert + Platform Detection Specialist + Zero-Config Automation. Invoke when user mentions : AUTO, DETECT, HELP, EXIT.","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-yanstaller\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[20,124,125,126,127,128,129,130,131,132,133,134,135],"byan yanstaller","config","exit","expert","installer","auto","user","detection","ZeRO","help","automation","platform detection",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":21},"01M6CFN8VA7EJ2NW3BA2X9H06J","byan-tea-tea","tea agent","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-tea-tea\u002FSKILL.md",[],[143,20,144],"tea","byan tea tea",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":21},"01M6CFN7CFFBN3G3A7448FBX43","byan-suitability","Advisory model-suitability ledger — record adversarial verdicts, read learned ratings, human decides downgrades","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-suitability\u002FSKILL.md",[],[20,152,153,154],"byan suitability","read","model",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":21},"01M6CFN527VW62GZPVZFJBRQ8S","byan-strict","Enforcement mode that prevents scope downgrade and forces the agent to self-verify its work against the originally locked request before delivering. Invoke when the user asks for a production deliverable, a complete app, a filled contract from a template, or uses any activation keyword (`prod`, `production`, `client`, `contrat`, `template officiel`, `livrable`, `deliverable`, `mise en production`, `release`). Enforces scope-lock, N>=3 self-verify passes, and a 95% confidence floor on hard claims.","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-strict\u002FSKILL.md",[161],{"categoryNo":119,"categoryName":120,"taxonomyType":121,"taxonomyTypeDesc":122},[20,111,163,130,164,165,166,167,168,169,170,171,172,173],"work","en","enforcement","activation","verify","mise","template","Production","release","status","MCP",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":21},"01M6CFN409BDRSPHP0NJ96S1YM","byan-skeptic","Scientific Claim Challenger and Epistemic Guard","https:\u002F\u002Fgithub.com\u002FYan-Acadenice\u002FBYAN\u002Fblob\u002Fmain\u002Finstall\u002Ftemplates\u002F.claude\u002Fskills\u002Fbyan-skeptic\u002FSKILL.md",[],[181,20,182,183],"skeptic","byan skeptic","guard"]