[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-council-plan":3,"mdc-bwgdw6-key":36,"related-repo-microsoft-council-plan":552,"related-org-microsoft-council-plan":636},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"council-plan","perform multi-model council planning","Multi-model council planning for implementation and architecture decisions. Use when the user asks to 'plan with council', 'multi-model plan', 'get different perspectives on approach', 'council plan', or wants multiple models to independently propose plans for the same task. Also use when the user asks to 'debate approaches', 'compare strategies', or 'cross-plan'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"microsoft","Microsoft","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmicrosoft.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Architecture","architecture","tag",{"name":17,"slug":18,"type":15},"System Design","system-design",{"name":20,"slug":21,"type":15},"Engineering","engineering",{"name":23,"slug":24,"type":15},"Multi-Agent","multi-agent",25,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode-team-kit","2026-05-13T06:14:08.529779",null,5,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"Plugins the VS Code team uses","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode-team-kit\u002Ftree\u002FHEAD\u002Fmodel-council\u002Fskills\u002Fcouncil-plan","---\nname: council-plan\ndescription: \"Multi-model council planning for implementation and architecture decisions. Use when the user asks to 'plan with council', 'multi-model plan', 'get different perspectives on approach', 'council plan', or wants multiple models to independently propose plans for the same task. Also use when the user asks to 'debate approaches', 'compare strategies', or 'cross-plan'.\"\n---\n\n# Skill: Plan Council\n\nMulti-model planning powered by a council of model-pinned agents. Each agent independently researches the codebase and proposes an implementation plan for the same task. The orchestrator then synthesizes the proposals into a consensus plan — surfacing approaches the models agree on, alternatives where they diverge, and risks multiple models flagged independently.\n\nThis catches blind spots that a single-model plan misses: one model might notice a reusable pattern another overlooks, or flag an architectural risk the others didn't consider.\n\n## Council Models\n\nSpawn subagents with the `model` parameter to pin each to a different model. Use all three when available, at least two otherwise:\n\n- `GPT-5.5`\n- `Claude Opus 4.6`\n- `GPT-5.3-Codex`\n\nEach subagent receives the same system preamble:\n\n> You are an independent subagent for read-only code research.\n> MUST stay read-only. Stay within the requested scope.\n> Do not speculate. Do not suggest patches.\n> For every finding, cite exact files and lines.\n> Form your own view from first principles. Do not anchor to the provided context.\n\n## Workflow\n\n### Phase 1 — Scope\n\nEstablish what needs to be planned:\n\n- Gather the user's goal, constraints, and any relevant context (issue, PR description, conversation history).\n- If the task is vague, ask the user to clarify scope before fanning out — council time is expensive.\n- Run an Explore subagent to gather baseline codebase context: relevant files, existing patterns, analogous features. This context goes into the planner prompt so agents start informed.\n\n### Phase 2 — Build a Planning Brief\n\nBefore fanning out, build a **preliminary orientation** that each agent will receive. This is a starting point, not ground truth — agents are expected to contradict it if their own research leads elsewhere.\n\nThe brief should include only:\n1. **Goal** — what needs to be built or changed, and why.\n2. **Constraints** — technical constraints explicitly stated by the user (not inferred).\n3. **Codebase context** — file and directory paths discovered in Phase 1. No conclusions, no risk assessments — just locations.\n4. **Open questions** — unresolved areas where the user has not stated a preference.\n\nKeep the brief under ~50 lines. Do not answer the open questions — leave them open so agents form independent views. The agents will use search, read and terminal tools to dig into specifics.\n\n### Phase 3 — Independent Planning\n\nSpawn all subagents in parallel at once:\n- One subagent per model using the `model` parameter. Prepend the system preamble to the planner prompt below.\n- Do **not** share one agent's proposal with another before this phase completes.\n\n### Phase 4 — Consensus Synthesis\n\nCompare the three proposals and classify into:\n\n1. **Consensus approach** — two or more agents independently propose the same approach, architecture, or sequencing. These form the backbone of the plan. High confidence.\n2. **Alternatives** — agents propose different viable approaches for the same aspect. Present each with trade-offs and a recommendation. Let the user decide or pick the approach with the strongest rationale.\n3. **Consensus risks** — risks or concerns flagged by two or more agents independently. These are high-confidence and should be addressed in the plan.\n4. **Single-agent insights** — a useful idea only one agent surfaced. Keep if well-evidenced, note it came from one model.\n\nDrop vague suggestions, over-engineering proposals, and speculative concerns.\n\n### Phase 5 — Debate (optional)\n\nTrigger this phase when the user asks to \"debate\", \"discuss\", or \"cross-plan\", or when Phase 4 produces significant alternatives that could benefit from deliberation.\n\n1. Share the anonymized synthesis (without attributing which model said what) back to each council agent.\n2. Ask each agent to evaluate the alternatives and state which approach they'd recommend, with evidence.\n3. Spawn all subagents in parallel at once.\n4. Update the synthesis: promote alternatives to consensus if deliberation resolves the split, or sharpen the trade-off description if it persists.\n\nThis deliberation step is lightweight — it only re-examines the synthesized plan, not the full codebase.\n\n## Planner Prompt\n\nUse this prompt shape for each council agent. Pass the planning brief from Phase 2.\n\n```text\nYou are an independent planning agent. Research and propose an implementation plan for this task.\n\n## Goal\n\u003Cgoal from Phase 2>\n\n## Constraints\n\u003Cconstraints from Phase 2>\n\n## Codebase context\n\u003Ckey files, patterns, analogous features from Phase 2>\n\n## Open questions\n\u003Careas where you should propose an approach>\n\nUse your tools to read relevant files, search for patterns, and check diagnostics. Do not rely solely on this brief — explore the codebase yourself to find reusable patterns, potential conflicts, and implementation details.\n\n**The brief above is preliminary orientation, not ground truth.** If your own research contradicts the stated constraints, context, or framing, trust your findings over the brief and say so explicitly.\n\nReturn a structured plan:\n1. **Approach** — your recommended implementation strategy in 2-3 sentences.\n2. **Steps** — ordered implementation steps with file paths. Note dependencies between steps.\n3. **Files to modify** — each file with a one-line description of what changes.\n4. **Risks** — concrete risks or gotchas you found (not speculative concerns).\n5. **Alternatives considered** — other approaches you evaluated and why you didn't recommend them.\n\nBe specific. Reference exact functions, types, and patterns. Do not suggest code edits — describe what needs to change and why.\nIf the task is straightforward with one obvious approach, say so and keep the plan short.\n```\n\n## Debate Prompt\n\nUse this prompt shape when running Phase 5:\n\n```text\nThe following plan was synthesized from independent proposals by a council of planning agents:\n\n\u003Csynthesized plan, without model attribution>\n\nFor each alternative or contested decision, state which approach you recommend and why. Cite files, patterns, or constraints as evidence.\n\nDo not introduce entirely new approaches. Stay focused on the presented alternatives.\nIf you agree with the consensus, say so briefly and move on.\n```\n\n## Saving the Plan\n\nAfter synthesis, persist the consensus plan so it is available for implementation, follow-up turns, and cross-referencing with reviews. Use whichever mechanism the runtime provides:\n\n- If a plan-mode tool is available (e.g., `exit_plan_mode`), use it to present the plan for user approval.\n- Otherwise, save the plan to session memory as `plan.md`.\n\n## Output Shape\n\n### After Phase 4 (standard planning)\n\n**Goal** — one-sentence restatement of what's being planned.\n\n**Consensus approach** — the implementation strategy the council agrees on. Structured as ordered steps with file paths and dependencies.\n\n**Alternatives** (if any) — aspects where agents proposed different approaches. For each: the options, trade-offs, and a recommendation.\n\n**Consensus risks** — risks flagged by multiple agents. Each with a mitigation suggestion.\n\n**Single-agent insights** (if any) — useful ideas from one model, noted as lower confidence.\n\n**Verification** — how to validate the implementation (specific tests, commands, checks).\n\n### After Phase 5 (debate)\n\nSame structure as above, but update based on deliberation:\n- Alternatives that reached agreement move to Consensus approach.\n- Sharpen trade-off descriptions for alternatives where the split persists.\n- Note any risks that were upgraded or downgraded after debate.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,56,61,68,82,114,119,128,134,141,146,164,170,183,188,232,237,243,248,275,281,286,329,334,340,345,368,373,379,384,396,402,407,416,422,427,456,462,468,477,486,495,504,513,523,529,534],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"skill-plan-council",[47],{"type":48,"value":49},"text","Skill: Plan Council",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Multi-model planning powered by a council of model-pinned agents. Each agent independently researches the codebase and proposes an implementation plan for the same task. The orchestrator then synthesizes the proposals into a consensus plan — surfacing approaches the models agree on, alternatives where they diverge, and risks multiple models flagged independently.",{"type":42,"tag":51,"props":57,"children":58},{},[59],{"type":48,"value":60},"This catches blind spots that a single-model plan misses: one model might notice a reusable pattern another overlooks, or flag an architectural risk the others didn't consider.",{"type":42,"tag":62,"props":63,"children":65},"h2",{"id":64},"council-models",[66],{"type":48,"value":67},"Council Models",{"type":42,"tag":51,"props":69,"children":70},{},[71,73,80],{"type":48,"value":72},"Spawn subagents with the ",{"type":42,"tag":74,"props":75,"children":77},"code",{"className":76},[],[78],{"type":48,"value":79},"model",{"type":48,"value":81}," parameter to pin each to a different model. Use all three when available, at least two otherwise:",{"type":42,"tag":83,"props":84,"children":85},"ul",{},[86,96,105],{"type":42,"tag":87,"props":88,"children":89},"li",{},[90],{"type":42,"tag":74,"props":91,"children":93},{"className":92},[],[94],{"type":48,"value":95},"GPT-5.5",{"type":42,"tag":87,"props":97,"children":98},{},[99],{"type":42,"tag":74,"props":100,"children":102},{"className":101},[],[103],{"type":48,"value":104},"Claude Opus 4.6",{"type":42,"tag":87,"props":106,"children":107},{},[108],{"type":42,"tag":74,"props":109,"children":111},{"className":110},[],[112],{"type":48,"value":113},"GPT-5.3-Codex",{"type":42,"tag":51,"props":115,"children":116},{},[117],{"type":48,"value":118},"Each subagent receives the same system preamble:",{"type":42,"tag":120,"props":121,"children":122},"blockquote",{},[123],{"type":42,"tag":51,"props":124,"children":125},{},[126],{"type":48,"value":127},"You are an independent subagent for read-only code research.\nMUST stay read-only. Stay within the requested scope.\nDo not speculate. Do not suggest patches.\nFor every finding, cite exact files and lines.\nForm your own view from first principles. Do not anchor to the provided context.",{"type":42,"tag":62,"props":129,"children":131},{"id":130},"workflow",[132],{"type":48,"value":133},"Workflow",{"type":42,"tag":135,"props":136,"children":138},"h3",{"id":137},"phase-1-scope",[139],{"type":48,"value":140},"Phase 1 — Scope",{"type":42,"tag":51,"props":142,"children":143},{},[144],{"type":48,"value":145},"Establish what needs to be planned:",{"type":42,"tag":83,"props":147,"children":148},{},[149,154,159],{"type":42,"tag":87,"props":150,"children":151},{},[152],{"type":48,"value":153},"Gather the user's goal, constraints, and any relevant context (issue, PR description, conversation history).",{"type":42,"tag":87,"props":155,"children":156},{},[157],{"type":48,"value":158},"If the task is vague, ask the user to clarify scope before fanning out — council time is expensive.",{"type":42,"tag":87,"props":160,"children":161},{},[162],{"type":48,"value":163},"Run an Explore subagent to gather baseline codebase context: relevant files, existing patterns, analogous features. This context goes into the planner prompt so agents start informed.",{"type":42,"tag":135,"props":165,"children":167},{"id":166},"phase-2-build-a-planning-brief",[168],{"type":48,"value":169},"Phase 2 — Build a Planning Brief",{"type":42,"tag":51,"props":171,"children":172},{},[173,175,181],{"type":48,"value":174},"Before fanning out, build a ",{"type":42,"tag":176,"props":177,"children":178},"strong",{},[179],{"type":48,"value":180},"preliminary orientation",{"type":48,"value":182}," that each agent will receive. This is a starting point, not ground truth — agents are expected to contradict it if their own research leads elsewhere.",{"type":42,"tag":51,"props":184,"children":185},{},[186],{"type":48,"value":187},"The brief should include only:",{"type":42,"tag":189,"props":190,"children":191},"ol",{},[192,202,212,222],{"type":42,"tag":87,"props":193,"children":194},{},[195,200],{"type":42,"tag":176,"props":196,"children":197},{},[198],{"type":48,"value":199},"Goal",{"type":48,"value":201}," — what needs to be built or changed, and why.",{"type":42,"tag":87,"props":203,"children":204},{},[205,210],{"type":42,"tag":176,"props":206,"children":207},{},[208],{"type":48,"value":209},"Constraints",{"type":48,"value":211}," — technical constraints explicitly stated by the user (not inferred).",{"type":42,"tag":87,"props":213,"children":214},{},[215,220],{"type":42,"tag":176,"props":216,"children":217},{},[218],{"type":48,"value":219},"Codebase context",{"type":48,"value":221}," — file and directory paths discovered in Phase 1. No conclusions, no risk assessments — just locations.",{"type":42,"tag":87,"props":223,"children":224},{},[225,230],{"type":42,"tag":176,"props":226,"children":227},{},[228],{"type":48,"value":229},"Open questions",{"type":48,"value":231}," — unresolved areas where the user has not stated a preference.",{"type":42,"tag":51,"props":233,"children":234},{},[235],{"type":48,"value":236},"Keep the brief under ~50 lines. Do not answer the open questions — leave them open so agents form independent views. The agents will use search, read and terminal tools to dig into specifics.",{"type":42,"tag":135,"props":238,"children":240},{"id":239},"phase-3-independent-planning",[241],{"type":48,"value":242},"Phase 3 — Independent Planning",{"type":42,"tag":51,"props":244,"children":245},{},[246],{"type":48,"value":247},"Spawn all subagents in parallel at once:",{"type":42,"tag":83,"props":249,"children":250},{},[251,263],{"type":42,"tag":87,"props":252,"children":253},{},[254,256,261],{"type":48,"value":255},"One subagent per model using the ",{"type":42,"tag":74,"props":257,"children":259},{"className":258},[],[260],{"type":48,"value":79},{"type":48,"value":262}," parameter. Prepend the system preamble to the planner prompt below.",{"type":42,"tag":87,"props":264,"children":265},{},[266,268,273],{"type":48,"value":267},"Do ",{"type":42,"tag":176,"props":269,"children":270},{},[271],{"type":48,"value":272},"not",{"type":48,"value":274}," share one agent's proposal with another before this phase completes.",{"type":42,"tag":135,"props":276,"children":278},{"id":277},"phase-4-consensus-synthesis",[279],{"type":48,"value":280},"Phase 4 — Consensus Synthesis",{"type":42,"tag":51,"props":282,"children":283},{},[284],{"type":48,"value":285},"Compare the three proposals and classify into:",{"type":42,"tag":189,"props":287,"children":288},{},[289,299,309,319],{"type":42,"tag":87,"props":290,"children":291},{},[292,297],{"type":42,"tag":176,"props":293,"children":294},{},[295],{"type":48,"value":296},"Consensus approach",{"type":48,"value":298}," — two or more agents independently propose the same approach, architecture, or sequencing. These form the backbone of the plan. High confidence.",{"type":42,"tag":87,"props":300,"children":301},{},[302,307],{"type":42,"tag":176,"props":303,"children":304},{},[305],{"type":48,"value":306},"Alternatives",{"type":48,"value":308}," — agents propose different viable approaches for the same aspect. Present each with trade-offs and a recommendation. Let the user decide or pick the approach with the strongest rationale.",{"type":42,"tag":87,"props":310,"children":311},{},[312,317],{"type":42,"tag":176,"props":313,"children":314},{},[315],{"type":48,"value":316},"Consensus risks",{"type":48,"value":318}," — risks or concerns flagged by two or more agents independently. These are high-confidence and should be addressed in the plan.",{"type":42,"tag":87,"props":320,"children":321},{},[322,327],{"type":42,"tag":176,"props":323,"children":324},{},[325],{"type":48,"value":326},"Single-agent insights",{"type":48,"value":328}," — a useful idea only one agent surfaced. Keep if well-evidenced, note it came from one model.",{"type":42,"tag":51,"props":330,"children":331},{},[332],{"type":48,"value":333},"Drop vague suggestions, over-engineering proposals, and speculative concerns.",{"type":42,"tag":135,"props":335,"children":337},{"id":336},"phase-5-debate-optional",[338],{"type":48,"value":339},"Phase 5 — Debate (optional)",{"type":42,"tag":51,"props":341,"children":342},{},[343],{"type":48,"value":344},"Trigger this phase when the user asks to \"debate\", \"discuss\", or \"cross-plan\", or when Phase 4 produces significant alternatives that could benefit from deliberation.",{"type":42,"tag":189,"props":346,"children":347},{},[348,353,358,363],{"type":42,"tag":87,"props":349,"children":350},{},[351],{"type":48,"value":352},"Share the anonymized synthesis (without attributing which model said what) back to each council agent.",{"type":42,"tag":87,"props":354,"children":355},{},[356],{"type":48,"value":357},"Ask each agent to evaluate the alternatives and state which approach they'd recommend, with evidence.",{"type":42,"tag":87,"props":359,"children":360},{},[361],{"type":48,"value":362},"Spawn all subagents in parallel at once.",{"type":42,"tag":87,"props":364,"children":365},{},[366],{"type":48,"value":367},"Update the synthesis: promote alternatives to consensus if deliberation resolves the split, or sharpen the trade-off description if it persists.",{"type":42,"tag":51,"props":369,"children":370},{},[371],{"type":48,"value":372},"This deliberation step is lightweight — it only re-examines the synthesized plan, not the full codebase.",{"type":42,"tag":62,"props":374,"children":376},{"id":375},"planner-prompt",[377],{"type":48,"value":378},"Planner Prompt",{"type":42,"tag":51,"props":380,"children":381},{},[382],{"type":48,"value":383},"Use this prompt shape for each council agent. Pass the planning brief from Phase 2.",{"type":42,"tag":385,"props":386,"children":391},"pre",{"className":387,"code":389,"language":48,"meta":390},[388],"language-text","You are an independent planning agent. Research and propose an implementation plan for this task.\n\n## Goal\n\u003Cgoal from Phase 2>\n\n## Constraints\n\u003Cconstraints from Phase 2>\n\n## Codebase context\n\u003Ckey files, patterns, analogous features from Phase 2>\n\n## Open questions\n\u003Careas where you should propose an approach>\n\nUse your tools to read relevant files, search for patterns, and check diagnostics. Do not rely solely on this brief — explore the codebase yourself to find reusable patterns, potential conflicts, and implementation details.\n\n**The brief above is preliminary orientation, not ground truth.** If your own research contradicts the stated constraints, context, or framing, trust your findings over the brief and say so explicitly.\n\nReturn a structured plan:\n1. **Approach** — your recommended implementation strategy in 2-3 sentences.\n2. **Steps** — ordered implementation steps with file paths. Note dependencies between steps.\n3. **Files to modify** — each file with a one-line description of what changes.\n4. **Risks** — concrete risks or gotchas you found (not speculative concerns).\n5. **Alternatives considered** — other approaches you evaluated and why you didn't recommend them.\n\nBe specific. Reference exact functions, types, and patterns. Do not suggest code edits — describe what needs to change and why.\nIf the task is straightforward with one obvious approach, say so and keep the plan short.\n","",[392],{"type":42,"tag":74,"props":393,"children":394},{"__ignoreMap":390},[395],{"type":48,"value":389},{"type":42,"tag":62,"props":397,"children":399},{"id":398},"debate-prompt",[400],{"type":48,"value":401},"Debate Prompt",{"type":42,"tag":51,"props":403,"children":404},{},[405],{"type":48,"value":406},"Use this prompt shape when running Phase 5:",{"type":42,"tag":385,"props":408,"children":411},{"className":409,"code":410,"language":48,"meta":390},[388],"The following plan was synthesized from independent proposals by a council of planning agents:\n\n\u003Csynthesized plan, without model attribution>\n\nFor each alternative or contested decision, state which approach you recommend and why. Cite files, patterns, or constraints as evidence.\n\nDo not introduce entirely new approaches. Stay focused on the presented alternatives.\nIf you agree with the consensus, say so briefly and move on.\n",[412],{"type":42,"tag":74,"props":413,"children":414},{"__ignoreMap":390},[415],{"type":48,"value":410},{"type":42,"tag":62,"props":417,"children":419},{"id":418},"saving-the-plan",[420],{"type":48,"value":421},"Saving the Plan",{"type":42,"tag":51,"props":423,"children":424},{},[425],{"type":48,"value":426},"After synthesis, persist the consensus plan so it is available for implementation, follow-up turns, and cross-referencing with reviews. Use whichever mechanism the runtime provides:",{"type":42,"tag":83,"props":428,"children":429},{},[430,443],{"type":42,"tag":87,"props":431,"children":432},{},[433,435,441],{"type":48,"value":434},"If a plan-mode tool is available (e.g., ",{"type":42,"tag":74,"props":436,"children":438},{"className":437},[],[439],{"type":48,"value":440},"exit_plan_mode",{"type":48,"value":442},"), use it to present the plan for user approval.",{"type":42,"tag":87,"props":444,"children":445},{},[446,448,454],{"type":48,"value":447},"Otherwise, save the plan to session memory as ",{"type":42,"tag":74,"props":449,"children":451},{"className":450},[],[452],{"type":48,"value":453},"plan.md",{"type":48,"value":455},".",{"type":42,"tag":62,"props":457,"children":459},{"id":458},"output-shape",[460],{"type":48,"value":461},"Output Shape",{"type":42,"tag":135,"props":463,"children":465},{"id":464},"after-phase-4-standard-planning",[466],{"type":48,"value":467},"After Phase 4 (standard planning)",{"type":42,"tag":51,"props":469,"children":470},{},[471,475],{"type":42,"tag":176,"props":472,"children":473},{},[474],{"type":48,"value":199},{"type":48,"value":476}," — one-sentence restatement of what's being planned.",{"type":42,"tag":51,"props":478,"children":479},{},[480,484],{"type":42,"tag":176,"props":481,"children":482},{},[483],{"type":48,"value":296},{"type":48,"value":485}," — the implementation strategy the council agrees on. Structured as ordered steps with file paths and dependencies.",{"type":42,"tag":51,"props":487,"children":488},{},[489,493],{"type":42,"tag":176,"props":490,"children":491},{},[492],{"type":48,"value":306},{"type":48,"value":494}," (if any) — aspects where agents proposed different approaches. For each: the options, trade-offs, and a recommendation.",{"type":42,"tag":51,"props":496,"children":497},{},[498,502],{"type":42,"tag":176,"props":499,"children":500},{},[501],{"type":48,"value":316},{"type":48,"value":503}," — risks flagged by multiple agents. Each with a mitigation suggestion.",{"type":42,"tag":51,"props":505,"children":506},{},[507,511],{"type":42,"tag":176,"props":508,"children":509},{},[510],{"type":48,"value":326},{"type":48,"value":512}," (if any) — useful ideas from one model, noted as lower confidence.",{"type":42,"tag":51,"props":514,"children":515},{},[516,521],{"type":42,"tag":176,"props":517,"children":518},{},[519],{"type":48,"value":520},"Verification",{"type":48,"value":522}," — how to validate the implementation (specific tests, commands, checks).",{"type":42,"tag":135,"props":524,"children":526},{"id":525},"after-phase-5-debate",[527],{"type":48,"value":528},"After Phase 5 (debate)",{"type":42,"tag":51,"props":530,"children":531},{},[532],{"type":48,"value":533},"Same structure as above, but update based on deliberation:",{"type":42,"tag":83,"props":535,"children":536},{},[537,542,547],{"type":42,"tag":87,"props":538,"children":539},{},[540],{"type":48,"value":541},"Alternatives that reached agreement move to Consensus approach.",{"type":42,"tag":87,"props":543,"children":544},{},[545],{"type":48,"value":546},"Sharpen trade-off descriptions for alternatives where the split persists.",{"type":42,"tag":87,"props":548,"children":549},{},[550],{"type":48,"value":551},"Note any risks that were upgraded or downgraded after debate.",{"items":553,"total":635},[554,561,576,590,601,612,621],{"slug":4,"name":4,"fn":5,"description":6,"org":555,"tags":556,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[557,558,559,560],{"name":13,"slug":14,"type":15},{"name":20,"slug":21,"type":15},{"name":23,"slug":24,"type":15},{"name":17,"slug":18,"type":15},{"slug":562,"name":562,"fn":563,"description":564,"org":565,"tags":566,"stars":25,"repoUrl":26,"updatedAt":575},"council-review","perform multi-model council code reviews","Multi-model council review for diffs, pull requests, and risky changes. It is CRITICAL to use this skill after ANY non-trivial development phase — changes are usually not 100% correct. Development CANNOT be called done until the code has been reviewed. Use whenever the user asks for a review, PR feedback, a bug hunt in recent edits, or wants multiple models to inspect the same change independently. Also use when the user asks to 'discuss findings', 'cross-review', or 'debate' review results between models.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[567,570,571,572],{"name":568,"slug":569,"type":15},"Code Review","code-review",{"name":20,"slug":21,"type":15},{"name":23,"slug":24,"type":15},{"name":573,"slug":574,"type":15},"Pull Requests","pull-requests","2026-05-13T06:14:07.202801",{"slug":577,"name":577,"fn":578,"description":579,"org":580,"tags":581,"stars":25,"repoUrl":26,"updatedAt":589},"follow-goal","manage agent goals and stopping conditions","Give the agent a durable objective with a verifiable stopping condition, then keep iterating across turns until that condition is met. Use when the user says 'set a goal', 'follow a goal', '\u002Fgoal …', 'keep working until …', or asks for a long-running task with a clear end state (migrations, large refactors, retry-until-green loops, experiments).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[582,585,586],{"name":583,"slug":584,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":587,"slug":588,"type":15},"Productivity","productivity","2026-07-07T06:54:04.263607",{"slug":591,"name":591,"fn":592,"description":593,"org":594,"tags":595,"stars":25,"repoUrl":26,"updatedAt":600},"inbox-add-reaction","add reactions to GitHub issues and PRs","Add a reaction to a GitHub issue or pull request",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[596,599],{"name":597,"slug":598,"type":15},"GitHub","github",{"name":573,"slug":574,"type":15},"2026-07-07T06:53:33.958298",{"slug":602,"name":602,"fn":603,"description":604,"org":605,"tags":606,"stars":25,"repoUrl":26,"updatedAt":611},"inbox-install-gh-cli","install GitHub CLI","Install the GitHub CLI (gh) if not already installed",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[607,610],{"name":608,"slug":609,"type":15},"CLI","cli",{"name":597,"slug":598,"type":15},"2026-05-13T06:14:05.911879",{"slug":613,"name":613,"fn":614,"description":615,"org":616,"tags":617,"stars":25,"repoUrl":26,"updatedAt":620},"inbox-mark-all-read","mark GitHub notifications as read","Mark all GitHub notifications as read",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[618,619],{"name":597,"slug":598,"type":15},{"name":587,"slug":588,"type":15},"2026-05-13T06:14:02.019522",{"slug":622,"name":622,"fn":623,"description":624,"org":625,"tags":626,"stars":25,"repoUrl":26,"updatedAt":634},"inbox-memory","manage agent memory and rules","Read and write agent storage — memory and rules with environment-aware fallback",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[627,628,631],{"name":583,"slug":584,"type":15},{"name":629,"slug":630,"type":15},"Configuration","configuration",{"name":632,"slug":633,"type":15},"Memory","memory","2026-05-13T06:14:00.740431",14,{"items":637,"total":826},[638,658,677,698,713,730,741,754,769,782,801,814],{"slug":639,"name":639,"fn":640,"description":641,"org":642,"tags":643,"stars":655,"repoUrl":656,"updatedAt":657},"rushstack-best-practices","manage Rush monorepos with best practices","Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[644,645,648,649,652],{"name":20,"slug":21,"type":15},{"name":646,"slug":647,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":650,"slug":651,"type":15},"Project Management","project-management",{"name":653,"slug":654,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":659,"name":659,"fn":660,"description":661,"org":662,"tags":663,"stars":674,"repoUrl":675,"updatedAt":676},"azure-ai-agents-persistent-dotnet","build AI agents with Azure .NET SDK","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[664,667,668,671],{"name":665,"slug":666,"type":15},".NET","net",{"name":583,"slug":584,"type":15},{"name":669,"slug":670,"type":15},"Azure","azure",{"name":672,"slug":673,"type":15},"LLM","llm",2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":678,"name":678,"fn":679,"description":680,"org":681,"tags":682,"stars":674,"repoUrl":675,"updatedAt":697},"azure-ai-anomalydetector-java","build anomaly detection applications with Java","Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate\u002Fmultivariate anomaly detection, time-series analysis, or AI-powered monitoring.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[683,686,687,690,693,694],{"name":684,"slug":685,"type":15},"Analytics","analytics",{"name":669,"slug":670,"type":15},{"name":688,"slug":689,"type":15},"Data Analysis","data-analysis",{"name":691,"slug":692,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":695,"slug":696,"type":15},"Monitoring","monitoring","2026-05-13T06:14:16.261754",{"slug":699,"name":699,"fn":700,"description":701,"org":702,"tags":703,"stars":674,"repoUrl":675,"updatedAt":712},"azure-ai-contentsafety-java","build content moderation applications with Azure AI","Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[704,707,708,709],{"name":705,"slug":706,"type":15},"AI Infrastructure","ai-infrastructure",{"name":669,"slug":670,"type":15},{"name":691,"slug":692,"type":15},{"name":710,"slug":711,"type":15},"Security","security","2026-07-07T06:53:31.293235",{"slug":714,"name":714,"fn":715,"description":716,"org":717,"tags":718,"stars":674,"repoUrl":675,"updatedAt":729},"azure-ai-contentsafety-py","detect harmful content with Azure AI Content Safety","Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\nTriggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[719,720,723,724,725,728],{"name":669,"slug":670,"type":15},{"name":721,"slug":722,"type":15},"Compliance","compliance",{"name":672,"slug":673,"type":15},{"name":9,"slug":8,"type":15},{"name":726,"slug":727,"type":15},"Python","python",{"name":710,"slug":711,"type":15},"2026-07-18T05:14:23.017504",{"slug":731,"name":731,"fn":732,"description":733,"org":734,"tags":735,"stars":674,"repoUrl":675,"updatedAt":740},"azure-ai-language-conversations-py","implement conversational language understanding with Python","Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[736,737,738,739],{"name":684,"slug":685,"type":15},{"name":669,"slug":670,"type":15},{"name":672,"slug":673,"type":15},{"name":726,"slug":727,"type":15},"2026-07-31T05:54:29.068751",{"slug":742,"name":742,"fn":743,"description":744,"org":745,"tags":746,"stars":674,"repoUrl":675,"updatedAt":753},"azure-ai-translation-text-py","translate text using Azure AI services","Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.\nTriggers: \"text translation\", \"translator\", \"translate text\", \"transliterate\", \"TextTranslationClient\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[747,750,751,752],{"name":748,"slug":749,"type":15},"API Development","api-development",{"name":669,"slug":670,"type":15},{"name":9,"slug":8,"type":15},{"name":726,"slug":727,"type":15},"2026-07-18T05:14:16.988376",{"slug":755,"name":755,"fn":756,"description":757,"org":758,"tags":759,"stars":674,"repoUrl":675,"updatedAt":768},"azure-ai-vision-imageanalysis-py","analyze images with Azure AI Vision","Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.\nTriggers: \"image analysis\", \"computer vision\", \"OCR\", \"object detection\", \"ImageAnalysisClient\", \"image caption\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[760,761,764,767],{"name":669,"slug":670,"type":15},{"name":762,"slug":763,"type":15},"Computer Vision","computer-vision",{"name":765,"slug":766,"type":15},"Images","images",{"name":726,"slug":727,"type":15},"2026-07-18T05:14:18.007737",{"slug":770,"name":770,"fn":771,"description":772,"org":773,"tags":774,"stars":674,"repoUrl":675,"updatedAt":781},"azure-appconfiguration-java","manage configuration with Azure App Configuration","Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.\nTriggers: \"ConfigurationClient java\", \"app configuration java\", \"feature flag java\", \"configuration setting java\", \"azure config java\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[775,776,777,780],{"name":669,"slug":670,"type":15},{"name":629,"slug":630,"type":15},{"name":778,"slug":779,"type":15},"Feature Flags","feature-flags",{"name":691,"slug":692,"type":15},"2026-07-03T16:32:01.278468",{"slug":783,"name":783,"fn":784,"description":785,"org":786,"tags":787,"stars":674,"repoUrl":675,"updatedAt":800},"azure-cosmos-rust","build applications with Azure Cosmos DB","Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data.\nTriggers: \"cosmos db rust\", \"CosmosClient rust\", \"document crud rust\", \"NoSQL rust\", \"partition key rust\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[788,791,794,797],{"name":789,"slug":790,"type":15},"Cosmos DB","cosmos-db",{"name":792,"slug":793,"type":15},"Database","database",{"name":795,"slug":796,"type":15},"NoSQL","nosql",{"name":798,"slug":799,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":802,"name":802,"fn":784,"description":803,"org":804,"tags":805,"stars":674,"repoUrl":675,"updatedAt":813},"azure-cosmos-ts","Azure Cosmos DB JavaScript\u002FTypeScript SDK (@azure\u002Fcosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: \"Cosmos DB\", \"@azure\u002Fcosmos\", \"CosmosClient\", \"document CRUD\", \"NoSQL queries\", \"bulk operations\", \"partition key\", \"container.items\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[806,807,808,809,810],{"name":789,"slug":790,"type":15},{"name":792,"slug":793,"type":15},{"name":9,"slug":8,"type":15},{"name":795,"slug":796,"type":15},{"name":811,"slug":812,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":815,"name":815,"fn":816,"description":817,"org":818,"tags":819,"stars":674,"repoUrl":675,"updatedAt":825},"azure-data-tables-java","build table storage applications with Java","Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[820,821,822,823,824],{"name":669,"slug":670,"type":15},{"name":789,"slug":790,"type":15},{"name":792,"slug":793,"type":15},{"name":691,"slug":692,"type":15},{"name":795,"slug":796,"type":15},"2026-05-13T06:14:17.582229",267]