[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AVH4KNP3TCVQDRVS70VP19":3,"skill-same:01M7AVH4KNP3TCVQDRVS70VP19":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7AVH4KNP3TCVQDRVS70VP19","tiered-memory",null,"Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","alonf\u002FKeyContextAI","alonf","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F554150?v=4","01M7ATEPSCNKG13BVTKA74VG59","Alon Fliess","01M7ATEPSZ4YMBM9W25SKM3GES",0,"MIT","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tiered-memory\ndescription: Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn\ndomain: memory-management, performance\nconfidence: design (runtime not yet implemented)\nsource: design proposal\n---\n\n# Skill: Tiered Agent Memory\n\n> **Status (v0.10.0):** This skill describes a **design proposal**, not a shipped runtime. Skill files install via `squad init`\u002F`upgrade`, but the underlying tier scaffolding (`.squad\u002Fmemory\u002Fhot\u002F`, `cold\u002F`, `wiki\u002F`), Scribe promotion logic, and spawn-template tier-aware reads are tracked in [bradygaster\u002Fsquad#1264](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F1264). Until those land, agents continue to load full `history.md` + `decisions.md` on every spawn.\n\n## Overview\n\nSquad agents today load their full context history on every spawn, which grows unboundedly across sessions. The Tiered Agent Memory model proposes a three-tier separation so agents only load the bytes that are actually relevant to the current task, with older context kept available on demand.\n\n---\n\n## Memory Tiers\n\n### 🔥 Hot Tier — Current Session Context\n- **Size target:** keep small (~2–4KB typical)\n- **Load policy:** Always loaded. Every spawn includes hot memory by default.\n- **Contents:** Current task description, active decisions made this session, immediate blockers, last 3–5 actions taken, who you are talking to right now.\n- **Lifetime:** Current session only. Discarded after session ends (Scribe promotes relevant parts to Cold).\n- **Purpose:** Provide immediate task context without any latency or load decision.\n\n### ❄️ Cold Tier — Summarized Cross-Session History\n- **Size target:** larger summary, not full transcript (~8–12KB typical)\n- **Load policy:** Load on demand. Include only when the task explicitly needs history.\n- **Contents:** Summarized past sessions (compressed by Scribe), cross-session decisions, recurring patterns, unresolved issues from prior work.\n- **Lifetime:** Rolling window (default proposal: 30 days). Eligible entries are then promoted to Wiki.\n- **Purpose:** Answer \"what have we tried before?\" and \"what was decided?\" without replaying full transcripts.\n- **How to include:** Pass `--include-cold` in spawn template or add `## Cold Memory` section.\n\n### 📚 Wiki Tier — Durable Structured Knowledge\n- **Size target:** variable, structured reference docs\n- **Load policy:** Async write, selective read. Load only when task requires domain knowledge.\n- **Contents:** Architecture decisions (ADRs), agent charters, routing rules, stable conventions, external API contracts, known platform constraints.\n- **Lifetime:** Permanent until explicitly deprecated.\n- **Purpose:** Authoritative reference. Not history — structured facts.\n- **How to include:** Pass `--include-wiki` or reference specific wiki doc paths in spawn template.\n\n---\n\n## When to Load Each Tier\n\n| Situation | Hot | Cold | Wiki |\n|-----------|-----|------|------|\n| New task, no prior context needed | ✅ | ❌ | ❌ |\n| Resuming interrupted work | ✅ | ✅ | ❌ |\n| Debugging a recurring issue | ✅ | ✅ | ❌ |\n| Implementing against a spec\u002FADR | ✅ | ❌ | ✅ |\n| Onboarding to unfamiliar subsystem | ✅ | ❌ | ✅ |\n| Post-incident review | ✅ | ✅ | ✅ |\n\n---\n\n## Spawn Template Pattern\n\nThe default spawn prompt should include **Hot tier only**:\n\n```\n## Memory Context\n\n### Hot (current session)\n{hot_context}\n```\n\nAdd `--include-cold` when the task needs history:\n```\n## Memory Context\n\n### Hot (current session)\n{hot_context}\n\n### Cold (summarized history — load on demand)\nSee: .squad\u002Fmemory\u002Fcold\u002F{agent-name}.md\n```\n\nAdd `--include-wiki` when the task needs domain knowledge:\n```\n## Memory Context\n\n### Hot (current session)\n{hot_context}\n\n### Wiki (durable reference)\nSee: .squad\u002Fmemory\u002Fwiki\u002F{topic}.md\n```\n\n---\n\n## Integration with Scribe Agent (design — not yet implemented)\n\nScribe is the proposed memory coordinator for this system. Once the runtime lands, Scribe will:\n\n1. **End of session:** Compress Hot → Cold summary (target: ~10% of session verbosity)\n2. **Aged cold entries:** Promote Cold → Wiki for decisions\u002Ffacts that aged into stable knowledge\n3. **On-demand wiki writes:** Any agent can request Scribe to write a wiki entry mid-session\n\nUntil then, see the Scribe charter for current behavior: `.squad\u002Fagents\u002Fscribe\u002Fcharter.md`\n\n---\n\n## Implementation Checklist (tracked in #1264)\n\n- [ ] Scribe writes Hot context file at session start (`.squad\u002Fmemory\u002Fhot\u002F{agent}.md`)\n- [ ] Scribe compresses and writes Cold summary at session end\n- [ ] Spawn templates default to Hot-only\n- [ ] Coordinators add `--include-cold` \u002F `--include-wiki` flags as needed\n- [ ] Wiki entries stored in `.squad\u002Fmemory\u002Fwiki\u002F`\n- [ ] Cold entries stored in `.squad\u002Fmemory\u002Fcold\u002F` with rolling TTL\n\n---\n\n## References\n\n- Tracking issue: [bradygaster\u002Fsquad#1264](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F1264) — installation gap + runtime status\n- Original design spike: [bradygaster\u002Fsquad#686](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F686) — tiered memory implementation plan\n- Related: [bradygaster\u002Fsquad#600](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F600) — context payload growth\n\n---\n\n## Spawn Template\n\n# Spawn Template: Agent with Tiered Memory\n\nUse this template when spawning any Squad agent. By default it loads **Hot tier only**. Add optional sections as needed.\n\n---\n\n## Task\n\n{task_description}\n\n## WHY\n\n{why_this_matters}\n\n## Success Criteria\n\n- [ ] {criterion_1}\n- [ ] {criterion_2}\n\n---\n\n## Memory Context\n\n### 🔥 Hot (always included)\n\n> Paste current session context here (~2–4KB target):\n\n```\nCurrent task: {task_description}\nActive decisions: {decisions_this_session}\nLast actions: {last_3_to_5_actions}\nBlockers: {current_blockers_or_none}\nTalking to: {current_interlocutor}\n```\n\n---\n\n### ❄️ Cold (include when task needs history — add `--include-cold`)\n\n> Load on demand. Do not inline unless specifically needed.\n\nSummarized cross-session history is at:\n`.squad\u002Fmemory\u002Fcold\u002F{agent-name}.md`\n\nInclude when:\n- Resuming interrupted work\n- Debugging a recurring issue\n- \"What have we tried before?\"\n\n**To load cold memory, add this section and fetch the file before spawning:**\n\n```\n## Cold Memory Summary\n{contents_of_.squad\u002Fmemory\u002Fcold\u002F{agent-name}.md}\n```\n\n---\n\n### 📚 Wiki (include when task needs domain knowledge — add `--include-wiki`)\n\n> Load on demand. Reference specific wiki docs by path.\n\nWiki entries are at: `.squad\u002Fmemory\u002Fwiki\u002F`\n\nInclude when:\n- Implementing against an ADR or spec\n- Onboarding to unfamiliar subsystem\n- Need stable conventions or API contracts\n\n**To load wiki, add this section and reference the specific doc:**\n\n```\n## Wiki Reference\n{contents_of_.squad\u002Fmemory\u002Fwiki\u002F{topic}.md}\n```\n\n---\n\n## Escalation\n\nIf blocked or uncertain:\n- Architecture questions → @picard\n- Security concerns → @worf\n- Infrastructure\u002Fdeployment → @belanna\n- Memory\u002Fhistory questions → @scribe\n\n---\n\n## Notes\n\n- Hot tier is always included; keep it focused\n- Cold adds a summary; only include when history is relevant\n- Wiki adds variable size; only include specific relevant docs\n- Runtime backing is tracked in [bradygaster\u002Fsquad#1264](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F1264) — until those changes land, this skill is design-only and agents continue to load full history.md + decisions.md on every spawn\n\n","# Skill: Tiered Agent Memory\n\n> **Status (v0.10.0):** This skill describes a **design proposal**, not a shipped runtime. Skill files install via `squad init`\u002F`upgrade`, but the underlying tier scaffolding (`.squad\u002Fmemory\u002Fhot\u002F`, `cold\u002F`, `wiki\u002F`), Scribe promotion logic, and spawn-template tier-aware reads are tracked in [bradygaster\u002Fsquad#1264](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F1264). Until those land, agents continue to load full `history.md` + `decisions.md` on every spawn.\n\n## Overview\n\nSquad agents today load their full context history on every spawn, which grows unboundedly across sessions. The Tiered Agent Memory model proposes a three-tier separation so agents only load the bytes that are actually relevant to the current task, with older context kept available on demand.\n\n---\n\n## Memory Tiers\n\n### 🔥 Hot Tier — Current Session Context\n- **Size target:** keep small (~2–4KB typical)\n- **Load policy:** Always loaded. Every spawn includes hot memory by default.\n- **Contents:** Current task description, active decisions made this session, immediate blockers, last 3–5 actions taken, who you are talking to right now.\n- **Lifetime:** Current session only. Discarded after session ends (Scribe promotes relevant parts to Cold).\n- **Purpose:** Provide immediate task context without any latency or load decision.\n\n### ❄️ Cold Tier — Summarized Cross-Session History\n- **Size target:** larger summary, not full transcript (~8–12KB typical)\n- **Load policy:** Load on demand. Include only when the task explicitly needs history.\n- **Contents:** Summarized past sessions (compressed by Scribe), cross-session decisions, recurring patterns, unresolved issues from prior work.\n- **Lifetime:** Rolling window (default proposal: 30 days). Eligible entries are then promoted to Wiki.\n- **Purpose:** Answer \"what have we tried before?\" and \"what was decided?\" without replaying full transcripts.\n- **How to include:** Pass `--include-cold` in spawn template or add `## Cold Memory` section.\n\n### 📚 Wiki Tier — Durable Structured Knowledge\n- **Size target:** variable, structured reference docs\n- **Load policy:** Async write, selective read. Load only when task requires domain knowledge.\n- **Contents:** Architecture decisions (ADRs), agent charters, routing rules, stable conventions, external API contracts, known platform constraints.\n- **Lifetime:** Permanent until explicitly deprecated.\n- **Purpose:** Authoritative reference. Not history — structured facts.\n- **How to include:** Pass `--include-wiki` or reference specific wiki doc paths in spawn template.\n\n---\n\n## When to Load Each Tier\n\n| Situation | Hot | Cold | Wiki |\n|-----------|-----|------|------|\n| New task, no prior context needed | ✅ | ❌ | ❌ |\n| Resuming interrupted work | ✅ | ✅ | ❌ |\n| Debugging a recurring issue | ✅ | ✅ | ❌ |\n| Implementing against a spec\u002FADR | ✅ | ❌ | ✅ |\n| Onboarding to unfamiliar subsystem | ✅ | ❌ | ✅ |\n| Post-incident review | ✅ | ✅ | ✅ |\n\n---\n\n## Spawn Template Pattern\n\nThe default spawn prompt should include **Hot tier only**:\n\n```\n## Memory Context\n\n### Hot (current session)\n{hot_context}\n```\n\nAdd `--include-cold` when the task needs history:\n```\n## Memory Context\n\n### Hot (current session)\n{hot_context}\n\n### Cold (summarized history — load on demand)\nSee: .squad\u002Fmemory\u002Fcold\u002F{agent-name}.md\n```\n\nAdd `--include-wiki` when the task needs domain knowledge:\n```\n## Memory Context\n\n### Hot (current session)\n{hot_context}\n\n### Wiki (durable reference)\nSee: .squad\u002Fmemory\u002Fwiki\u002F{topic}.md\n```\n\n---\n\n## Integration with Scribe Agent (design — not yet implemented)\n\nScribe is the proposed memory coordinator for this system. Once the runtime lands, Scribe will:\n\n1. **End of session:** Compress Hot → Cold summary (target: ~10% of session verbosity)\n2. **Aged cold entries:** Promote Cold → Wiki for decisions\u002Ffacts that aged into stable knowledge\n3. **On-demand wiki writes:** Any agent can request Scribe to write a wiki entry mid-session\n\nUntil then, see the Scribe charter for current behavior: `.squad\u002Fagents\u002Fscribe\u002Fcharter.md`\n\n---\n\n## Implementation Checklist (tracked in #1264)\n\n- [ ] Scribe writes Hot context file at session start (`.squad\u002Fmemory\u002Fhot\u002F{agent}.md`)\n- [ ] Scribe compresses and writes Cold summary at session end\n- [ ] Spawn templates default to Hot-only\n- [ ] Coordinators add `--include-cold` \u002F `--include-wiki` flags as needed\n- [ ] Wiki entries stored in `.squad\u002Fmemory\u002Fwiki\u002F`\n- [ ] Cold entries stored in `.squad\u002Fmemory\u002Fcold\u002F` with rolling TTL\n\n---\n\n## References\n\n- Tracking issue: [bradygaster\u002Fsquad#1264](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F1264) — installation gap + runtime status\n- Original design spike: [bradygaster\u002Fsquad#686](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F686) — tiered memory implementation plan\n- Related: [bradygaster\u002Fsquad#600](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F600) — context payload growth\n\n---\n\n## Spawn Template\n\n# Spawn Template: Agent with Tiered Memory\n\nUse this template when spawning any Squad agent. By default it loads **Hot tier only**. Add optional sections as needed.\n\n---\n\n## Task\n\n{task_description}\n\n## WHY\n\n{why_this_matters}\n\n## Success Criteria\n\n- [ ] {criterion_1}\n- [ ] {criterion_2}\n\n---\n\n## Memory Context\n\n### 🔥 Hot (always included)\n\n> Paste current session context here (~2–4KB target):\n\n```\nCurrent task: {task_description}\nActive decisions: {decisions_this_session}\nLast actions: {last_3_to_5_actions}\nBlockers: {current_blockers_or_none}\nTalking to: {current_interlocutor}\n```\n\n---\n\n### ❄️ Cold (include when task needs history — add `--include-cold`)\n\n> Load on demand. Do not inline unless specifically needed.\n\nSummarized cross-session history is at:\n`.squad\u002Fmemory\u002Fcold\u002F{agent-name}.md`\n\nInclude when:\n- Resuming interrupted work\n- Debugging a recurring issue\n- \"What have we tried before?\"\n\n**To load cold memory, add this section and fetch the file before spawning:**\n\n```\n## Cold Memory Summary\n{contents_of_.squad\u002Fmemory\u002Fcold\u002F{agent-name}.md}\n```\n\n---\n\n### 📚 Wiki (include when task needs domain knowledge — add `--include-wiki`)\n\n> Load on demand. Reference specific wiki docs by path.\n\nWiki entries are at: `.squad\u002Fmemory\u002Fwiki\u002F`\n\nInclude when:\n- Implementing against an ADR or spec\n- Onboarding to unfamiliar subsystem\n- Need stable conventions or API contracts\n\n**To load wiki, add this section and reference the specific doc:**\n\n```\n## Wiki Reference\n{contents_of_.squad\u002Fmemory\u002Fwiki\u002F{topic}.md}\n```\n\n---\n\n## Escalation\n\nIf blocked or uncertain:\n- Architecture questions → @picard\n- Security concerns → @worf\n- Infrastructure\u002Fdeployment → @belanna\n- Memory\u002Fhistory questions → @scribe\n\n---\n\n## Notes\n\n- Hot tier is always included; keep it focused\n- Cold adds a summary; only include when history is relevant\n- Wiki adds variable size; only include specific relevant docs\n- Runtime backing is tracked in [bradygaster\u002Fsquad#1264](https:\u002F\u002Fgithub.com\u002Fbradygaster\u002Fsquad\u002Fissues\u002F1264) — until those changes land, this skill is design-only and agents continue to load full history.md + decisions.md on every spawn\n\n",{"name":5,"domain":24,"source":25,"confidence":26,"description":7},"memory-management, performance","design proposal","design (runtime not yet implemented)","main","176da577bfd98859f793bdd1312690c6c3940c67",".squad\u002Ftemplates\u002Fskills\u002Ftiered-memory","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI","https:\u002F\u002Fgithub.com\u002Falonf","http:\u002F\u002Falonfliess.me","CTO & Founder of Zionet.\r\nMicrosoft Regional Director and Foundry MVP.\r\n","2026-08-28 05:21:35",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add alonf\u002FKeyContextAI --skill tiered-memory",{"tool":41,"command":42},"bunx","bunx skills add alonf\u002FKeyContextAI --skill tiered-memory",{"tool":44,"command":45},"pnpm","pnpm dlx skills add alonf\u002FKeyContextAI --skill tiered-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7AVHRWWXA0BQ5PXNA8FG30W","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7AVHABPRYXYM3GWJY1RW92A","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7AVH18JDSA55Z7KK2GH6X49","test-discipline","Update tests when changing APIs — no exceptions","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftest-discipline\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7AVGVGWYD7NBNXAV4PAZJ92","squad","Squad's command catalog and interactive menu. Invoke via \u002Fsquad (slash command) or natural language (\"squad commands\", \"what can squad do\", \"show me squad options\"). Presents categorized operations (Install & Upgrade, Team Management, Issues & PRs, Plugins & Skills, Model & Cost, Sessions & State) as an interactive picker. Routes to the right squad CLI command or the Squad coordinator agent.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7AVGPSFT1WHW3PK35DHS5XK","squad-version-check","Internals of how @bradygaster\u002Fsquad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad-version-check\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7AVGHW8X709TBZ9YZAV7GE9","squad-help","How to actually use Squad — Squad is a custom Copilot agent (invoked via the task tool with agent_type='Squad'), not a skill. This file explains the right invocation paths for setting up a team, listing squad commands, and initializing Squad in a new project.","https:\u002F\u002Fgithub.com\u002Falonf\u002FKeyContextAI\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fsquad-help\u002FSKILL.md",[],[]]