[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X0RGZ0932QC1W4VY331YCF":3,"skill-same:01M6X0RGZ0932QC1W4VY331YCF":58},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M6X0RGZ0932QC1W4VY331YCF","model-selection",null,"Per-agent model selection with 4-layer hierarchy and fallback chains","github\u002Fsquad","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6X0MZ6B0WYMMDPK3Q61KER6",3391,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002F.copilot\u002Fskills\u002Fmodel-selection\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"model selection","model","selection","orchestration","fallback","with","high","layer","hierarchy","2026-11-10 10:12:30",false,"---\nname: \"model-selection\"\ndescription: \"Per-agent model selection with 4-layer hierarchy and fallback chains\"\ndomain: \"orchestration\"\nconfidence: \"high\"\nsource: \"extracted\"\n---\n\n## Context\n\nBefore spawning an agent, the coordinator determines which model to use. This skill codifies the 4-layer hierarchy, role-to-model mappings, task complexity adjustments, and fallback chains. Applies to all agent spawns in Team Mode.\n\n## Patterns\n\n### 4-Layer Hierarchy\n\nCheck these layers in order — first match wins:\n\n**Layer 1 — User Override:** Did the user specify a model? (\"use opus\", \"save costs\", \"use gpt-5.3-codex for this\"). If yes, use that model. Session-wide directives (\"always use haiku\") persist until contradicted.\n\n**Layer 2 — Charter Preference:** Does the agent's charter have a `## Model` section with `Preferred` set to a specific model (not `auto`)? If yes, use that model.\n\n**Layer 3 — Task-Aware Auto-Selection:** Use the governing principle: **cost first, unless code is being written.** Match the agent's task to determine output type, then select accordingly:\n\n| Task Output | Model | Tier | Rule |\n|-------------|-------|------|------|\n| Writing code (implementation, refactoring, test code, bug fixes) | `gpt-5.6-terra` | Standard | Quality and accuracy matter for code. Use standard tier. |\n| Writing prompts or agent designs (structured text that functions like code) | `gpt-5.6-terra` | Standard | Prompts are executable — treat like code. |\n| NOT writing code (docs, planning, triage, logs, changelogs, mechanical ops) | `gpt-5.6-luna` | Fast | Cost first. Luna handles non-code tasks by default. |\n| Visual\u002Fdesign work requiring image analysis | `gpt-5.6-sol` | Premium | Vision capability required. Overrides cost rule. |\n\n**Role-to-model mapping** (applying cost-first principle):\n\n| Role | Default Model | Why | Override When |\n|------|--------------|-----|---------------|\n| Core Dev \u002F Backend \u002F Frontend | `gpt-5.6-terra` | Writes code — quality first | Heavy code gen → `gpt-5.3-codex` |\n| Tester \u002F QA | `gpt-5.6-terra` | Writes test code — quality first | Simple test scaffolding → `claude-haiku-4.5` |\n| Lead \u002F Architect | auto (per-task) | Mixed: code review needs quality, planning needs cost | Architecture proposals → premium; triage\u002Fplanning → luna |\n| Prompt Engineer | auto (per-task) | Mixed: prompt design is like code, research is not | Prompt architecture → `gpt-5.6-terra`; research\u002Fanalysis → haiku |\n| Copilot SDK Expert | `gpt-5.6-terra` | Technical analysis that often touches code | Pure research → `claude-haiku-4.5` |\n| Designer \u002F Visual | `gpt-5.6-sol` | Vision-capable model required | — (never downgrade — vision is non-negotiable) |\n| DevRel \u002F Writer | `gpt-5.6-luna` | Docs and writing — not code | — |\n| Scribe \u002F Logger | `gpt-5.6-luna` | Mechanical file ops — cheapest possible | — (never bump Scribe) |\n| Git \u002F Release | `gpt-5.6-luna` | Mechanical ops — changelogs, tags, version bumps | — (never bump mechanical ops) |\n\n**Task complexity adjustments** (apply at most ONE — no cascading):\n- **Bump UP to premium:** architecture proposals, reviewer gates, security audits, multi-agent coordination (output feeds 3+ agents)\n- **Bump DOWN to fast\u002Fcheap:** typo fixes, renames, boilerplate, scaffolding, changelogs, version bumps\n- **Switch to code specialist (`gpt-5.3-codex`):** large multi-file refactors, complex implementation from spec, heavy code generation (500+ lines)\n- **Switch to analytical diversity (`gemini-3.1-pro`):** code reviews where a second perspective helps, security reviews, architecture reviews after a rejection\n\n**Layer 4 — Default:** If nothing else matched, use `gpt-5.6-luna`. Cost wins when in doubt, unless code is being produced.\n\n### Fallback Chains\n\nIf a spawn fails because the selected model is unavailable (plan restriction, org policy, rate limit, deprecation, or any other reason), silently retry with the next model in the chain. Do NOT tell the user about fallback attempts. Maximum 3 retries before using the platform default fallback.\n\n```\nPremium:  gpt-5.6-sol → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → claude-opus-4.6 → claude-sonnet-4.6 → (omit model param)\nStandard: gpt-5.6-terra → claude-sonnet-5 → claude-sonnet-4.6 → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → claude-sonnet-4.5 → gemini-3.1-pro → (omit model param)\nFast:     gpt-5.6-luna → claude-haiku-4.5 → gpt-5.4-mini → gpt-5-mini → (omit model param)\n```\n\n`(omit model param)` = call the `task` tool WITHOUT the `model` parameter. The platform uses its built-in default. This is the platform default fallback — it lets the platform choose the model.\n\n**Fallback rules:**\n- If the user specified a provider (\"use Claude\"), fall back within that provider only before using the platform default fallback\n- Never fall back UP in tier — a fast\u002Fcheap task should not land on a premium model\n- Log fallbacks to the orchestration log for debugging, but never surface to the user unless asked\n\n### Passing the Model to Spawns\n\nPass the resolved model as the `model` parameter on every `task` tool call:\n\n```\nagent_type: \"general-purpose\"\nmodel: \"{resolved_model}\"\nmode: \"background\"\ndescription: \"{emoji} {Name}: {brief task summary}\"\nprompt: |\n  ...\n```\n\nOnly set `model` when it differs from the platform default (`claude-sonnet-4.6`). If the resolved model IS `claude-sonnet-4.6`, you MAY omit the `model` parameter — the platform uses it as default.\n\nIf you've exhausted the fallback chain and reached the platform default fallback, omit the `model` parameter entirely.\n\n### Spawn Output Format\n\nWhen spawning, include the model in your acknowledgment:\n\n```\n? Agent Alpha (claude-sonnet-5) — refactoring auth module\n? Agent Beta (gpt-5.6-sol · vision) — designing color system\n? Scribe (gpt-5.6-luna · fast) — logging session\n⚡ Agent Gamma (gpt-5.6-sol · bumped for architecture) — reviewing proposal\n? Agent Delta (gpt-5.6-luna · fast) — updating docs\n```\n\nInclude tier annotation only when the model was bumped or a specialist was chosen. Default-tier spawns just show the model name.\n\n### Valid Models\n\n**Premium:** `gpt-5.6-sol`, `claude-opus-5`, `claude-opus-4.8`, `claude-opus-4.7`, `claude-opus-4.6`\n**Standard:** `gpt-5.6-terra`, `claude-sonnet-5`, `claude-sonnet-4.6`, `claude-sonnet-4.5`, `gpt-5.5`, `gpt-5.4`, `gpt-5.3-codex`, `gemini-3.1-pro`\n**Fast\u002FCheap:** `gpt-5.6-luna`, `claude-haiku-4.5`, `gpt-5.4-mini`, `gpt-5-mini`\n\n## Examples\n\n**Example 1: Backend dev writing API endpoints**\n- Role: Backend Dev\n- Task: \"implement REST endpoints for user management\"\n- Layer 3 decision: writing code → `gpt-5.6-terra` (standard tier)\n- Spawn: `? Agent Alpha (gpt-5.6-terra) — implementing user API endpoints`\n\n**Example 2: User override**\n- User says: \"use haiku for everything this session\"\n- Layer 1 overrides all other layers\n- All spawns use `claude-haiku-4.5` regardless of role or task\n\n**Example 3: Complex refactor**\n- Role: Backend Dev\n- Task: \"refactor 15 auth-related files to use new token system\"\n- Layer 3 base: `gpt-5.6-terra`\n- Task complexity: heavy multi-file refactor → switch to `gpt-5.3-codex`\n- Spawn: `? Agent Alpha (gpt-5.3-codex · code specialist) — refactoring auth to new token system`\n\n**Example 4: Scribe logging**\n- Role: Scribe\n- Task: \"log session to decisions.md\"\n- Layer 3: NOT writing code → `gpt-5.6-luna`\n- Role mapping: Scribe always luna, never bump\n- Spawn: `? Scribe (gpt-5.6-luna · fast) — logging session`\n\n## Anti-Patterns\n\n- ❌ Falling back UP in tier (fast task landing on premium model)\n- ❌ Telling the user about fallback attempts (\"Opus failed, trying Sonnet\")\n- ❌ Bumping Scribe or mechanical ops agents to higher tiers\n- ❌ Using premium models for documentation or planning tasks\n- ❌ Applying multiple complexity adjustments (cascading bumps)\n- ❌ Forgetting to include model in spawn acknowledgment\n- ❌ Downgrading vision-required tasks from the premium visual model\n","## Context\n\nBefore spawning an agent, the coordinator determines which model to use. This skill codifies the 4-layer hierarchy, role-to-model mappings, task complexity adjustments, and fallback chains. Applies to all agent spawns in Team Mode.\n\n## Patterns\n\n### 4-Layer Hierarchy\n\nCheck these layers in order — first match wins:\n\n**Layer 1 — User Override:** Did the user specify a model? (\"use opus\", \"save costs\", \"use gpt-5.3-codex for this\"). If yes, use that model. Session-wide directives (\"always use haiku\") persist until contradicted.\n\n**Layer 2 — Charter Preference:** Does the agent's charter have a `## Model` section with `Preferred` set to a specific model (not `auto`)? If yes, use that model.\n\n**Layer 3 — Task-Aware Auto-Selection:** Use the governing principle: **cost first, unless code is being written.** Match the agent's task to determine output type, then select accordingly:\n\n| Task Output | Model | Tier | Rule |\n|-------------|-------|------|------|\n| Writing code (implementation, refactoring, test code, bug fixes) | `gpt-5.6-terra` | Standard | Quality and accuracy matter for code. Use standard tier. |\n| Writing prompts or agent designs (structured text that functions like code) | `gpt-5.6-terra` | Standard | Prompts are executable — treat like code. |\n| NOT writing code (docs, planning, triage, logs, changelogs, mechanical ops) | `gpt-5.6-luna` | Fast | Cost first. Luna handles non-code tasks by default. |\n| Visual\u002Fdesign work requiring image analysis | `gpt-5.6-sol` | Premium | Vision capability required. Overrides cost rule. |\n\n**Role-to-model mapping** (applying cost-first principle):\n\n| Role | Default Model | Why | Override When |\n|------|--------------|-----|---------------|\n| Core Dev \u002F Backend \u002F Frontend | `gpt-5.6-terra` | Writes code — quality first | Heavy code gen → `gpt-5.3-codex` |\n| Tester \u002F QA | `gpt-5.6-terra` | Writes test code — quality first | Simple test scaffolding → `claude-haiku-4.5` |\n| Lead \u002F Architect | auto (per-task) | Mixed: code review needs quality, planning needs cost | Architecture proposals → premium; triage\u002Fplanning → luna |\n| Prompt Engineer | auto (per-task) | Mixed: prompt design is like code, research is not | Prompt architecture → `gpt-5.6-terra`; research\u002Fanalysis → haiku |\n| Copilot SDK Expert | `gpt-5.6-terra` | Technical analysis that often touches code | Pure research → `claude-haiku-4.5` |\n| Designer \u002F Visual | `gpt-5.6-sol` | Vision-capable model required | — (never downgrade — vision is non-negotiable) |\n| DevRel \u002F Writer | `gpt-5.6-luna` | Docs and writing — not code | — |\n| Scribe \u002F Logger | `gpt-5.6-luna` | Mechanical file ops — cheapest possible | — (never bump Scribe) |\n| Git \u002F Release | `gpt-5.6-luna` | Mechanical ops — changelogs, tags, version bumps | — (never bump mechanical ops) |\n\n**Task complexity adjustments** (apply at most ONE — no cascading):\n- **Bump UP to premium:** architecture proposals, reviewer gates, security audits, multi-agent coordination (output feeds 3+ agents)\n- **Bump DOWN to fast\u002Fcheap:** typo fixes, renames, boilerplate, scaffolding, changelogs, version bumps\n- **Switch to code specialist (`gpt-5.3-codex`):** large multi-file refactors, complex implementation from spec, heavy code generation (500+ lines)\n- **Switch to analytical diversity (`gemini-3.1-pro`):** code reviews where a second perspective helps, security reviews, architecture reviews after a rejection\n\n**Layer 4 — Default:** If nothing else matched, use `gpt-5.6-luna`. Cost wins when in doubt, unless code is being produced.\n\n### Fallback Chains\n\nIf a spawn fails because the selected model is unavailable (plan restriction, org policy, rate limit, deprecation, or any other reason), silently retry with the next model in the chain. Do NOT tell the user about fallback attempts. Maximum 3 retries before using the platform default fallback.\n\n```\nPremium:  gpt-5.6-sol → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → claude-opus-4.6 → claude-sonnet-4.6 → (omit model param)\nStandard: gpt-5.6-terra → claude-sonnet-5 → claude-sonnet-4.6 → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → claude-sonnet-4.5 → gemini-3.1-pro → (omit model param)\nFast:     gpt-5.6-luna → claude-haiku-4.5 → gpt-5.4-mini → gpt-5-mini → (omit model param)\n```\n\n`(omit model param)` = call the `task` tool WITHOUT the `model` parameter. The platform uses its built-in default. This is the platform default fallback — it lets the platform choose the model.\n\n**Fallback rules:**\n- If the user specified a provider (\"use Claude\"), fall back within that provider only before using the platform default fallback\n- Never fall back UP in tier — a fast\u002Fcheap task should not land on a premium model\n- Log fallbacks to the orchestration log for debugging, but never surface to the user unless asked\n\n### Passing the Model to Spawns\n\nPass the resolved model as the `model` parameter on every `task` tool call:\n\n```\nagent_type: \"general-purpose\"\nmodel: \"{resolved_model}\"\nmode: \"background\"\ndescription: \"{emoji} {Name}: {brief task summary}\"\nprompt: |\n  ...\n```\n\nOnly set `model` when it differs from the platform default (`claude-sonnet-4.6`). If the resolved model IS `claude-sonnet-4.6`, you MAY omit the `model` parameter — the platform uses it as default.\n\nIf you've exhausted the fallback chain and reached the platform default fallback, omit the `model` parameter entirely.\n\n### Spawn Output Format\n\nWhen spawning, include the model in your acknowledgment:\n\n```\n? Agent Alpha (claude-sonnet-5) — refactoring auth module\n? Agent Beta (gpt-5.6-sol · vision) — designing color system\n? Scribe (gpt-5.6-luna · fast) — logging session\n⚡ Agent Gamma (gpt-5.6-sol · bumped for architecture) — reviewing proposal\n? Agent Delta (gpt-5.6-luna · fast) — updating docs\n```\n\nInclude tier annotation only when the model was bumped or a specialist was chosen. Default-tier spawns just show the model name.\n\n### Valid Models\n\n**Premium:** `gpt-5.6-sol`, `claude-opus-5`, `claude-opus-4.8`, `claude-opus-4.7`, `claude-opus-4.6`\n**Standard:** `gpt-5.6-terra`, `claude-sonnet-5`, `claude-sonnet-4.6`, `claude-sonnet-4.5`, `gpt-5.5`, `gpt-5.4`, `gpt-5.3-codex`, `gemini-3.1-pro`\n**Fast\u002FCheap:** `gpt-5.6-luna`, `claude-haiku-4.5`, `gpt-5.4-mini`, `gpt-5-mini`\n\n## Examples\n\n**Example 1: Backend dev writing API endpoints**\n- Role: Backend Dev\n- Task: \"implement REST endpoints for user management\"\n- Layer 3 decision: writing code → `gpt-5.6-terra` (standard tier)\n- Spawn: `? Agent Alpha (gpt-5.6-terra) — implementing user API endpoints`\n\n**Example 2: User override**\n- User says: \"use haiku for everything this session\"\n- Layer 1 overrides all other layers\n- All spawns use `claude-haiku-4.5` regardless of role or task\n\n**Example 3: Complex refactor**\n- Role: Backend Dev\n- Task: \"refactor 15 auth-related files to use new token system\"\n- Layer 3 base: `gpt-5.6-terra`\n- Task complexity: heavy multi-file refactor → switch to `gpt-5.3-codex`\n- Spawn: `? Agent Alpha (gpt-5.3-codex · code specialist) — refactoring auth to new token system`\n\n**Example 4: Scribe logging**\n- Role: Scribe\n- Task: \"log session to decisions.md\"\n- Layer 3: NOT writing code → `gpt-5.6-luna`\n- Role mapping: Scribe always luna, never bump\n- Spawn: `? Scribe (gpt-5.6-luna · fast) — logging session`\n\n## Anti-Patterns\n\n- ❌ Falling back UP in tier (fast task landing on premium model)\n- ❌ Telling the user about fallback attempts (\"Opus failed, trying Sonnet\")\n- ❌ Bumping Scribe or mechanical ops agents to higher tiers\n- ❌ Using premium models for documentation or planning tasks\n- ❌ Applying multiple complexity adjustments (cascading bumps)\n- ❌ Forgetting to include model in spawn acknowledgment\n- ❌ Downgrading vision-required tasks from the premium visual model\n",{"name":5,"domain":22,"source":33,"confidence":25,"description":7},"extracted","dev","7b731ec97f35346bdc4fa87c3edaf16b808fc0ae",".copilot\u002Fskills\u002Fmodel-selection",520,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fsquad","https:\u002F\u002Fgithub.github.io\u002Fsquad\u002F","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-15 02:13:59",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add github\u002Fsquad --skill model-selection",{"tool":50,"command":51},"bunx","bunx skills add github\u002Fsquad --skill model-selection",{"tool":53,"command":54},"pnpm","pnpm dlx skills add github\u002Fsquad --skill model-selection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002F.copilot\u002Fskills\u002Fmodel-selection\u002FSKILL.md",true,[],[59,67,74,81,88,95],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":66},"01M76752CVNE7K6NWD59CRAYNJ","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002Fplugins\u002Fsquad\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":66},"01M767508W8A4G83NX1FKEW5VN","versioning-policy","SemVer rules for Squad's stable, preview, insider, and local package versions","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002Fplugins\u002Fsquad\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":66},"01M7674X5JJKNJ74B3SS8PGXG2","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002Fplugins\u002Fsquad\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":66},"01M7674V3S9H03A76H75M1KSAF","test-discipline","Design assertions that prove the actual contract and fail on realistic regressions","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002Fplugins\u002Fsquad\u002Fskills\u002Ftest-discipline\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":66},"01M7674QB8CA61RNDX2Z0NAK71","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\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002Fplugins\u002Fsquad\u002Fskills\u002Fsquad\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":66},"01M7674KTQ632N30HQB1TP7TXH","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\u002Fgithub\u002Fsquad\u002Fblob\u002Fdev\u002Fplugins\u002Fsquad\u002Fskills\u002Fsquad-version-check\u002FSKILL.md",[],[]]