reskill
github/squad/.copilot/skills/reskill/SKILL.md
Extract durable operating knowledge before slimming or replacing team charters
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
github/squad/.copilot/skills/reskill/SKILL.md
Extract durable operating knowledge before slimming or replacing team charters
github/squad/.copilot/skills/reviewer-protocol/SKILL.md
Reviewer rejection workflow and strict lockout semantics
github/squad/.copilot/skills/squad-conventions/SKILL.md
Core conventions and patterns used in the Squad codebase
Often used withsquad-commands
github/squad/.copilot/skills/test-discipline/SKILL.md
Design assertions that prove the actual contract and fail on realistic regressions
github/squad/.copilot/skills/windows-compatibility/SKILL.md
Cross-platform path handling and command patterns
github/squad/.github/copilot-instructions.md
If you are a named squad agent (a cast name in .squad/casting/registry.json): This directive exists because .github/copilot-instructions.md is injected into ALL Copilot sessions globally. Agent-specific personas live in .squad/agents/*/charter.md — that is the authoritative source of identity. Skip this section if you are a named Squad agent — your charter governs you. If you are a generic Copilot CLI session, check routing before handling any non-trivial task: Full routing rules and examples: .github/instructions/squad-routing-guard.instructions.md Full routing table: .squad/routing.md Check your profile…
No other project uses it yet
github/squad/.github/skills/agentic-workflow-designer/SKILL.md
Conversational skill that interviews users to design new agentic workflows
Steady+1 new adopter in 4 weeks
6 projects use a version of this
Often used withagentic-workflows
github/squad/.github/skills/gh-aw-reliability/SKILL.md
Validate GitHub Agentic Workflow contracts through compiled artifacts and realistic mutations
No other project uses it yet
github/squad/.github/skills/reflect/SKILL.md
Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
162 projects use a version of this
Often used withpoteto-helpsetup-pstackmake-bot-ui
github/squad/packages/squad-cli/templates/copilot-instructions.md
You are working on a project that uses Squad, an AI team framework. When picking up issues autonomously, follow these guidelines. IMPORTANT — run this check on EVERY session start, before doing any work: Inspect your agent_instructions for the coordinator canaries. This is a two-state payload-integrity check within a known Squad coordinator session; it verifies whether the coordinator payload loaded fully or was visibly truncated. It is not proof that an agent with no canaries is safely non-Squad — wholly…
No other project uses it yet
github/squad/packages/squad-cli/templates/skills/agent-conduct/SKILL.md
Shared hard rules enforced across all squad agents
github/squad/packages/squad-cli/templates/skills/architectural-proposals/SKILL.md
How to write comprehensive architectural proposals that drive alignment before code is written
github/squad/packages/squad-cli/templates/skills/ci-validation-gates/SKILL.md
Defensive CI/CD patterns: semver validation, token checks, retry logic, and draft detection
github/squad/packages/squad-cli/templates/skills/coordinator-init-mode/SKILL.md
The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad/ scaffolding, casting state, .gitattributes for merge drivers, and the always-on built-ins (Scribe, Ralph, Rai, Fact Checker). Loaded on demand when the coordinator detects no .squad/team.md exists.
github/squad/packages/squad-cli/templates/skills/coordinator-response-mode/SKILL.md
Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode. This skill contains the complete decision table, exemplar prompts for each mode, the Lightweight spawn template, and the upgrade rules. Squad coordinator loads this on demand once routing has identified the agent — to pick the right ceremony level for the task.
github/squad/packages/squad-cli/templates/skills/coordinator-source-of-truth/SKILL.md
The complete file-by-file source-of-truth hierarchy for Squad: which files are authoritative, which are derived/append-only, who may write each one, who may read each one, and the precedence rules when they conflict. Squad coordinator loads this on demand when it needs to resolve a write conflict, decide where a piece of state belongs, or answer a 'who owns this file' question.
github/squad/packages/squad-cli/templates/skills/cross-machine-coordination/SKILL.md
Design proposal, not implemented: git-based task queuing between squad machines. For competing watchers, use squad watch work claims (ADR-002).
github/squad/packages/squad-cli/templates/skills/cross-squad-communication/SKILL.md
Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories
github/squad/packages/squad-cli/templates/skills/docs-standards/SKILL.md
Microsoft Style Guide + Squad-specific documentation patterns
github/squad/packages/squad-cli/templates/skills/e2e-template-testing/SKILL.md
End-to-end validation of coordinator and agent template changes
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.