model-selection
github/squad/plugins/squad/skills/model-selection/SKILL.md
Determines which LLM model to use for each agent spawn
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/plugins/squad/skills/model-selection/SKILL.md
Determines which LLM model to use for each agent spawn
github/squad/plugins/squad/skills/nap/SKILL.md
Context hygiene — compress, prune, archive .squad/ state
github/squad/plugins/squad/skills/notification-routing/SKILL.md
Route agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding
github/squad/plugins/squad/skills/project-conventions/SKILL.md
Core conventions and patterns for this codebase
github/squad/plugins/squad/skills/pr-review-response/SKILL.md
Teaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable
github/squad/plugins/squad/skills/pr-screenshots/SKILL.md
Capture Playwright screenshots and embed them in GitHub PR descriptions
github/squad/plugins/squad/skills/ralph-two-pass-scan/SKILL.md
Cuts GitHub API calls by separating lightweight list scanning from full hydration
github/squad/plugins/squad/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.
Often used withpoteto-helpsetup-pstackmake-bot-ui
github/squad/plugins/squad/skills/release-process/SKILL.md
Prepare, publish, recover, and verify Squad insider, preview, and stable releases
github/squad/plugins/squad/skills/reskill/SKILL.md
Extract durable operating knowledge before slimming or replacing team charters
github/squad/plugins/squad/skills/retro-enforcement/SKILL.md
Keep retrospectives on schedule and track their action items as GitHub Issues, not markdown checklists
github/squad/plugins/squad/skills/reviewer-protocol/SKILL.md
Reviewer rejection workflow and strict lockout semantics
github/squad/plugins/squad/skills/secret-handling/SKILL.md
Never read .env files or write secrets to .squad/ committed files
Often used withsquad-commands
github/squad/plugins/squad/skills/session-recovery/SKILL.md
Find and resume interrupted Copilot CLI sessions using session_store queries
Often used withsquad-commands
github/squad/plugins/squad/skills/squad-commands/SKILL.md
Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.
github/squad/plugins/squad/skills/squad-conventions/SKILL.md
Core conventions and patterns used in the Squad codebase
Often used withsquad-commands
github/squad/plugins/squad/skills/squad-coordinator-ceremonies/SKILL.md
Squad coordinator only: running team ceremonies (design review, retro, manual ceremonies). Load before spawning work when ceremonies.md defines a before or after trigger, or when a ceremony is requested.
github/squad/plugins/squad/skills/squad-coordinator-init-mode/SKILL.md
Squad coordinator only: Init Mode, proposing and casting a new team. Load when team.md is missing or has an empty roster, or when asked to set up or cast a team.
github/squad/plugins/squad/skills/squad-coordinator-issues-mode/SKILL.md
Squad coordinator only: GitHub Issues mode (connecting a repo, listing, routing and working issues with gh). Load when the user mentions issues, connecting a repo, or squad labels.
github/squad/plugins/squad/skills/squad-coordinator-prd-mode/SKILL.md
Squad coordinator only: PRD mode (decomposing a product requirements document into owned work items). Load when the user provides or points to a PRD or spec to break down.
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.