swigerb
34 verified skills
test-discipline
Update tests when changing APIs — no exceptions
development
{skill-name}
{what this skill teaches agents}
data-ai
agent-conduct
Shared hard rules enforced across all squad agents
data-ai
distributed-mesh
How to coordinate with squads on different machines using git as transport
tools
init-mode
Team initialization flow (Phase 1 proposal + Phase 2 creation)
tools
.copilot/skills/model-selection
# Model Selection > Determines which LLM model to use for each agent spawn. ## SCOPE ✅ THIS SKILL PRODUCES: - A resolved `model` parameter for every `task` tool call - Persistent model preferences in `.squad/config.json` - Spawn acknowledgments that include the resolved model ❌ THIS SKILL DOES NOT PRODUCE: - Code, tests, or documentation - Model performance benchmarks - Cost reports or billing artifacts ## Context Squad supports 18+ models across three tiers (premium, standard, fast). The
tools
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
tools
architectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
development
client-compatibility
Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces
tools
.copilot/skills/cli-wiring
# Skill: CLI Command Wiring **Bug class:** Commands implemented in `packages/squad-cli/src/cli/commands/` but never routed in `cli-entry.ts`. ## Checklist — Adding a New CLI Command 1. **Create command file** in `packages/squad-cli/src/cli/commands/<name>.ts` - Export a `run<Name>(cwd, options)` async function (or class with static methods for utility modules) 2. **Add routing block** in `packages/squad-cli/src/cli-entry.ts` inside `main()`: ```ts if (cmd === '<name>') { const
tools
cross-squad
Coordinating work across multiple Squad instances
tools
docs-standards
Microsoft Style Guide + Squad-specific documentation patterns
testing
.copilot/skills/echo-suppression
# Skill: WebSocket Echo Suppression for Realtime Voice AI ## Problem In a WebSocket middleware that bridges client audio ↔ AI model (e.g., OpenAI Realtime API), the AI's audio response leaks from the client's speakers back into the microphone, gets forwarded to the model, and is transcribed as phantom user input — creating an infinite self-conversation loop. ## Pattern Multi-layered suppression combining **client-side early muting** and **server-side audio gating** to eliminate the timing ga
tools
economy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
data-ai
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
data-ai
history-hygiene
Record final outcomes to history.md, not intermediate requests or reversed decisions
testing
humanizer
Tone enforcement patterns for external-facing community responses
testing
.copilot/skills/personal-squad
# Personal Squad — Skill Document ## What is a Personal Squad? A personal squad is a user-level collection of AI agents that travel with you across projects. Unlike project agents (defined in a project's `.squad/` directory), personal agents live in your global config directory and are automatically discovered when you start a squad session. ## Directory Structure ``` ~/.config/squad/personal-squad/ # Linux/macOS %APPDATA%/squad/personal-squad/ # Windows ├── agents/ │ ├── {agent-name
documentation
release-process
Step-by-step release checklist for Squad — prevents v0.8.22-style disasters
testing
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
tools
.copilot/skills/sonic-menu-parsing
# Skill: Sonic Menu Data Parsing ## When to Use Whenever you need to parse the production `sonic-menu-items.json` data — for ingestion, analysis, or any backend/tool code that works with menu items. ## Data Source `app/frontend/src/data/sonic-menu-items.json` (UTF-8 encoded, ~1.3MB) ## Structure ``` data['menus'][<menu-key>] = { 'products': dict (1334 items, keyed by product ID), 'categories': dict (43 items, keyed by category ID), 'productGroups': dict (503 items, keyed by group ID),
tools
squad-conventions
Core conventions and patterns used in the Squad codebase
development
windows-compatibility
Cross-platform path handling and command patterns
tools
project-conventions
Core conventions and patterns for this codebase
development
{skill-name}
{what this skill teaches agents}
data-ai
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
testing
ci-validation-gates
Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22
testing
external-comms
PAO workflow for scanning, drafting, and presenting community responses with human review gate
tools
git-workflow
Squad branching model: dev-first workflow with insiders preview channel
development
gpt-realtime-expert
Expert guidance for implementing OpenAI gpt-realtime-1.5, including WebRTC, WebSocket, and SIP configurations.
development
.copilot/skills/nap
# Skill: nap > Context hygiene — compress, prune, archive .squad/ state ## What It Does Reclaims context window budget by compressing agent histories, pruning old logs, archiving stale decisions, and cleaning orphaned inbox files. ## When To Use - Before heavy fan-out work (many agents will spawn) - When history.md files exceed 15KB - When .squad/ total size exceeds 1MB - After long-running sessions or sprints ## Invocation - CLI: `squad nap` / `squad nap --deep` / `squad nap --dry-run` -
tools
reskill
Team-wide charter and history optimization through skill extraction
tools
secret-handling
Never read .env files or write secrets to .squad/ committed files
documentation
github-multi-account
Detect and set up account-locked gh aliases for multi-account GitHub. The AI reads this skill, detects accounts, asks the user which is personal/work, and runs the setup automatically.
data-ai