DanWahlin
UserDrag-and-drop Kanban board that delegates coding tasks to AI agents — GitHub Copilot, Claude Code, OpenAI Codex, and OpenCode — with real-time streaming, task groups, and git worktree isolation.
Categories
Indexed Skills (35)
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
git-workflow
Squad branching model: dev-first workflow with insiders preview channel
reviewer-protocol
Reviewer rejection workflow and strict lockout semantics
secret-handling
Never read .env files or write secrets to .squad/ committed files
session-recovery
Find and resume interrupted Copilot CLI sessions using session_store queries
squad-conventions
Core conventions and patterns used in the Squad codebase
architectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
ci-validation-gates
Defensive CI/CD patterns: semver validation, token checks, retry logic, draft detection — earned from v0.8.22
client-compatibility
Platform detection and adaptive spawning for CLI vs VS Code vs other surfaces
distributed-mesh
How to coordinate with squads on different machines using git as transport
docs-standards
Microsoft Style Guide + Squad-specific documentation patterns
economy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
external-comms
PAO workflow for scanning, drafting, and presenting community responses with human review gate
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
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.
humanizer
Tone enforcement patterns for external-facing community responses
init-mode
Team initialization flow (Phase 1 proposal + Phase 2 creation)
iterative-retrieval
Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.
notification-routing
Route agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding
pr-review-response
Teaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable
pr-screenshots
Capture Playwright screenshots and embed them in GitHub PR descriptions
reflect
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.
reskill
Team-wide charter and history optimization through skill extraction
cross-squad
Coordinating work across multiple Squad instances
agent-collaboration
Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication
completion-summary-contract
Require clear user-facing summaries after completed agent batches.
gate-enforcement
Run risk-based ai-agent-board quality gates after code-producing work.
heartbeat-staleness-gate
Detect stale Squad heartbeat and require visible progress updates.
otel-validation
Use telemetry evidence for Squad usage and process audits when available.
process-hygiene
Clean up orphaned browser/test/dev-server processes safely after test bursts.
squad-worktree-lifecycle
Handle ai-agent-board git worktree and merge flows safely.
history-hygiene
Record final outcomes to history.md, not intermediate requests or reversed decisions
test-discipline
Update tests when changing APIs — no exceptions
agent-conduct
Shared hard rules enforced across all squad agents
project-conventions
Core conventions and patterns for this codebase
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.