com um clique
agent-orchestrator-ts
agent-orchestrator-ts contém 12 skills coletadas de jleechanorg, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Multi-PR triage and parallel work dispatcher. Prevents single-PR tunnel vision by enforcing a survey-before-deep-dive protocol.
Canonical 6-green PR merge criteria, PR status check pattern, PR freeze discipline, and admin merge protocol
Watch one or more AO worker tmux sessions, classify their state (WORKING/IDLE/QUEUED/DEAD/COMPLETED), auto-remediate known failures (trust TUI), and push-notify on STALLED-COMPLETED / DEAD sessions. Reuses ao-session-monitor state detection. Use /babysit to start a monitoring loop on a specific worker, all active workers, or workers matching a PR/branch.
Codex-native AO evolve loop. Run a deterministic local observe/measure cycle, then optionally delegate targeted fixes via /claw using the canonical evolve-loop skill.
Use after every `git push` on a PR — enumerates ALL current gate failures, fixes ALL in one local pass, and pushes once. The fix-all-before-push invariant. Pairs with the CLAUDE.md PR driver loop contract and babysit DRIVER mode.
Evidence standards for testing and verification, including evidence classes, mock/real boundaries, and proof bundle requirements.
Classifies GitHub issues/PRs into PR-type categories and recommends autor techniques. Used by packages/core/src/decomposer.ts.
Use this skill when working in repositories managed by Agent Orchestrator or when the user asks how to use `ao` properly. Covers the default AO workflow: bootstrap with `ao start`, dispatch work with `ao spawn`, inspect progress with `ao status` or `ao session ls`, steer sessions with `ao send`, and recover or clean up sessions safely.
TDD-driven evidence workflow for generating authoritative failure/fix proof in PRs.
Define and run skeptic exit criteria for non-trivial tasks — independent verification agent with inverted incentive to find gaps
How to record asciinema/tmux evidence videos that prove work was done correctly
How to record captioned browser/UI evidence GIFs that prove visual behavior and user flows ran correctly