What problem does it solve? Prompt-level changes to coordinator and agent templates cannot be caught by unit tests because the prompts are interpreted by an LLM at runtime, so regressions only surface during real sessions. This Skill provides a repeatable end-to-end workflow for validating template changes against a locally built CLI before merging. ## Core Features & Use Cases - Local Build Validation: Builds and links the squad CLI from your feature branch, with fast-fail checks that stop the run on build, link, or version errors. - Disposable Test Repos: Creates isolated git repositories, runs squad init, and executes real Copilot CLI sessions with --allow-all-tools to verify template behavior. - PR Progress Reporting: Posts and updates a live tracking comment on the pull request with per-step status, durations, and progressive per-scenario verdicts. - Use Case: After editing squad.agent.md to add state-backend-aware spawn logic, run this Skill to build the CLI, init a test squad, run a coordinator session, and confirm state lands in the expected git-notes location with evidence posted to the PR. ## Quick Start Ask the agent to run end-to-end validation of your squad template changes on the current feature branch and post progress to the open PR.
