AI Agent Workflow Collection

Process Codecov coverage reports on PRs and add missing tests for uncovered lines. Use when Codecov reports insufficient coverage, the user says "check codecov", "fix coverage", "add missing tests", or after CI passes and Codecov posts its report. Also invoked automatically by the SDLC workflow and resolve-pr-feedback skill.

Research and recommend libraries, technologies, or software solutions for specific use cases or project requirements.

The final, adversarial judge of the fx-ultra workflow. Runs LAST, after every other step is claimed done, and renders a verdict on whether the ENTIRE progression was executed with extreme rigor — with special, suspicious scrutiny on verification (ultra-verifier), visual polish (ultra-designer), and 100% test/integration coverage. It assumes steps were skipped or faked until proven otherwise, inspecting primary evidence (git history, the diff, the coverage report, ultra-verifier and ultra-designer verdict blocks, CI status, review-thread state, the PR) rather than trusting summaries. It has the authority to HALT the entire run/team and block merge/completion when rigor was bypassed and not corrected. Use as the terminal gate of fx-ultra:dev (STEP 9) and the final per-PR gate of fx-ultra:team shutdown. Triggers: 'judge', 'final gate', 'audit the work', 'is this actually done', 'ultra-judge', before declaring any task/PR complete or merging.

Verify web application changes work by launching the app stack and testing in a real browser. This skill should be used when the user asks to "verify the change", "test in browser", "check if it works", or after completing a PR to validate the implementation. Requires Playwright MCP server. MUST exit if Playwright MCP is unavailable.