ecodan

Use when the user says "kickoff", "start feature", "complete initiative", "check status", "signal", "prune", "bootstrap", "reflect", or any other Cicadas lifecycle command. Orchestrates the Cicadas spec-driven development methodology.

Reviews existing test suites for coverage gaps, quality, and rigor; identifies weak or missing tests and guides fixes to reach a target coverage threshold. Use when asked to "review unit tests", "fix unit tests", "check test coverage", "audit tests", "improve test suite", or ensure coverage at end of an initiative or during maintenance. Do NOT use when the user asks to write tests from scratch for new, untested code.

Use before committing or pushing to update project documentation. Updates README.md, HOW-TO.md, src/cicadas/README.md, release-notes.md, agents.md, and CLAUDE.md to reflect recent code and structural changes.

Use when the user mentions "gavel", "gavel-ai", or asks for help running, configuring, or interpreting AI evaluations with the gavel-ai framework. Covers eval setup, golden dataset preparation, scenario formatting, CLI execution, judge selection, debugging, and results interpretation. Does NOT trigger on general requests to "evaluate" code, bugs, or written documents that are unrelated to the gavel-ai eval system.

Debug and diagnose media-lens production issues on Google Cloud Platform

Debug and diagnose media-lens production issues on Google Cloud Platform

Use when the user mentions "gavel", "gavel-ai", or asks for help running, configuring, or interpreting AI evaluations with the gavel-ai framework. Covers eval setup, scenario data, CLI execution, debugging, and results interpretation. Does NOT trigger on general requests to "evaluate" code, bugs, or written documents that are unrelated to the gavel-ai eval system.

Use when the user mentions "gavel", "gavel-ai", or asks for help running, configuring, or interpreting AI evaluations with the gavel-ai framework. Covers eval setup, scenario data, CLI execution, debugging, and results interpretation. Does NOT trigger on general requests to "evaluate" code, bugs, or written documents that are unrelated to the gavel-ai eval system.

Use when the user says "kickoff", "start feature", "complete initiative", "check status", "signal", "prune", "bootstrap", "reflect", "create a skill", "build a skill", "edit skill", "start a skill", or any other Cicadas lifecycle command. Orchestrates the Cicadas spec-driven development methodology.