Initialize a project for Flight Control. Creates .flightops directory with methodology reference and artifact configuration. Run before using other Flight Control skills on a new project.
Run a behavior test — spawn two live agents (an Executor that performs each step's actions and a Validator that judges each step's expected results), drive them through the spec's step table communicating mid-test so failures surface immediately, then write a run log with evidence. Tests are specs that follow the Witnessed pattern: every action is judged by an independent agent. Verifies system properties through observables (UI state, HTTP responses, shell output, filesystem state) measured via whichever apparatus (MCP, tool) is registered. Invocation: `/behavior-test <slug>` to run a test by slug. Specs are authored inline during flight/leg/mission planning — see `AUTHORING.md` sibling file for the authoring guide. Spec format lives in the target project's `.flightops/ARTIFACTS.md`.
Active orchestrator for multi-agent flight execution. Drives leg design per leg, then batches implementation across all autonomous legs, with a single code review and commit at the end of the flight.
Create technical flight specifications from missions. Use when breaking down a mission into implementable work or planning technical approach.
Between-mission codebase health assessment. Run after `/mission-debrief`, never after an individual flight, to verify the codebase is flight-ready or scaffold a maintenance mission. Per-flight findings instead roll into the next flight or accumulate into an end-of-mission maintenance flight — not into this skill.
Generate detailed implementation guidance for LLM execution. Use when creating atomic implementation steps from a flight.
Create outcome-driven missions through research and user interview. Use when starting a new project, feature, or initiative that needs planning.
Post-flight analysis for continuous improvement. Use after a flight is completed to capture lessons learned and improve the methodology.