// Record user feedback (natural language or structured data), perform AI attribution analysis linking results to past tasks, update evolution.md, and ask the user whether to start a new version. This is the core feedback loop skill.
Brainstorm features or run full project planning through structured dialogue. Use --full for initial project-wide planning (includes north star metrics if not set), or --feature <name> for a single feature. Always asks one question at a time. Invokes zeus-plan automatically after spec is approved.
Map an existing (brownfield) codebase into deterministic Zeus artifacts under .zeus/{version}/ so downstream skills can reuse real project context.
Execute all pending tasks in task.json using the zeus-runner.sh shell loop. Tasks are grouped into dependency waves and run with fresh claude CLI subagents. Each task gets an atomic git commit and a mandatory ai-log entry. Supports --version flag for v2/v3/v4 execution.
Initialize a new Zeus project. Creates .zeus/main/ directory structure, sets up config.json with north star metrics, and writes the first evolution.md entry. Use this FIRST before any other zeus skill.
Convert a spec document into structured prd.json user stories and task.json execution units. Called automatically by zeus-brainstorm, but can also be invoked directly. Supports --version flag to target v2/v3/v4 folders.
Display a full status report of the Zeus project — all active versions, task progress, recent feedback attribution, evolution history, and next recommended action.
| name | zeus-feedback |
| description | Record user feedback (natural language or structured data), perform AI attribution analysis linking results to past tasks, update evolution.md, and ask the user whether to start a new version. This is the core feedback loop skill. |
| argument-hint | ["--version vN"] |
| shell | bash |
Use this skill to convert real-world feedback into traceable product decisions.
Never recommend roadmap actions before attribution analysis is complete.
.zeus/{version}/task.json exists..zeus/{version}/feedback/ is writable..zeus/{version}/evolution.md is writable.Accept natural language, structured metrics, or mixed input.
If essential details are missing, ask one question at a time:
If .zeus/scripts/collect-metrics.sh exists, ask for permission and run:
bash .zeus/scripts/collect-metrics.sh
Merge output into feedback evidence.
Read:
.zeus/{version}/task.json.zeus/{version}/ai-logs/*git log --oneline -20)Compute candidate task attribution with confidence score:
Set requires_new_version true when:
Create .zeus/{version}/feedback/{YYYY-MM-DD-HHmmss}.json including:
Append a FEEDBACK record in .zeus/{version}/evolution.md.
Create .zeus/{version}/ai-logs/{ISO-ts}-feedback.md.
If evolution signal is true, offer:
/zeus:evolveUse zeus-analyst for attribution scoring and version-evolution recommendation quality.