--- name: 'expand' description: 'Runs the expansion analyzer to identify gaps, missing capabilities, undocumented decisions, and improvement opportunities in the codebase. Produces a ranked list of suggestions with rationale, impact scores, and effort estimates. Never creates tasks in analysis mode — all suggestions require explicit human approval. Use --save to persist suggestions to disk for later review.' generated_by: 'retort' last_model: 'sync-engine' last_updated: '' # Format: YAML frontmatter + Markdown body. Codex agent skill definition. # Docs: https://developers.openai.com/codex/guides/agents-md --- # expand Runs the expansion analyzer to identify gaps, missing capabilities, undocumented decisions, and improvement opportunities in the codebase. Produces a ranked list of suggestions with rationale, impact scores, and effort estimates. Never creates tasks in analysis mode — all suggestions require explicit human approval. Use --save to persist suggestions to disk for later review. ## Usage Invoke this skill when you need to perform the `expand` operation. ## Instructions 1. Parse command arguments and identify requested scope/files 2. Scan relevant files and adjacent tests/docs before changes 3. Execute the task with minimal diffs and explicit error handling 4. Validate using concrete checks (prefer `pnpm check-all`, plus command-specific test/lint/build) 5. Report outcomes with changed files, checks run, and any follow-up actions ## Output - Return a concise summary with status (`success`/`partial`/`failed`) - Include validation evidence (exit code, failing command, or passing summary) - Include next-step remediation when checks fail ## Project Context - Repository: retort - Default branch: main - Tech stack: javascript, yaml, markdown ## Conventions - Write minimal, focused changes - Maintain backwards compatibility - Include tests for behavioral changes - Never expose secrets or credentials - Follow the project's established patterns