claude_plugin_skill_instructions:
  description: "PLUG-REQ-001 & REVIEW-REQ-007: Verify skill instructions adequately convey behavioral requirements."
  match:
    include:
      - "skills/**/*.md"
  review:
    strategy: matches_together
    instructions: |
      Review the Claude Code plugin skill files against behavioral
      requirements from PLUG-REQ-001 and REVIEW-REQ-007. These requirements
      specify what the skill instructions must tell the agent to do.

      Read each skill file and check the following:

      ## deepwork skill (plugins/claude/skills/deepwork/SKILL.md)

      - **PLUG-REQ-001.3.4**: The skill must support four intent-parsing
        modes: (1) discovering available workflows, (2) starting a named
        workflow, (3) inferring the best workflow from a freeform request,
        and (4) prompting the user to choose when no context is given.
        Verify the instructions clearly describe all four modes and an
        agent following them would handle each case.

      ## review skill (plugins/claude/skills/review/SKILL.md)

      - **PLUG-REQ-001.4.4 / REVIEW-REQ-007.1.5**: The skill must instruct
        the agent to launch review tasks in parallel. Verify the
        instructions clearly direct parallel execution, not just mention
        the word.
      - **PLUG-REQ-001.4.5 / REVIEW-REQ-007.1.6**: The skill must instruct
        the agent to automatically apply findings that are obviously correct
        with no downsides (e.g., typo fixes, unused imports). Verify the
        instructions clearly distinguish auto-apply cases from cases
        requiring user input.
      - **PLUG-REQ-001.4.7 / REVIEW-REQ-007.1.8**: The skill must instruct
        the agent to re-run reviews after making changes, repeating until
        no further actionable findings remain. Verify the instructions
        describe a clear iteration loop, not just a one-shot review.
      - **PLUG-REQ-001.4.9**: When no review rules are configured, the
        skill must offer to help the user discover and set up rules rather
        than silently producing no results. Verify the instructions include
        explicit handling for the no-rules case.

      ## configure_reviews skill (plugins/claude/skills/configure_reviews/SKILL.md)

      - **PLUG-REQ-001.5.4 / REVIEW-REQ-007.2.5**: The skill must instruct
        the agent to reuse existing review rules and instructions where
        possible rather than creating duplicates. Verify the instructions
        clearly convey a preference for reuse over duplication.

      ## deepreviews skill (plugins/claude/skills/deepreviews/SKILL.md)

      - **PLUG-REQ-001.13.2**: The skill must document how DeepWork Reviews
        work, including `.deepreview` config format, review strategies
        (`individual`, `matches_together`, `all_changed_files`), and how
        changed files are detected.
      - **PLUG-REQ-001.13.3**: The skill must explain how DeepSchemas
        automatically generate synthetic review rules.
      - **PLUG-REQ-001.13.4**: The skill must describe workflow quality
        gates and how `finished_step` triggers reviews on step outputs.

      Output Format:
      - PASS: All behavioral requirements are adequately conveyed.
      - FAIL: List each requirement ID that is not adequately covered,
        with a specific explanation of what is missing or unclear.
