Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable and workflow-clear, with concrete file paths, regex logic, and full output templates plus error states. Its weaknesses are minor generic boilerplate in the Instructions section and a monolithic structure where the large output-format blocks could be factored into referenced files.
Suggestions
Remove the generic Instructions bullets ("Clarify goals…", "Apply relevant best practices…") that restate what Claude already knows.
Consider moving the long full/single-track output-format templates into a referenced file (e.g. templates/STATUS_FORMAT.md) with a concise inline summary to improve progressive disclosure.
Tighten the 'Use this skill when' / 'Do not use this skill when' sections to conductor-specific triggers rather than generic phrasing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with concrete output templates and calculation logic, but it includes generic boilerplate Claude already knows ("Clarify goals, constraints, and required inputs", "Apply relevant best practices and validate outcomes") that could be trimmed, matching the level-2 anchor. | 2 / 3 |
Actionability | It provides fully executable guidance: exact file paths (conductor/tracks/{trackId}/plan.md), regex patterns for task counting, a progress-bar formula, and complete copy-paste-ready output templates for every mode, matching the level-3 anchor. | 3 / 3 |
Workflow Clarity | The process is clearly sequenced (pre-flight checks → data collection → output) with explicit validation checkpoints (verify product.md/tracks.md exist) and dedicated error-state sections for recovery, matching the level-3 anchor. | 3 / 3 |
Progressive Disclosure | The skill is a single monolithic ~330-line file with no external references; sections are well-organized but the large output-format templates could be split into referenced files, matching the level-2 anchor for content that could be separate being inline. | 2 / 3 |
Total | 10 / 12 Passed |