Content
72%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
Highly actionable and clearly sequenced multi-step orchestration with explicit validation, weakened mainly by repeated constraint restatements and no externalized reference structure.
Suggestions
Consolidate the repeated CJS_TO_ESM override and no-write constraint clauses into a single authoritative block to reduce token bloat.
Move the long git-grep command families and quality-contract bullet list into a references/ file linked from the body to improve progressive disclosure.
Add a short 'Validation steps are read-only' reminder once instead of restating the forbidden-command list multiple times.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a reasonable overview, but the frontmatter task prompt contains heavy repetition (the CJS_TO_ESM override and no-write constraints are restated many times) that pads the loaded skill; some explanation could be tightened. | 3 / 5 |
Actionability | Provides concrete, copy-paste-ready discovery commands (e.g. `git grep -nE "require\(...`, `npm pkg get type main exports scripts`, `npm pack --dry-run`), explicit section structure, and specific validation command families. | 5 / 5 |
Workflow Clarity | The pipeline is clearly sequenced (intake -> clarify -> classify -> fetch_guide -> repo_context -> write_plan) with explicit gating conditions, depends_on edges, and read-only validation checkpoints with error-recovery guidance. | 5 / 5 |
Progressive Disclosure | No bundle files exist (references/, scripts/, assets/ are absent) and the body is a single self-contained overview; structure is adequate but content that could be externalized (long command tables, quality contract) is inlined. | 3 / 5 |
Total | 16 / 20 Passed |