Content
88%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.
A lean, highly actionable body: exact commands, a copy-paste-ready fallback Grep, and two clearly numbered workflows with an explicit validate-and-fix checkpoint. The main defects are minor — a small motivational section and duplicated language examples that could be trimmed, and references to SPECIFICATION.md/example files that do not resolve within the bundle.
Suggestions
Ship SPECIFICATION.md and the example files in the bundle (or remove the references to them), so the 'See SPECIFICATION.md for the complete per-language reference' pointers resolve.
Trim or drop the '## Why this works' section and the four per-language wrapper code blocks — the body already says `generate` produces the correct wrapper and SPECIFICATION.md holds the complete list.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and assumes competence — no explaining what YAML or Python is, and concrete cost framing ('a 300-line file's header costs ~50 tokens'). Minor trimming possible: the '## Why this works' section is motivational rather than instructional, and the four per-language wrapper examples duplicate detail the body itself says `generate` produces automatically and `SPECIFICATION.md` fully documents. Matches the 4 anchor (efficient, minor over-explanation) rather than the 5 anchor (every token earns its place). | 4 / 5 |
Actionability | Fully executable guidance throughout: exact commands with flags ('python scripts/frontmatter.py index <dir> [--format md|json] [--min-lines N]', 'generate <file> [--write]', 'validate <dir>' with exit-1 note), a copy-paste-ready parameterized Grep call, `Read` with `limit: 20`, a worked purpose example ('Genetic algorithm for FPL squad optimisation' beats 'GA module'), and a field table with formats. Matches the 5 anchor. | 5 / 5 |
Workflow Clarity | Both modes are clearly sequenced as numbered steps with an explicit validation checkpoint — 'Validate before you finish. Run validate <dir>; fix any unresolved `related` paths or empty purposes' — that enumerates the failure modes, plus a no-frontmatter fallback ('No frontmatter? Say so and fall back'). Matches the 5 anchor (explicit validation steps and error-recovery guidance); the 4 anchor would require missing checkpoints, which are present in both workflows. | 5 / 5 |
Progressive Disclosure | Good structure: the main file is self-sufficient for the common case and explicitly defers the full schema ('Don't read the example files or `SPECIFICATION.md` unless you need the full schema'; 'See `SPECIFICATION.md` for the complete per-language reference'), and `scripts/frontmatter.py` exists with exactly the documented index/generate/validate subcommands. However, `SPECIFICATION.md` and the 'example files' are referenced but absent from the bundle — dangling references are a minor organization gap, matching the 4 anchor rather than 5. | 4 / 5 |
Total | 18 / 20 Passed |