CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

mcclowes/code-frontmatter

Context-efficient codebase navigation and documentation using structured frontmatter headers. Use this when exploring an unfamiliar codebase, answering "where is X / how does Y work" questions, or when asked to add/maintain file-level documentation. Index a tree's headers in one pass instead of reading every file, and generate or validate frontmatter with the bundled scripts. Reach for it whenever token budget matters while navigating code, even if the user does not say "frontmatter".

78

5.07x
Quality

90%

Does it follow best practices?

Impact

71%

5.07x

Average score across 7 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

88%Weight 40%Scale 1-5

Reviews 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.

DimensionReasoningScore

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

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly states both capabilities and trigger conditions in third person with concrete, natural trigger phrases. The only weaknesses are minor: a few missing natural trigger synonyms and slight overlap risk with generic codebase-exploration skills.

DimensionReasoningScore

Specificity

Multiple concrete actions are stated — 'Index a tree's headers in one pass', 'generate or validate frontmatter with the bundled scripts', 'add/maintain file-level documentation' — covering navigation, authoring, and validation comprehensively. This matches the 5 anchor (multiple specific concrete actions, comprehensive coverage); the 4 anchor would require a noticeable coverage gap, and none exists.

5 / 5

Completeness

Both what ('Context-efficient codebase navigation and documentation using structured frontmatter headers… Index a tree's headers in one pass… generate or validate frontmatter with the bundled scripts') and when ('Use this when exploring an unfamiliar codebase, answering "where is X / how does Y work" questions, or when asked to add/maintain file-level documentation') are explicit with concrete trigger phrases, exactly matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural phrases users would actually say are present: 'exploring an unfamiliar codebase', 'where is X / how does Y work', 'add/maintain file-level documentation', 'token budget matters while navigating code'. Falls short of the 5 anchor (comprehensive synonyms) because common variants like 'codebase overview', 'onboarding', or 'understand the code' are absent.

4 / 5

Distinctiveness Conflict Risk

The frontmatter-header niche is distinct and the description scopes triggers to it, but 'exploring an unfamiliar codebase' and 'token budget matters while navigating code' are broad enough to overlap with general code-exploration/search skills — the 4 anchor (mostly distinct, minor overlap risk with closely related skills) fits better than 5.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

On this page