document-code

AI DevKit · Document a code entry point with structured analysis, dependency mapping, and saved knowledge docs. Use when users ask to document, understand, or map code for a module, file, folder, function, or API.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and highly actionable, with a gated, validated workflow and clean section organization. Its only weakness is mild verbosity in the optional HTML Artifact section, which slightly dents token efficiency.

Suggestions

Tighten the HTML Artifact section: trim editorial lines like 'Complements the markdown — does not replace it' and move the detailed section-mapping spec to a bundled reference (e.g. references/html-artifact.md) so the main SKILL.md stays lean.

Keep the inline HTML guidance to the essential constraints (single file, inline CSS, mermaid via CDN, card-based grid) and link out for the full section mapping.

Consider extracting the Output Template into a short reference once a bundle directory is in use, keeping the workflow body focused on the analysis-first process.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean with short imperatives and no over-explanation of basic concepts, but the HTML Artifact section carries editorial prose ('Complements the markdown — does not replace it') and a fairly long inline spec that pads the token budget, placing it at 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Provides executable specifics throughout: an exact search command ('npx ai-devkit@latest memory search --query "..."'), a concrete output path ('docs/ai/implementation/knowledge-{name}.md'), a concrete normalization example ('calculateTotalPrice' → 'calculate-total-price'), and an exact CDN URL — copy-paste ready guidance.	3 / 3
Workflow Clarity	A clear 6-step sequence is gated by a Hard Rule ('Do not create documentation until the entry point is validated and analysis is complete') and includes explicit validation checkpoints (verify-exists in step 1, a dedicated Validation section), matching the score-3 anchor for clear sequence with validation steps.	3 / 3
Progressive Disclosure	No bundle files exist, so the skill is correctly self-contained with well-organized, clearly signaled sections; per the simple-skills guideline, well-organized sections alone can score 3 when no external references are needed.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

The description is strong across all dimensions: it states concrete capabilities, includes an explicit and natural trigger clause, answers both what and when, and occupies a clearly distinct niche. No changes needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Document a code entry point', 'structured analysis', 'dependency mapping', and 'saved knowledge docs' — matching the score-3 anchor for multiple specific concrete actions rather than naming only a domain plus some actions.	3 / 3
Completeness	It explicitly states both what the skill does (document entry points via analysis, dependency mapping, saved docs) and when to use it with an explicit 'Use when...' clause, satisfying the score-3 anchor for both what AND when.	3 / 3
Trigger Term Quality	The 'Use when users ask to document, understand, or map code for a module, file, folder, function, or API' clause covers natural terms users would actually say, including the common variations of entry-point types, fitting the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	The 'AI DevKit' tooling prefix plus the structured-analysis/dependency-mapping framing carves a clear niche with distinct triggers, making conflict with other skills unlikely as in the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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.

Repository: codeaholicguy/ai-devkit
Path: skills/document-code/SKILL.md
Commit: 15b09d2

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.