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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/document-code/SKILL.md

Quality

Content

75%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 well-structured, mostly lean instruction skill with concrete commands, a gating rule, and a validation checklist. It falls just short of top marks because it lacks a worked example, an explicit error-recovery feedback loop, and any offloading of the detailed HTML spec to a reference file.

Suggestions

Add one short worked example of a generated knowledge-{name}.md (even a truncated sample) so the Output Template is unambiguous and actionability can reach 5.

Add an explicit feedback loop in the Workflow or Validation section (e.g., if the HTML artifact drifts from the markdown, regenerate from markdown and re-check) to strengthen workflow clarity.

Consider moving the detailed HTML Artifact section mapping into a referenced HTML_ARTIFACT.md so the SKILL.md body stays a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean with short workflow bullets and no padding of concepts Claude already knows; only minor prose like "The reader should capture structure at a glance" could be trimmed, fitting the efficient-but-slightly-tightenable 4 anchor.	4 / 5
Actionability	Provides a concrete command (npx ai-devkit memory search), an exact output path, a naming normalization example, and an Output Template, but lacks a full worked example of a produced knowledge doc, matching the mostly-executable 4 anchor.	4 / 5
Workflow Clarity	A clear 6-step sequence with a Hard Rule gating step and a final Validation checklist is strong, but there is no explicit validate-fix-retry feedback loop, which keeps it at 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist and the body is well-organized into clear sections, but at ~85 lines the detailed HTML Artifact spec is inlined where it could plausibly be a separate one-level reference, matching the good-structure-with-minor-gaps 4 anchor.	4 / 5
	Total	16 / 20 Passed

Description

83%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, third-person description that clearly states capability and explicit usage triggers with natural synonyms and concrete entry-point types. It is comprehensive on completeness and only slightly shy of top marks on specificity, trigger breadth, and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions ("structured analysis, dependency mapping, and saved knowledge docs"), matching the "several specific actions; minor gaps" anchor rather than the 1-2 actions of a 3 or the comprehensive coverage of a 5.	4 / 5
Completeness	Explicitly answers both what ("Document a code entry point with structured analysis, dependency mapping, and saved knowledge docs") and when ("Use when users ask to document, understand, or map code…") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger verbs ("document, understand, or map code") plus an entity list (module, file, folder, function, API) give good keyword coverage with synonyms, but no file extensions, so it falls just short of the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (code entry-point documentation tied to AI DevKit) with distinct triggers, but minor overlap risk with generic code-explanation skills keeps it just below the minimal-conflict 5.	4 / 5
	Total	17 / 20 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: d56e554

Reviewed: 3 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.