code-documentation

Use this skill when the user requests to generate, create, or improve documentation for code, APIs, libraries, repositories, or software projects. Supports README generation, API reference documentation, inline code comments, architecture documentation, changelog generation, and developer guides. Trigger on requests like "document this code", "create a README", "generate API docs", "write developer guide", or when analyzing codebases for documentation purposes.

Quality

88%

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

77%

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

The body is highly actionable with a clear three-phase workflow and explicit validation, but it is verbose and monolithic — it teaches docstring/formatting conventions Claude already knows and inlines large templates that belong in separate reference files. Actionability and workflow clarity are strong; conciseness and progressive disclosure lag.

Suggestions

Condense or remove the inline docstring examples (Python/TypeScript/Go) and the "Documentation Style Guide" writing principles and formatting rules — Claude already knows these conventions; keep only project-specific deviations.

Trim the ~70-line generic README template to the essential section list rather than full placeholder boilerplate.

Move the large templates (README, API reference, architecture) and style guide into separate reference files (e.g., references/readme-template.md, references/api-reference-template.md) and link to them from SKILL.md, leaving the body as a concise overview.

Dimension	Reasoning	Score
Conciseness	The ~410-line body is mostly structured but padded with concepts Claude already knows — full docstring examples for Python/TypeScript/Go, writing principles ("active voice", "present tense"), and basic formatting rules ("Use ATX-style headers", fenced code blocks) — plus a ~70-line generic README template that could be tightened.	2 / 3
Actionability	Provides concrete, executable guidance throughout — Phase 1.2 bash commands (ls, read_file, grep -r "export "), discovery checks keyed to real files (package.json, pyproject.toml, go.mod, Cargo.toml), copy-paste-ready templates, and explicit output paths and tools (present_files, /mnt/user-data/outputs/).	3 / 3
Workflow Clarity	Sequences work into Phase 1 (Analysis) → Phase 2 (Generation) → Phase 3 (QA) with numbered sub-steps, and Phase 3 supplies explicit validation checkpoints (completeness checklist, cross-reference validation ensuring paths/functions/signatures/links are correct).	3 / 3
Progressive Disclosure	No bundle files exist and everything is inline in one ~410-line file; large templates (README, API reference, architecture) and the style guide are content that should be split into separate reference files but instead sit inline, matching the score-2 anchor of "content that should be separate is inline."	2 / 3
	Total	10 / 12 Passed

Description

100%

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, supplies natural trigger phrases, explicitly covers both what and when, and occupies a clear niche. It follows the proven "Use when..." pattern from the reference examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and output types — "README generation, API reference documentation, inline code comments, architecture documentation, changelog generation, and developer guides" — matching the score-3 anchor of listing multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("generate, create, or improve documentation for code, APIs, libraries...") and when ("Use this skill when the user requests..." / "Trigger on requests like..."), matching the score-3 anchor for clear what-and-when with explicit triggers.	3 / 3
Trigger Term Quality	Quotes natural phrases users would actually say — "document this code", "create a README", "generate API docs", "write developer guide" — giving good coverage of real-world trigger terms.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche — documentation for code/APIs/libraries/repositories/software projects — with triggers tied to that domain, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: bytedance/deer-flow
Path: skills/public/code-documentation/SKILL.md
Commit: 5f0108f

Reviewed: about 13 hours 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.