reverse-documentation

Automatically generate comprehensive documentation for Rust and TypeScript codebases by analyzing code structure, patterns, and relationships. Supports trait-based patterns, async operations, React components, and Next.js applications.

Quality

46%

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 ./.github/skills/reverse-documentation/SKILL.md

Quality

Content

31%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.

The skill reads as a feature catalog rather than operational guidance: it explains concepts Claude already knows and lists capabilities instead of giving concrete, executable steps for generating documentation. The single-file monolithic structure and missing validation feedback loop further weaken it.

Suggestions

Cut the 'Core concepts' and 'Capabilities' enumeration sections that re-explain Rust/TypeScript fundamentals Claude already knows, and replace with concise guidance on how to actually produce the documentation.

Add a concrete Validation feedback loop with a checkpoint and command, e.g. run `cargo test --doc` / `cargo build` for Rust examples and `tsc --noEmit` for TypeScript, then fix and re-verify before emitting final docs.

Move the EdgeQuake-specific patterns and per-language capability catalogs into separate reference files under references/ and link to them from SKILL.md, keeping the main file as a lean overview with quick-start prompts.

Dimension	Reasoning	Score
Conciseness	The 292-line body extensively enumerates concepts Claude already knows (what module organization, Result types, useState/useReducer, React props, JSDoc, etc. are) and pads with redundant best-practice and capability lists; it noticeably over-explains without adding information beyond Claude's existing knowledge.	2 / 5
Actionability	Despite being a documentation-generation skill, the body provides almost no executable guidance: the 'examples' are just natural-language prompts to paste, and there is no concrete code, command, or tool invocation showing how to actually generate the documentation.	2 / 5
Workflow Clarity	The Workflow section lists a clear five-phase sequence (Discovery, Analysis, Understanding, Generation, Validation), but the Validation Phase is only a single bullet ('Verify examples compile and documentation is complete') with no checkpoint, command, or feedback loop for this batch-generation operation, which per the rubric caps the score at 3.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ all absent), yet a large body of capability catalogs, language-specific pattern lists, and EdgeQuake-specific details that clearly belong in separate reference files is fully inlined into SKILL.md, leaving minimal structure across files.	2 / 5
	Total	9 / 20 Passed

Description

61%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.

The description clearly states what the skill does and names a coherent niche, but lacks an explicit 'Use when...' trigger clause, which caps completeness. Specificity is decent but the listed capabilities are pattern categories rather than crisp discrete actions.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when generating or regenerating documentation for Rust or TypeScript codebases, or when the user asks for API docs, architecture docs, or READMEs from existing code.'

Replace abstract pattern categories with concrete discrete actions, e.g. 'Generate API references, READMEs, architecture diagrams, and migration guides.'

Include common synonyms and file extensions users might say (crates, .rs, JSDoc, doc comments) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Rust and TypeScript codebases') and lists several concrete capability areas ('trait-based patterns, async operations, React components, and Next.js applications') but these are pattern categories rather than discrete documented actions, sitting between anchor 3 (1-2 concrete actions) and anchor 4 (several specific actions) and leaning toward the lower side because the actions are abstract categories.	3 / 5
Completeness	It clearly answers 'what' (generate comprehensive documentation for Rust and TypeScript codebases by analyzing code structure, patterns, and relationships) but has no explicit 'Use when...' clause or concrete trigger phrase for 'when', which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	It includes natural terms users would say ('documentation', 'Rust', 'TypeScript', 'React components', 'Next.js applications') with good coverage, though it omits common synonyms and file extensions like '.rs', 'crates', 'JSDoc', or 'API docs'.	4 / 5
Distinctiveness Conflict Risk	It carves a fairly clear niche (reverse-documentation generation for Rust+TypeScript codebases) with mostly distinct triggers, with only minor overlap risk against general documentation skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: raphaelmansuy/edgequake
Path: .github/skills/reverse-documentation/SKILL.md
Commit: 4904960

Reviewed: about 19 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.