Tessl • The management layer for AI agent skills

SkillPublic

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

59%

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

35%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 body is well-organized and easy to navigate, but it reads as a capability catalog rather than an operating manual: it re-lists concepts Claude already knows across duplicated sections, and provides prompt templates and phase names instead of executable commands or concrete validation loops. Moving the language-specific and EdgeQuake-specific catalogs into reference files and tightening the workflow into actionable, verifiable steps would raise both conciseness and actionability.

Suggestions

Merge the duplicated "Core concepts" and "Capabilities" sections into one catalog and cut explanations of concepts Claude already knows (Result types, useState/useReducer, what a trait is), keeping only the repo-specific conventions.

Make the Workflow actionable: for each phase give the concrete action (e.g. commands to run, what to extract from Cargo.toml) and an explicit validation loop such as "run `cargo test --doc` on generated examples; fix and re-run until they compile".

Split bulk detail into one-level-deep reference files (e.g. references/rust-patterns.md, references/typescript-patterns.md, references/edgequake.md) and keep SKILL.md as a lean overview with clearly signaled links, replacing inline prompt snippets with a few copy-paste-ready invocations.

Dimension	Reasoning	Score
Conciseness	"Core concepts" and "Capabilities" duplicate each other, both cataloging concepts Claude already knows ("Result types, custom error types", "useState, useReducer, Context API", "Struct, enum, and trait definitions"), the ✅ "Best practices" checklists state the obvious, and "Next.js 15 App Router" bakes in a version number — several padded sections that should be trimmed or merged, matching anchor 2 rather than the occasional excess of anchor 3.	2 / 5
Actionability	The guidance consists of prompt templates ("Generate comprehensive documentation for the [crate-name] crate") and a config YAML block, with no executable commands or code, and the Workflow phases ("Discovery Phase: Scan the codebase") are one-line descriptions that never say how to perform each step — high-level hints missing the specific steps to execute, matching anchor 2.	2 / 5
Workflow Clarity	The five-phase sequence (Discovery → Analysis → Understanding → Generation → Validation) is clearly ordered and names a Validation Phase, but the checkpoints are implicit — there is no concrete validate/fix/re-verify loop for "Verify examples compile" — and Troubleshooting offers only generic checklists, matching anchor 3.	3 / 5
Progressive Disclosure	The body has clear section headers and easy navigation, but ~290 lines are inlined in a single file with no bundle — the language-specific capability catalogs and the ~78-line "EdgeQuake-specific patterns" section are content that would sit better in one-level-deep reference files, matching anchor 3 rather than the well-split structure of anchor 4.	3 / 5
	Total	10 / 20 Passed

Description

66%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 anchors it to a specific, recognizable niche (Rust/TypeScript documentation generation), but it omits any explicit "use when" trigger guidance and is missing natural synonyms like "docs" or "README". It sits comfortably above the midpoint but below the exemplar descriptions that pair concrete actions with explicit trigger phrases.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to generate docs, document a crate or component, or create README/API-reference documentation for Rust or TypeScript code."

Enumerate the concrete documentation outputs (API reference, README, architecture diagrams, migration guides) so the "what" is comprehensive, not just "comprehensive documentation".

Add natural synonyms and trigger phrases users would actually say — "docs", "document this", "README", "API reference" — to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Automatically generate comprehensive documentation" and "analyzing code structure, patterns, and relationships" are concrete actions, and the description enumerates specific pattern coverage ("trait-based patterns, async operations, React components, and Next.js"), but it never states what documentation outputs it produces (README, API reference, migration guides), leaving minor gaps that keep it below anchor 5.	4 / 5
Completeness	The "what" is clear (generate documentation for Rust/TypeScript codebases by analyzing structure and patterns), but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by naming the codebase types, which caps this dimension at 3.	3 / 5
Trigger Term Quality	Natural terms users would say are present ("documentation", "Rust", "TypeScript", "React components", "Next.js"), but common synonyms and phrases like "docs", "document this code", "README", or "API reference" are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	"Rust and TypeScript codebases" combined with the specific pattern list carves a mostly distinct documentation-generation niche with only minor overlap risk against a generic write-documentation skill; it lacks the fully distinct trigger phrases of anchor 5.	4 / 5
	Total	15 / 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
Revision: 7b305fb

Reviewed: 28 days ago

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.

reverse-documentation

Table of Contents

Is this your skill?