devtu-docs-quality

TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code execution, (A) automated validation, (B) ToolUniverse audit, (E) less-is-more simplification. Core philosophy: each concept appears exactly once; remove don't add; no emojis; single setup entry point. Use when reviewing docs, before releases, after API changes, or when asked to audit, fix, or simplify documentation.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

80%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 highly actionable with a clear, well-validated multi-phase workflow, but it loses points to internal redundancy and to references that point at files not shipped in the bundle.

Suggestions

Consolidate the 'no emojis', '1000+ tools', and less-is-more guidance into a single canonical section and cross-link from the others instead of restating them in 'Two Equal Priorities', 'Core Philosophy', and 'Apple-Style Simplification Rules'.

Ship the referenced API_REFERENCE.md, DOCS_STRUCTURE.md, and the scripts/ files in the bundle, or remove the 'Reference Files' section and Phase C/A script invocations so navigation does not point at missing files.

Move the long Phase D and Phase E Python scripts into bundled scripts/ files and invoke them from SKILL.md, keeping only the fix-table and rules inline to reduce the monolithic wall of code.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and concrete, but the 'no emojis' rule is restated three times, '1000+ tools' is repeated across sections, and the less-is-more philosophy is spread across 'Two Equal Priorities', 'Core Philosophy', and 'Apple-Style Simplification Rules' with overlapping guidance.	3 / 5
Actionability	Provides fully executable, copy-paste-ready Python scripts for Phases D and E, exact runner commands, and a complete wrong→correct method fix table covering the common cases.	5 / 5
Workflow Clarity	Five phases are explicitly ordered with a time/coverage table, gating rules ('Fix all items before proceeding to Phase C'), retry feedback loops ('stop, fix it, re-run... do not proceed until clean'), and a terminal validation checklist.	5 / 5
Progressive Disclosure	Internally well-sectioned with headers, but the 'Reference Files' section and Phase C/A commands point to API_REFERENCE.md, DOCS_STRUCTURE.md, and scripts/ that are not present in the bundle, and the large phase scripts are inlined rather than split into referenced files.	3 / 5
	Total	16 / 20 Passed

Description

92%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 is specific, complete, and well-scoped, explicitly stating both what the skill does and when to invoke it with natural trigger phrases. Its only minor gap is trigger-term synonym breadth.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('find and immediately fix or remove') and specific defect types (wrong code, broken links, incorrect counts, overlapping instructions) plus five enumerated phases — comprehensive coverage rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (fix/remove wrong, outdated, or redundant info in ToolUniverse docs via five phases) and 'when' with a concrete 'Use when...' clause listing multiple trigger situations.	5 / 5
Trigger Term Quality	Natural triggers are present ('reviewing docs', 'before releases', 'after API changes', 'audit, fix, or simplify documentation'), but coverage stops short of the synonym breadth a 5 would require.	4 / 5
Distinctiveness Conflict Risk	Scoped specifically to ToolUniverse docs QA with distinct phase-based triggers and a unique less-is-more philosophy, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 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
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: skills/devtu-docs-quality/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.