devtu-fix-tool

Fix failing ToolUniverse tools by diagnosing test failures, identifying root causes, implementing fixes, and validating solutions. Use when ToolUniverse tools fail tests, return errors, have schema validation issues, or when asked to debug or fix tools in the ToolUniverse framework.

Quality

70%

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/devtu-fix-tool/SKILL.md

Quality

Content

52%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 and lays out a clear, validated workflow for fixing ToolUniverse tools, but it is undermined by noticeable redundancy across sections and a broken external reference. Consolidating duplicated tables/pitfalls and either providing or removing the dead unit-tests-reference.md link would materially improve it.

Suggestions

Consolidate the duplicate 'Where to Fix' table and the Quick Reference 'Error Type | Fix Location' table into one, and fold 'Common Pitfalls' into the Error Types section to remove restated content.

Fix the broken '[unit-tests-reference.md](unit-tests-reference.md)' reference by either adding the file to a references/ bundle or inlining the unit-test patterns directly.

Tighten 'Testing Best Practices' so it does not re-explain parameter-name verification already covered in Error Type 7 / the Verify Parameter Names subsection.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose through redundancy: the 'Where to Fix' table and the Quick Reference 'Error Type \| Fix Location' table overlap heavily, 'Common Pitfalls' restates the Error Types section, and 'Testing Best Practices' repeats the parameter-name verification already covered in Error Type 7 — several padded sections that could be consolidated.	2 / 5
Actionability	Mostly executable guidance with concrete bash commands, JSON config snippets, and ✅/❌ code examples covering common cases; minor gaps remain such as 'search online for official API documentation' and the Multi-Operation Pattern being described rather than shown as full code.	4 / 5
Workflow Clarity	A clear numbered sequence (run test → verify API → identify error → apply fix → regenerate → update tests → verify → summary) with validation checkpoints, a unit-test checklist, and a verify-then-fix feedback loop; a numbering bug (two steps labeled '4') and workflow content scattered across multiple sections are minor gaps.	4 / 5
Progressive Disclosure	The bulk error-type catalog and common-pitfalls material are inlined in SKILL.md rather than split out, and the single external reference '[unit-tests-reference.md](unit-tests-reference.md)' is a broken link — the referenced file does not exist in any bundle directory, signaling progressive disclosure that isn't actually delivered.	2 / 5
	Total	12 / 20 Passed

Description

87%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 description that clearly states capabilities and explicit use-when triggers tied to a specific framework niche. The only soft spot is specificity, where the listed actions are generic process verbs rather than concrete tool-level operations.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'diagnosing test failures, identifying root causes, implementing fixes, and validating solutions' — but the verbs are process-generic rather than concrete tool operations, leaving minor coverage gaps versus the level-5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' (Fix failing ToolUniverse tools by diagnosing/identifying/implementing/validating) and 'when' (Use when tools fail tests, return errors, have schema issues, or when asked to debug/fix) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('fail tests', 'return errors', 'schema validation issues', 'debug or fix tools', 'ToolUniverse') that users would plausibly say, though a few common synonyms/variations are missing.	4 / 5
Distinctiveness Conflict Risk	The 'ToolUniverse' framework qualifier carves a clear niche with distinct triggers, making overlap with other skills minimal.	5 / 5
	Total	18 / 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: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: skills/devtu-fix-tool/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.