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

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 concrete commands, JSON/Python fix snippets, and a well-sequenced workflow including validation checkpoints. Its main weaknesses are redundancy across sections (Common Pitfalls, Quick Reference, Verification restate earlier content) and a broken external reference with no bundle files to offload detail into.

Suggestions

Create the referenced unit-tests-reference.md (or remove the dead link) and consider splitting the Error Types catalog and Quick Reference tables into reference files under references/ so SKILL.md stays a lean overview.

Remove duplicated content: drop the "Common Pitfalls" list and "Quick Reference" command/error tables that restate Error Types, "Where to Fix", and the Instructions commands verbatim.

Fix the step numbering in Instructions (two items are both labeled "4") and consolidate the regenerate/verify steps so the sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely additive domain knowledge (return_schema, optional_api_keys, data wrapper), but "Common Pitfalls", "Quick Reference", and "Verification" substantially restate commands and fixes already given in Error Types and Instructions, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready commands (cli run, test_new_tools.py, generate_tools, pytest) and concrete JSON/Python fix snippets (e.g. {"type": ["integer", "null"]}) plus a file-to-modify table — fully executable guidance.	3 / 3
Workflow Clarity	Instructions give a clear sequence with explicit validation checkpoints (CRITICAL verify-before-fix, verify-after, regenerate-then-retest feedback loop) and a unit-test checklist; the only blemish is a duplicated step numbered "4".	3 / 3
Progressive Disclosure	Internal sections are well-organized, but the skill is one monolithic file with no bundle files present, and its sole external reference ([unit-tests-reference.md](unit-tests-reference.md)) points to a file that does not exist — a broken link with content that should be split remaining 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 well-crafted: it states four concrete actions, includes an explicit "Use when" clause with multiple natural trigger terms, and is scoped to a distinct framework niche. It avoids vague fluff and over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "diagnosing test failures, identifying root causes, implementing fixes, and validating solutions" — matching the anchor for several specific concrete actions rather than just naming a domain.	3 / 3
Completeness	Clearly answers both what ("Fix failing ToolUniverse tools by diagnosing...") and when via an explicit "Use when..." clause with multiple triggers, matching the top anchor.	3 / 3
Trigger Term Quality	The "Use when" clause covers natural trigger phrasings a user would actually say — "fail tests", "return errors", "schema validation issues", "debug or fix tools" — giving good coverage of variations rather than only technical jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to a named framework (ToolUniverse) and specific failure modes (test failures, schema validation), giving it a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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: 089eb8e

Reviewed: about 6 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.