CtrlK
BlogDocsLog inGet started
Tessl Logo

devtu-code-optimization

Code quality patterns and guidelines for ToolUniverse tool development. Apply when writing, fixing, or refactoring tool Python code in the ToolUniverse project. Encodes lessons from 80+ debug rounds. Use alongside devtu-fix-tool and devtu-self-evolve. Triggers: implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug fixes.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A model of a lean, actionable skill body: concrete commands, a validation checklist, a routing table, and well-structured one-level-deep references. The single blemish is that the Key Fix Categories table links use bare filenames (e.g. 'code-patterns.md') while the files live under 'references/', making those relative links inconsistent with the correctly-prefixed References section.

Suggestions

Make link paths consistent: the Key Fix Categories table uses bare 'code-patterns.md' / 'api-fixes.md' while the References section uses 'references/code-patterns.md' / 'references/api-fixes.md' — prefix the table links with 'references/' so they resolve.

DimensionReasoningScore

Conciseness

The ~45-line body is lean throughout: it assumes Claude's competence, explains no basic concepts, and every line is an actionable command, checklist item, or routing pointer with no padding.

3 / 3

Actionability

Provides copy-paste-ready executable commands throughout — 'ruff check src/tooluniverse/<file>.py', 'python -c "from tooluniverse.<module> import <Class>"', 'python -m tooluniverse.cli run <Tool> \'<real_args_json>\'', the json.load one-liner, and concrete git commands.

3 / 3

Workflow Clarity

The Pre-Commit Checklist is an explicit validation gate before commit, and the git workflow includes a checkpoint ('gh pr view <N> --json mergeable # must be MERGEABLE before done'); validation is present so the destructive/batch cap does not apply.

3 / 3

Progressive Disclosure

A concise overview routes to two real one-level-deep references (verified: references/api-fixes.md and references/code-patterns.md exist with matching sections) via a category-to-section table and a dedicated References list.

3 / 3

Total

12

/

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.

A strong, third-person description that clearly states capabilities, gives explicit trigger guidance, and is tightly scoped to its project niche with named sibling skills. Every dimension lands at the top anchor; the only minor nit is that some trigger terms are project-internal jargon, but they remain natural within this domain.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'writing, fixing, or refactoring tool Python code' and a Triggers list covering 'implementing tool fixes, writing new tool classes, reviewing tool code quality, checking schema correctness, looking up API-specific bug fixes' — rather than vague language.

3 / 3

Completeness

Answers both what ('Code quality patterns and guidelines for ToolUniverse tool development', 'Encodes lessons from 80+ debug rounds') and when via an explicit 'Apply when…' clause plus the 'Triggers:' list.

3 / 3

Trigger Term Quality

An explicit 'Triggers:' clause gives five distinct, naturally-said phrases a developer would use when reaching for this skill; coverage is broad rather than jargon-only.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to 'ToolUniverse project' / 'tool Python code' and names sibling skills ('Use alongside devtu-fix-tool and devtu-self-evolve'), giving it a clear niche unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

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.