devtu-self-evolve

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.

Quality

93%

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

95%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 content is a well-structured orchestrator skill: actionable commands throughout, a clearly sequenced multi-phase workflow with explicit validation checkpoints and feedback loops, and clean progressive disclosure via verified one-level-deep references. The only weakness is minor verbosity in the usefulness-testing section and a few inline tables that could be externalized.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely efficient, assuming Claude's competence throughout, with minor instances of over-explanation (e.g., the embedded usefulness-testing 1-10 rubric narrative) that could be tightened; it sits above the level-3 midpoint but below the fully lean level-5 anchor.	4 / 5
Actionability	Provides copy-paste-ready commands across every phase ('gh pr list --state open', 'python3 -m tooluniverse.cli run <ToolName> '<json_args>'', benchmark script invocations with full paths) and a real referenced persona template with a complete prompt structure, matching the fully-executable level-5 anchor.	5 / 5
Workflow Clarity	A clearly sequenced six-phase cycle with explicit CRITICAL validation steps (CLI verification before fixes, the '50%+ false positives' guardrail) and feedback loops for destructive/batch git operations (pre-commit re-stage, force-with-lease, mergeable-state check), matching the level-5 anchor with explicit validation and error-recovery checkpoints.	5 / 5
Progressive Disclosure	The body functions as an overview that dispatches to other devtu skills and signals one-level-deep references to two real, existing files ([references/persona-template.md] and [references/bug-patterns.md]) with clear markdown links; minor inline content (the issue-categories and usefulness-testing tables) could arguably be referenced out, keeping it just below the level-5 anchor.	4 / 5
	Total	18 / 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 strong: it concisely states the skill's purpose, lists concrete actions across the full lifecycle, and provides an explicit 'Use when' clause with natural trigger phrases. It is clearly distinguishable from other skills with low conflict risk.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — 'discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git' — covering the full cycle comprehensively, matching the level-5 anchor listing multiple specific concrete actions.	5 / 5
Completeness	Clearly states what ('Orchestrate the full ToolUniverse self-improvement cycle' with enumerated actions) and explicitly answers when via 'Use when asked to:' followed by concrete trigger phrases, matching the level-5 anchor.	5 / 5
Trigger Term Quality	Provides several natural trigger phrases users would say ('run the self-improvement loop', 'do a debug/test round', 'expand tool coverage', 'improve tool quality', 'evolve ToolUniverse') with good coverage, but lacks synonyms/file-extension-style variations for the level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The 'ToolUniverse self-improvement cycle' and 'devtu skills' framing carves a clear niche with distinct triggers and minimal conflict risk with unrelated skills, matching the level-5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: skills/devtu-self-evolve/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.