Claude MarketplacesSubmit
mims-harvard avatar

Devtu Self Evolve

mims-harvard/tooluniverse

This is the orchestrator for ToolUniverse's self-improvement loop. It chains together specialized devtu skills to discover APIs, generate tools, test them with researcher persona agents, fix verified bugs, optimize skill quality, and ship via git. The testing phase is interesting because it runs biologist personas to find real issues, but about 50% are false positives from MCP interface confusion, so you always verify via CLI before fixing. It also includes usefulness testing beyond just "does the tool work" to catch skills that dump data without interpretation. Use this when you want to run a full development cycle or coordinate multiple improvement phases. The repo has benchmarks and detailed anti-patterns for both code and skill design.

skills.sh installs
310
GitHub stars
1.8K
last updated
Aug 21, 2026
View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill devtu-self-evolve --agent claude-code

Installs into .claude/skills of the current project.

Files

This is the orchestrator for ToolUniverse's self-improvement loop. It chains together specialized devtu skills to discover APIs, generate tools, test them with researcher persona agents, fix verified bugs, optimize skill quality, and ship via git. The testing phase is interesting because it runs biologist personas to find real issues, but about 50% are false positives from MCP interface confusion, so you always verify via CLI before fixing. It also includes usefulness testing beyond just "does the tool work" to catch skills that dump data without interpretation. Use this when you want to run a full development cycle or coordinate multiple improvement phases. The repo has benchmarks and detailed anti-patterns for both code and skill design.

Browse the repository on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/mims-harvard/tooluniverse
Categories
Testing & QA, Git & Pull Requests, Code Review & Quality, Debugging, Automation & Workflows
First seen
Jun 3, 2026

More from mims-harvard/tooluniverse

All 68

Recommended

More Testing & QA
1jwynia avatarnpx-clijwynia/agent-skillsBuild and publish npx-executable CLI tools using Bun as the primary toolchain with npm-compatible output. Use when the user wants to create a new CLI tool, set 307skills.sh installs
2microsoft avatarlaunchmicrosoft/vscodeLaunch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node deb304skills.sh installs
3pbnicad avatartelegram-bot-grammypbnicad/telegram-bot-grammy-skillTelegram Bot development skill using grammY framework, TypeScript, Drizzle ORM, Vitest testing, Biome linting, deployed to Cloudflare Workers with D1 database. 292skills.sh installs
4wix avatarwix-cli-app-validationwix/skillsUse when testing app readiness, verifying runtime behavior, or validating before releases and after changes in the code. Triggers include validate, test, verify287skills.sh installs
5davila7 avatarloki-modedavila7/claude-code-templatesMulti-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, d284skills.sh installs
6microsoft avatarcomponent-fixturesmicrosoft/vscodeUse when creating or updating component fixtures for screenshot testing, or when designing UI components to be fixture-friendly. Covers fixture file structure, 277skills.sh installs