devtu-fix-tool

Diagnose and fix failing ToolUniverse tools and their test failures.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/Centaurioun/osteogenesis_imperfecta --skill devtu-fix-tool-centaurioun
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: devtu-fix-tool
Source: https://github.com/Centaurioun/osteogenesis_imperfecta/tree/main/.agents/skills/devtu-fix-tool
Command: npx skills add https://github.com/Centaurioun/osteogenesis_imperfecta --skill devtu-fix-tool-centaurioun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of debugging and repairing ToolUniverse tools that fail integration tests or produce incorrect results by providing a structured workflow for diagnosis, targeted fixes, and verification.

Core Features & Use Cases

  • Root-cause diagnosis: Run targeted verbose tests and inspect API responses, headers, and generated wrappers to identify binary responses, schema mismatches, endpoint errors, and parameter type issues.
  • Targeted remediation: Update tool run() implementations, adjust return_schema and parameter schemas, make mutually-exclusive params nullable, fix endpoints, and add binary-response metadata handling.
  • Verification & regeneration: Regenerate tool wrappers, run integration tests and unit tests, and produce a concise fix summary for handoff or commit.
  • Use case: Fix a failing ChEMBL image endpoint that raises JSON parse errors by detecting image content-types, returning metadata instead of parsing, and updating the tool's return_schema and tests.

Quick Start

Run a verbose diagnostic on the failing ToolUniverse tool, identify schema or binary-response issues, propose code and JSON config changes, and verify by re-running tests.

Frequently Asked Questions about devtu-fix-tool

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fix a ToolUniverse tool that fails schema validation?

Fix schema validation failures by running verbose diagnostics to inspect API responses, updating the tool's return_schema, correcting parameter typing, and regenerating generated wrappers for final verification.

Why does my REST API tool return JSON parse errors for binary responses?

JSON parse errors occur when REST API tools receive binary content-types. Resolve this by detecting image content-types, returning metadata instead of parsing, and updating the return_schema accordingly.

How do I debug failing integration tests for Python API tools?

Debug failing integration tests by executing targeted verbose tests, inspecting API headers and responses for endpoint errors, adjusting mutually-exclusive parameters, and rerunning unit and integration tests.

What is the best way to handle nullable and mutually-exclusive parameters in API testing?

Handle nullable and mutually-exclusive parameters during API testing by updating tool run() implementations, adjusting parameter schemas to allow nulls, and verifying valid test_examples end-to-end.

Can I use this workflow to correct endpoint errors in local ToolUniverse configurations?

Yes, you can use this workflow to correct endpoint errors in local ToolUniverse configurations by applying targeted remediation to REST-api backed tools and verifying fixes through wrapper regeneration.

What should I do when regenerating generated wrappers does not fix test failures?

When regenerating wrappers does not fix test failures, inspect content-type checks, verify return_schema alignment, ensure valid test_examples, and confirm correct endpoint corrections before re-running tests.