Devtu Code Optimization
Developmentdevtu-code-optimizationDevtu Code Optimization is an Agent Skill for development published in the mims-harvard/ToolUniverse repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
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.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/mims-harvard/ToolUniverse/blob/HEAD/skills/devtu-code-optimization/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/devtu-code-optimization, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
ToolUniverse Code Optimization
Always run Skill(skill="simplify") after writing or modifying code.
Pre-Commit Checklist
-
return_schemahasoneOf: [{data+metadata}, {error}] - Test examples use real IDs (no DUMMY/PLACEHOLDER)
-
try:hasexcept:at exact same indentation level - No trailing commas in JSON (
python3 -c "import json; json.load(open('f.json'))") - New tool class registered in
_lazy_registry_static.pyanddefault_config.py -
ruff check src/tooluniverse/<file>.pypasses -
python -c "from tooluniverse.<module> import <Class>"passes -
python -m tooluniverse.cli run <Tool> '<real_args_json>'returns expected data - Ran
Skill(skill="simplify")on all modified files
Key Fix Categories
| Category | Signal | Reference |
|---|---|---|
| Silent param ignored | API accepts but drops filter | code-patterns.md — Client-Side Filter |
| Wrong API field/endpoint | 0 results or 404 | api-fixes.md — Quick Lookup Table |
| Schema invalid | null type, missing oneOf | code-patterns.md — Schema Patterns |
| Undisclosed normalization | Auto-transform hidden from user | code-patterns.md — Normalization Disclosure |
| try/except indent | SyntaxError at runtime | code-patterns.md — try/except section |
| Truncation buried | Data count hidden in notes | code-patterns.md — Truncation |
| Hosted model API (NIM) | async 404 on poll, JSON-wrapped output, 200+inner-failure, "not found for account" | code-patterns.md — Hosted Model-API Tools |
| R subprocess tool | '\.' unrecognized escape from Rscript -e | code-patterns.md — R-subprocess Tools |
References
- references/api-fixes.md — Per-API bug fixes (GtoPdb, CIViC, GTEx, ENCODE, CPIC, etc.)
- references/code-patterns.md — Reusable Python patterns (schema, filtering, pagination, normalization)
Git & PR Workflow
git fetch origin && git stash && git rebase origin/main && git stash pop
git push --force-with-lease origin fix/round-XX-bugs
gh pr view <N> --json mergeable # must be MERGEABLE before done
- Never push to
maindirectly - Never have multiple open fix PRs
- Commit messages: "Feature" or "Fix" — never "Bug"
- No AI attribution in commits
- Repo:
mims-harvard/ToolUniverse— verify withgit remote -v