Skip to main content
skill CX Codex

create-tooluniverse-skill — Claude Code skill: build ToolUniverse

Walks you through seven phases of building a ToolUniverse skill, from domain analysis and tool testing to packaging. Aimed at maintainers.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mims-harvard/ToolUniverse --skill create-tooluniverse-skill -a claude-code
Open on GitHub

What create-tooluniverse-skill does

This skill lays out the order of work on a new ToolUniverse skill. You start with use cases and data types, then search tool configs and test each tool with a script. Docs come last, after testing — that is the first of ten principles the workflow rests on.

Seven phases, each with a rough time budget: domain analysis, tool discovery, tool creation, implementation of python_implementation.py, documentation, validation, packaging. Without tool creation it runs about 1.5–2 hours. Every phase has a template file in the repo: SKILL_TEMPLATE.md, TESTING_GUIDE.md, VALIDATION_CHECKLIST.md, CODE_TEMPLATES.md and others.

It is maintainer-facing, not part of the user-facing plugin mirror. Some steps hand off to devtu-create-tool, devtu-fix-tool and devtu-optimize-skills, but those moved to the tu-harness plugin and install separately — without it those references won't resolve. Worth checking that tu-harness is already present before you start.

What it helps with

  • break ToolUniverse skill creation into clear phases
  • test tools before documenting them
  • write SKILL.md with no Python or MCP code
  • produce a QUICK_START.md covering both interfaces
  • run a pre-release checklist over a finished skill

Example prompts for the agent

  • help me create a new ToolUniverse skill for working with protein structures
  • test the tools with a script before writing SKILL.md
  • walk my skill through the validation checklist

How to install create-tooluniverse-skill

1Skills CLI (Vercel)

npx skills add mims-harvard/ToolUniverse --skill create-tooluniverse-skill -a claude-code

2Manually: put the files in place

~/.claude/skills/create-tooluniverse-skill/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/create-tooluniverse-skill/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about create-tooluniverse-skill

How do I install create-tooluniverse-skill in Claude?

Run npx skills add mims-harvard/ToolUniverse --skill create-tooluniverse-skill -a claude-code. The skill file then lands at ~/.claude/skills/create-tooluniverse-skill/SKILL.md.

What does create-tooluniverse-skill do?

It runs you through seven phases of building a ToolUniverse skill: domain analysis, tool discovery and testing, implementation, documentation, validation and packaging. It follows ten principles, the first being tests before docs.

Do I need other skills for it to work?

Yes, when functionality is missing or tools fail. The devtu-create-tool, devtu-fix-tool and devtu-optimize-skills skills moved to the tu-harness plugin and install with claude plugin install tu-harness@tooluniverse-harness.

Source text

SKILL.md · Apache-2.0
---
name: create-tooluniverse-skill
description: Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology.
disable-model-invocation: true
---

# Create ToolUniverse Skill

Systematic workflow for creating production-ready ToolUniverse skills.

> **The `devtu-*` skills this one hands off to are no longer in this
> repository.** `devtu-optimize-skills`, `devtu-create-tool` and
> `devtu-fix-tool` moved to the **tu-harness** plugin
> ([tooluniverse/tooluniverse-harness](https://github.com/tooluniverse/tooluniverse-harness)),
> because they operate on this repository rather than being something a user of
> it calls. Install them with
> `claude plugin install tu-harness@tooluniverse-harness`; the references below
> name them by skill, so they resolve once that plugin is present. This skill
> is maintainer-facing too -- it is not in the user-facing plugin mirror -- and
> belongs beside them; it has not moved yet only because nothing forced the
> question.

## Core Principles

Build on the 10 pillars from `devtu-optimize-skills`:
1. TEST FIRST - never document untested tools
2. Verify tool contracts - don't trust function names
3. Handle SOAP tools - add `operation` parameter
4. Implementation-agnostic docs - no Python/MCP code in SKILL.md
5. Foundation first - query aggregators before specialized tools
6. Disambiguate carefully - resolve IDs properly
7. Implement fallbacks - Primary -> Fallback -> Default
8. Grade evidence - T1-T4 tiers on claims
9. Quantified completeness - numeric minimums per section
10. Synthesize - models and hypotheses, not just lists

See `OPTIMIZE_INTEGRATION.md` for detailed application of each pillar.

## 7-Phase Workflow

| Phase | Duration | Description |
|-------|----------|-------------|
| 1. Domain Analysis | 15 min | Understand use cases, data types, analysis phases |
| 2. Tool Discovery | 30-45 min | Search, read configs, test tools (MANDATORY) |
| 3. Tool Creation | 0-60 min | Create missing tools via devtu-create-tool |
| 4. Implementation | 30-45 min | Write python_implementation.py with tested tools |
| 5. Documentation | 30-45 min | Write SKILL.md (agnostic) + QUICK_START.md |
| 6. Validation | 15-30 min | Run test suite, validate checklist, manual verify |
| 7. Packaging | 15 min | Create summary, update tracking |

**Total**: ~1.5-2 hours (without tool creation).

### Phase 1: Domain Analysis

- Gather concrete use cases and expected outputs
- Identify inputs, outputs, and intermediate data types
- Break workflow into logical phases
- Review existing skills in `skills/` for patterns

### Phase 2: Tool Discovery and Testing

Search tools in `/src/tooluniverse/data/*.json` (186 tool files). For each tool, read its config to understand parameters and return schema. See `PARAMETER_VERIFICATION.md` for common pitfalls.

**Create and run a test script** using `test_tools_template.py`. For each tool: call with known-good params, verify response format, document corrections. See `TESTING_GUIDE.md` for the full test suite template and procedures.

### Phase 3: Tool Creation (If Needed)

Invoke `devtu-create-tool` when required functionality is missing and analysis is blocked. Use `devtu-fix-tool` if new tools fail tests.

### Phase 4: Implementation

Create `skills/tooluniverse-[domain]/` with:
- `python_implementation.py` - use only tested tools, try/except per phase, progressive report writing
- `test_skill.py` - test each input type, combined inputs, error handling

Use templates from `CODE_TEMPLATES.md`.

### Phase 5: Documentation

Write implementation-agnostic SKILL.md using `SKILL_TEMPLATE.md`. Write multi-implementation QUICK_START.md using `QUICKSTART_TEMPLATE.md`. Key rules: zero Python/MCP code in SKILL.md, equal treatment of both interfaces in QUICK_START.

See `IMPLEMENTATION_AGNOSTIC.md` for format guidelines with examples.

### Phase 6: Validation

Run the comprehensive test suite (see `TESTING_GUIDE.md`). Validate against `VALIDATION_CHECKLIST.md`. Perform manual verification: load ToolUniverse fresh, copy-paste QUICK_START example, verify output works.

### Phase 7: Packaging

Create summary document using `PACKAGING_TEMPLATE.md`. Update session tracking if creating multiple skills.

## Skill Integration

| Skill | When to Use |
|-------|-------------|
| **devtu-create-tool** | Critical functionality missing |
| **devtu-fix-tool** | Tool returns errors or unexpected format |
| **devtu-optimize-skills** | Evidence grading, report optimization |

## Quality Indicators

**High quality**: 100% test coverage before docs, agnostic SKILL.md, multi-implementation QUICK_START, fallback strategies, parameter corrections table, response format docs.

**Red flags**: Docs before testing, Python in SKILL.md, assumed parameters, no fallbacks, SOAP tools missing `operation`, no test script.

## Reference Files

| File | Content |
|------|---------|
| `SKILL_TEMPLATE.md` | Template for writing SKILL.md |
| `QUICKSTART_TEMPLATE.md` | Template for writing QUICK_START.md |
| `TESTING_GUIDE.md` | Test suite template and procedures |
| `VALIDATION_CHECKLIST.md` | Pre-release quality checklist |
| `PACKAGING_TEMPLATE.md` | Summary document template |
| `PARAMETER_VERIFICATION.md` | Tool parameter verification guide |
| `OPTIMIZE_INTEGRATION.md` | devtu-optimize-skills 10-pillar integration |
| `IMPLEMENTATION_AGNOSTIC.md` | Implementation-agnostic format guide with examples |
| `CODE_TEMPLATES.md` | Python implementation and test templates |
| `test_tools_template.py` | Tool testing script template |

© mims-harvard · Apache-2.0 · mims-harvard/ToolUniverse

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set55

tooluniverse-epigenomics Processes DNA methylation, histone modifications, ChIP-seq, and ATAC-seq data. It computes CpG density and chromatin stats without row-deduplication errors. CX Codex +1 422installs tooluniverse-pharmacovigilance Performs systematic drug safety and adverse event analysis using FAERS, FDA warnings, and SIDER data. Computes disproportionality metrics via Python. CX Codex +1 420installs tooluniverse-chemical-compound-retrieval This skill pulls chemical compound data from PubChem and ChEMBL: names, SMILES, InChI, CID, properties and bioactivity. Useful when you need to verify a substance against databases instead of guessing. CX Codex +1 417installs tooluniverse-target-research Gathers target intelligence across 9 research paths: tissue expression, genetic evidence, safety, and druggability. Useful for target evaluation in drug discovery projects. CX Codex +1 409installs tooluniverse-spatial-transcriptomics Runs spatial transcriptomics analysis on Visium, MERFISH, seqFISH and Slide-seq data: spatially variable genes, tissue domains and neighbourhood structure. CX Codex +1 408installs tooluniverse-proteomics-analysis A skill for mass-spec proteomics: protein identification, quantification, differential expression and pathway enrichment. CX Codex +1 408installs tooluniverse-rare-disease-diagnosis Turns a patient phenotype into a ranked differential: HPO term matching, Orphanet and OMIM lookups, gene panel prioritization, ACMG variant interpretation. CX Codex +1 406installs tooluniverse-expression-data-retrieval Finds gene expression and omics datasets in ArrayExpress and BioStudies, scoring replicates and metadata quality. Helps locate RNA-seq and microarray experiments for analysis. CX Codex +1 405installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor