Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Systematic workflow for creating production-ready ToolUniverse skills.
Build on the 10 pillars from devtu-optimize-skills:
operation parameterSee OPTIMIZE_INTEGRATION.md for detailed application of each pillar.
| 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).
skills/ for patternsSearch 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.
Invoke devtu-create-tool when required functionality is missing and analysis is blocked. Use devtu-fix-tool if new tools fail tests.
Create skills/tooluniverse-[domain]/ with:
python_implementation.py - use only tested tools, try/except per phase, progressive report writingtest_skill.py - test each input type, combined inputs, error handlingUse templates from CODE_TEMPLATES.md.
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.
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.
Create summary document using PACKAGING_TEMPLATE.md. Update session tracking if creating multiple skills.
| 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 |
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.
| 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 |
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
日本語の概要は準備中です。原文の説明を表示しています。
ADMET property prediction for drug candidates. Full pharmacokinetic panel (Caco-2, PPB, clearance, CYP), toxicity (hERG, AMES, DILI), drug-likeness (Lipinski, QED), using RDKit descriptors and TDC models.
日本語の概要は準備中です。原文の説明を表示しています。
Interpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
日本語の概要は準備中です。原文の説明を表示しています。
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
日本語の概要は準備中です。原文の説明を表示しています。
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
日本語の概要は準備中です。原文の説明を表示しています。