devtu-auto-discover-apis
Automatically discover life science APIs online, create ToolUniverse tools, validate them, and prepare integration PRs. Performs gap analysis to identify missing tool categories, web searches for APIs, automated tool creation using devtu-create-tool patterns, validation with devtu-fix-tool, and git workflow management. Use when expanding ToolUniverse coverage, adding new API integrations, or systematically discovering scientific resources.
- Installs
- 383
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/mims-harvard/tooluniverse --skill devtu-auto-discover-apis- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads devtu-auto-discover-apis automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Automated Life Science API Discovery & Tool Creation
Discover, create, validate, and integrate life science APIs into ToolUniverse.
Four-Phase Workflow
Gap Analysis → API Discovery → Tool Creation → Validation → Integration
↓ ↓ ↓ ↓ ↓
Coverage Web Search devtu-create devtu-fix Git PR
Human approval gates after: discovery, creation, validation, and before PR.
Phase 1: Discovery & Gap Analysis
1.1 Analyze Current Coverage
Load ToolUniverse, categorize tools by domain (genomics, proteomics, drug discovery, clinical, omics, imaging, literature, pathways, systems biology). Count per category.
1.2 Identify Gap Domains
- Critical Gap: <5 tools in category
- Moderate Gap: 5-15 tools, missing key subcategories
- Emerging Gap: New technologies not represented
Common gaps: single-cell genomics, metabolomics, patient registries, microbial genomics, multi-omics integration, synthetic biology, toxicology.
1.3 Web Search for APIs
For each gap domain, run multiple queries:
"[domain] API REST JSON"— direct API search"[domain] public database"— database discovery"[domain] API 2025 OR 2026"— recent releases"[domain] database" site:nar.oxfordjournals.org— NAR Database Issue
Extract: base URL, endpoints, auth method, parameter schemas, rate limits.
1.4 Score and Prioritize
| Criterion | Max Points |
|---|---|
| Documentation Quality | 20 |
| API Stability | 15 |
| Authentication Simplicity | 15 |
| Coverage | 15 |
| Maintenance | 10 |
| Community | 10 |
| License | 10 |
| Rate Limits | 5 |
High priority (>=70), Medium (50-69), Low (<50).
1.5 Generate Discovery Report
Coverage analysis, prioritized candidates with scores, implementation roadmap.
Phase 2: Tool Creation
For each API, use Skill(skill="devtu-create-tool") or follow these patterns.
Architecture Decision
- Multiple endpoints → multi-operation tool (single class, multiple JSON wrappers)
- Single endpoint → single-operation acceptable
Key Steps
- Design tool class following template — see references/tool-templates.md
- Create JSON config with oneOf return_schema
- Find real test examples (use List endpoint → extract IDs → verify)
- Register in
default_config.py
Critical Requirements
- return_schema MUST have
oneOf(success + error schemas) - test_examples MUST use real IDs (NO placeholders)
- Tool name <= 55 characters
- NEVER raise exceptions in
run()— return error dict - Set timeout on all HTTP requests (30s)
Phase 3: Validation
Full guide: references/validation-guide.md
Quick Validation Checklist
- Schema: oneOf structure, data wrapper, error field
- Placeholders: No TEST/DUMMY/PLACEHOLDER in test_examples
- Loading: 3-step check (class registered, config registered, wrappers generated)
- Integration tests:
python scripts/test_new_tools.py [api_name] -v→ 100% pass
Fix failures with Skill(skill="devtu-fix-tool").
Phase 4: Integration
Use Skill(skill="devtu-github") or:
- Create branch:
feature/add-[api-name]-tools - Stage tool files + default_config.py
- Commit with descriptive message
- Push and create PR with validation results
Processing Patterns
| Pattern | When to Use |
|---|---|
| Batch (multiple APIs → single PR) | Same domain, similar structure |
| Iterative (one API at a time) | Complex auth, novel patterns |
| Discovery-only (report, no tools) | Planning roadmap |
| Validation-only (audit existing) | PR review, quality check |
References
- Tool templates (Python class + JSON config): references/tool-templates.md
- Validation & integration guide: references/validation-guide.md
FAQ
What does the devtu-auto-discover-apis skill do?
Automatically discover life science APIs online, create ToolUniverse tools, validate them, and prepare integration PRs. Performs gap analysis to identify missing tool categories, web searches for APIs, automated tool creation using devtu-create-tool patterns, validation with devtu-fix-tool, and git workflow management. Use when expanding ToolUniverse coverage, adding new API integrations, or systematically discovering scientific resources.
How do I install devtu-auto-discover-apis?
Run npx skills add https://github.com/mims-harvard/tooluniverse --skill devtu-auto-discover-apis in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/devtu-auto-discover-apis/ (personal) or .claude/skills/devtu-auto-discover-apis/ (project).
Which AI agents can use devtu-auto-discover-apis?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is devtu-auto-discover-apis safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains devtu-auto-discover-apis?
It is published by mims-harvard in mims-harvard/tooluniverse. It has 383 recorded installs.
More from mims-harvard/tooluniverse
tooluniverse-sequence-retrieval
mims-harvard/tooluniverse
Retrieve DNA/RNA/protein sequences from NCBI and ENA with disambiguation. Quality hierarchy: RefSeq (NM/NP) RefSeq predicted (XM/XP) GenBank submissions. Use for fetching specific sequences by accession, gene-symbol-to-sequence lookup, transcript-isoform retrieval, and curated-vs-raw-submission preference.
tooluniverse-literature-deep-research
mims-harvard/tooluniverse
Deep literature review — PubMed, EuropePMC, bioRxiv preprints, citation networks, evidence synthesis. Disambiguates queries, runs collision-aware searches, grades evidence T1-T4, and produces structured reports. Use for systematic literature review, meta-analysis evidence collection, and detailed answer-with-citations workflows.
tooluniverse-image-analysis
mims-harvard/tooluniverse
Microscopy and quantitative imaging analysis — colony morphometry, fluorescence intensity quantification, cell-count statistics, dose-response curves, and ANOVA/Dunnett on image-derived measurements. Uses pandas/numpy/scipy/scikit-image. Use for analyzing tabular outputs from CellProfiler/ImageJ, image-derived measurement statistics, and image-based assay quantification.
tooluniverse-clinical-guidelines
mims-harvard/tooluniverse
Search and retrieve clinical practice guidelines from 12+ authoritative sources — NICE, WHO, NCCN, AHA, ADA, SIGN, USPSTF, IDSA, NIH consensus, ESMO/ESC/EASL European societies, and US specialty associations. Use for evidence-graded treatment recommendations, dosing protocols, screening guidance, and authoritative-source-prioritized clinical guidance (NICE/WHO ranked above society guidelines).
tooluniverse
mims-harvard/tooluniverse
ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains executed.ipynb, run tu run readexecutednotebook '{"datafolder":" ","search":" "}' to extract its cell outputs and apply EVERY filter/sample-exclusion the notebook used — even when the question says 'Using DESeq2/Run X/Compute Y' (this describes the METHOD the notebook used, not a request to rerun). The notebook's cell outputs are the only published authoritative answers; reimplementing or reading stale pre-computed CSVs in the data folder produces different numbers because of outlier-sample removal, library version, and filter steps you don't see by skimming. STEP 2 routing — pick a sub-skill name from this exact list (never invent): tooluniverse-rnaseq-deseq2 (RNA/miRNA-seq DE, correlation, PCA, clustering, dispersion), tooluniverse-gene-enrichment (GO/KEGG/Reactome/GSEA/pathway enrichment), tooluniverse-statistical-modeling (regression, ANOVA, ordinal/logistic, chi-square, correl
tooluniverse-drug-research
mims-harvard/tooluniverse
Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory work.
Popular education & science skills
teach
mattpocock/skills
Teach the user a new skill or concept, within this workspace.
scaffold-exercises
mattpocock/skills
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
caveman-learn
juliusbrussee/caveman
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
gsap-plugins
greensock/gsap-skills
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG drawing, or plugin registration.
teach-impeccable
pbakaus/impeccable
DEPRECATED: Use /impeccable teach instead. This command has been folded into the impeccable skill.