CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered orchestration skill: lean body, concrete commands and thresholds, a clearly gated four-phase workflow with validation feedback loops, and exemplary use of two one-level-deep reference files that actually contain the promised detail. The only deductions are a dated search-query example and a few steps stated at a high level without commands.

DimensionReasoningScore

Conciseness

The body is dense and lean — tables, bullets, and checklists with no explanations of concepts Claude already knows — but the dated search query "[domain] API 2025 OR 2026" embeds time-sensitive years outside any deprecated section, a trimmable instance that keeps it below the 'every token earns its place' anchor.

4 / 5

Actionability

Concrete executable guidance dominates: "python scripts/test_new_tools.py [api_name] -v", exact search query strings, a point-based prioritization table with thresholds, and file naming/branch conventions; a few steps remain high-level ("Load ToolUniverse, categorize tools by domain... Count per category" lacks the actual command), matching the 'mostly executable with minor gaps' anchor.

4 / 5

Workflow Clarity

The four phases are clearly sequenced with explicit gates ("Human approval gates after: discovery, creation, validation, and before PR"), a Quick Validation Checklist, and a feedback loop ("Fix failures with Skill(skill=\"devtu-fix-tool\")" plus a 100% pass requirement), matching the anchor for clear sequence with explicit validation, error recovery, and checklists; the only nit (the diagram labels five stages under 'Four-Phase Workflow') doesn't fit a lower anchor better.

5 / 5

Progressive Disclosure

The body is a true overview that delegates templates to references/tool-templates.md and full validation/integration detail to references/validation-guide.md — both real files, one level deep, clearly signaled inline and in a References section with descriptions — matching the ideal split-and-navigate anchor.

5 / 5

Total

18

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that concretely enumerates the full discover-create-validate-integrate pipeline with named tools and an explicit 'Use when...' trigger clause. Keyword coverage is good but misses some natural synonyms, and the breadth of actions creates minor overlap risk with the sibling devtu skills it references.

DimensionReasoningScore

Specificity

Quotes like "create ToolUniverse tools, validate them, and prepare integration PRs" and "automated tool creation using devtu-create-tool patterns, validation with devtu-fix-tool" list multiple concrete, named actions covering the entire pipeline in third person, matching the comprehensive 5 anchor rather than the 'minor gaps' of 4.

5 / 5

Completeness

It explicitly answers both questions: a detailed 'what' ("Performs gap analysis... web searches... automated tool creation... validation... git workflow management") and an explicit 'when' ("Use when expanding ToolUniverse coverage, adding new API integrations, or systematically discovering scientific resources"), matching the 5 anchor's concrete trigger phrases; score 4 would require a weaker 'when', which is not the case.

5 / 5

Trigger Term Quality

Triggers such as "adding new API integrations", "expanding ToolUniverse coverage", and "systematically discovering scientific resources" are natural phrasings, but common variations users might say (e.g., "bioinformatics APIs", "REST APIs", "public databases") are absent, fitting the 'good coverage; a few natural terms missing' anchor rather than 5.

4 / 5

Distinctiveness Conflict Risk

The ToolUniverse/life-science-API niche and devtu-* vocabulary make it mostly distinct, but it names actions (tool creation, validation, git workflow) that overlap with the closely related sibling skills it delegates to (devtu-create-tool, devtu-fix-tool, devtu-github), fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict 5 anchor.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.