database-lookup

Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. Use when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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-structured reference-catalog skill with a concrete, sequenced workflow, strong validation/feedback loops for batch database operations, and clean one-level-deep progressive disclosure to verified reference files. The only weakness is that some API examples use placeholders rather than fully executable snippets.

Suggestions

Replace the GraphQL placeholder bodies in the POST-Only APIs table with one complete, runnable query example (e.g., a minimal Open Targets GraphQL query) to lift actionability toward copy-paste ready.

Consider moving the full API-key registration table and the Available Databases catalog into a dedicated reference file, keeping SKILL.md as a tighter overview with links, to further trim token load at invocation time.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence throughout — no padding about what APIs or databases are — and every section (identifier formats, rate limits, POST-only table, API-key table) earns its place as reference material for a catalog skill.	5 / 5
Actionability	Concrete curl commands, specific endpoint and rate-limit values, and explicit identifier-conversion workflows give mostly executable guidance; the GraphQL placeholder bodies ('{"query":"..."}') and 'see reference file' deferrals are minor gaps rather than fully copy-paste-ready examples.	4 / 5
Workflow Clarity	A clear 7-step Core Workflow with explicit validation checkpoints ('count first', 'reconcile counts', 'fail visibly if incomplete', confirmation gates at 10,000 records/100 calls) plus a feedback-loop error-recovery sequence and a completeness checklist — appropriate for batch/database operations.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview that points to one-level-deep reference files (verified to exist) via markdown links and a full Available Databases table; content is appropriately split with easy navigation and no nested-reference chains.	5 / 5
	Total	19 / 20 Passed

Description

92%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 concise, third-person description that clearly states concrete capabilities and an explicit, well-scoped trigger condition. It distinguishes itself sharply from general-knowledge skills and is unlikely to fire for the wrong task.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Query documented public database APIs with explicit endpoints, filters, pagination, and provenance' — giving comprehensive, specific coverage of the retrieval actions rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Query documented public database APIs...') and when ('Use when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Covers several natural domain keywords ('scientific, regulatory, financial', 'database-backed fact', 'named source', 'public database APIs'), but lacks the synonym/file-extension breadth that the top anchor exemplifies.	4 / 5
Distinctiveness Conflict Risk	The 'retrieved reproducibly from a named source rather than inferred from general knowledge' framing carves out a clear niche with minimal overlap risk against general-knowledge or document skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/database-lookup/SKILL.md
Commit: 49c6e97

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.