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

85%

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

85%

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

A well-engineered, highly actionable reference skill with a clear sequenced workflow and proper progressive disclosure into per-database files. Its main weakness is length and duplication between the selection guide and the available-databases catalog.

Suggestions

Collapse or cross-reference the "Available Databases" table against the Database Selection Guide to remove the large duplication and reclaim tokens.

Consider moving the long API-key and identifier-format tables into a shared reference file, keeping SKILL.md as a tighter overview.

Dimension	Reasoning	Score
Conciseness	Most content is dense operational reference rather than concepts Claude already knows, but the ~530-line body is large and the "Available Databases" table substantially duplicates the Database Selection Guide, so it could be tightened.	2 / 3
Actionability	Concrete curl examples, exact env-variable names and registration URLs, identifier formats with worked examples, pagination parameter lists, and a copy-paste output template make the guidance fully executable.	3 / 3
Workflow Clarity	The 7-step Core Workflow is clearly sequenced with explicit validation/count-reconciliation checkpoints, a "fail visibly" rule, confirmation thresholds (10,000 records / 100 calls), and a dedicated error-recovery loop.	3 / 3
Progressive Disclosure	The body is an overview that signals one-level-deep references to per-database files in references/ (verified to exist, e.g. pubchem.md, retrieval-contract.md) with clear navigation tables, rather than nesting references deeper.	3 / 3
	Total	11 / 12 Passed

Description

85%

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: concrete actions, explicit "Use when" trigger, and a clear niche. The only weak spot is trigger phrasing that is somewhat technical rather than the natural terms a user would say.

Suggestions

Add natural trigger terms users would actually say, e.g. "look up", "fetch from", or name representative databases (PubChem, FDA, FRED) alongside the domain categories.

Soften the technical clause "retrieved reproducibly from a named source rather than inferred from general knowledge" so a non-expert user's phrasing would still match.

Dimension	Reasoning	Score
Specificity	"Query documented public database APIs with explicit endpoints, filters, pagination, and provenance" lists several concrete actions (endpoints, filters, pagination, provenance), matching the multiple-specific-actions anchor.	3 / 3
Completeness	It states what the skill does (query APIs for endpoints/filters/pagination/provenance) and gives an explicit "Use when" trigger clause, satisfying both the what and the when.	3 / 3
Trigger Term Quality	Domain keywords like "scientific, regulatory, financial" are natural, but the trigger phrasing "database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge" leans technical and omits common variations users would actually say (e.g. "look up", specific database names).	2 / 3
Distinctiveness Conflict Risk	The reproducible-from-a-named-source framing carves a clear niche distinct from general knowledge or web search, making false triggers unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (534 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/database-lookup/SKILL.md
Commit: 757b63b

Reviewed: about 12 hours 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.