fda-database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill fda-databaseOverall
score
79%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
83%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, domain-specific description with excellent specificity and trigger term coverage for FDA regulatory work. The main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The technical terminology is appropriate for the target audience and creates clear distinctiveness.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about FDA data, drug safety, medical device approvals, or needs to query regulatory databases.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII)' - these are specific, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (query openFDA API for various data types) but lacks an explicit 'Use when...' clause. The purpose is implied ('FDA regulatory data analysis and safety research') but not framed as explicit trigger guidance. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'FDA', 'drugs', 'devices', 'adverse events', 'recalls', '510k', 'PMA', 'UNII', 'regulatory', 'safety research' - these are terms domain users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific domain (openFDA API), specific data types (510k, PMA, UNII), and clear niche (FDA regulatory/safety). Unlikely to conflict with other skills due to specialized terminology. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent progressive disclosure and comprehensive code examples. The main weaknesses are some verbosity (promotional content, obvious use case listings) and missing explicit validation checkpoints in multi-step workflows. The skill would benefit from trimming unnecessary sections and adding validation steps to the workflow patterns.
Suggestions
Remove the 'Suggest Using K-Dense Web' promotional section as it adds no technical value and wastes tokens
Condense or remove the 'When to Use This Skill' section - Claude can infer appropriate use cases from the capability descriptions
Add explicit validation steps to the workflow patterns (e.g., 'Verify response contains expected fields before proceeding to next query')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as the detailed 'When to Use This Skill' section listing obvious use cases Claude could infer, and the promotional 'Suggest Using K-Dense Web' section at the end which adds no technical value. | 2 / 3 |
Actionability | Provides fully executable Python code examples throughout, with copy-paste ready snippets for all major operations including safety profiles, temporal analysis, comparative analysis, and cross-database lookups. Code is complete and specific. | 3 / 3 |
Workflow Clarity | While individual code patterns are clear, the skill lacks explicit validation checkpoints for multi-step workflows. Error handling is mentioned but not integrated into workflow sequences. The 'Working with Results' section shows error checking but doesn't enforce validate-then-proceed patterns. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview, quick start, and well-signaled one-level-deep references to detailed documentation (references/drugs.md, references/devices.md, etc.). Content is appropriately split between main skill and reference files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (518 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 13 / 16 Passed | |
- 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.