drug-discovery-search

End-to-end drug discovery platform combining ChEMBL compounds, DrugBank, targets, and FDA labels. Natural language powered by Valyu.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pharma/drug-discovery-search/SKILL.md

Quality

Content

77%

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

The content is highly actionable with concrete commands and integration code, and the setup flow is a clear feedback loop. Its weaknesses are a marketing-fluff section that wastes tokens and a monolithic structure that references script files not present in the bundle.

Suggestions

Remove or shrink the 'Why This Skill is Powerful' marketing bullets to reclaim tokens without losing actionable information.

Move the Python/TypeScript integration sections into a separate reference file (e.g., INTEGRATION.md) and link to it from the body to improve progressive disclosure.

Ensure the referenced scripts/ (search, search.mjs) actually ship in the bundle, or replace the path-resolution workaround with a stable relative path.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient executable guidance, but the 'Why This Skill is Powerful' section is marketing fluff ('No API Parameter Parsing', 'Semantic Search', 'Comprehensive Coverage') that pads tokens without aiding execution, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready commands ("scripts/search \"JAK2 inhibitors\" 20"), jq pipelines, a script-path resolution snippet, and complete Python/TypeScript integration code that are executable and specific.	3 / 3
Workflow Clarity	The single-action search workflow is unambiguous, and the 'API Key Setup Flow' is a clearly sequenced feedback loop (detect setup_required -> ask user -> run setup -> retry), with error handling and exit codes documented.	3 / 3
Progressive Disclosure	Sections are reasonably organized, but everything is inline in one ~200-line file (jq recipes, use cases, Python/TS integration, architecture) that could be split out, and the referenced scripts/ files do not actually exist in the bundle, so navigation is not one-level-deep and verified.	2 / 3
	Total	10 / 12 Passed

Description

57%

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

The description conveys a clear, distinctive niche and names concrete data sources, but it stops short of listing multiple specific actions and omits any explicit 'when to use' trigger guidance. It is written in correct third-person voice with no over-claims.

Suggestions

Add an explicit 'Use when...' clause listing natural trigger phrases (e.g., 'Use when searching drug compounds, validating targets, or researching FDA drug labels').

Expand the action list beyond 'combining' to concrete verbs like 'search, retrieve, and compare compounds, targets, and drug labels'.

Include common user phrasings such as 'drug search', 'compound lookup', or 'drug label lookup' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete data sources ("combining ChEMBL compounds, DrugBank, targets, and FDA labels", "Natural language powered by Valyu") but lists only combining/searching rather than multiple distinct concrete actions, so it is not comprehensive.	2 / 3
Completeness	It clearly states what the skill does but has no "Use when..." clause or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Contains relevant domain keywords users might say ("ChEMBL compounds", "DrugBank", "FDA labels", "Natural language") but misses common variations and phrasings a user would naturally request, keeping it just short of strong coverage.	2 / 3
Distinctiveness Conflict Risk	The niche is clear and specific (simultaneous search across ChEMBL, DrugBank, FDA labels, and targets via Valyu), making it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 10 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/drug-discovery-search/SKILL.md
Commit: df37802

Reviewed: about 1 hour 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.