tooluniverse-target-research

Gather comprehensive biological target intelligence from 9 parallel research paths covering protein info, structure, interactions, pathways, expression, variants, drug interactions, and literature. Features collision-aware searches, evidence grading (T1-T4), explicit Open Targets coverage, and mandatory completeness auditing. Use when users ask about drug targets, proteins, genes, or need target validation, druggability assessment, or comprehensive target profiling.

Quality

81%

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

62%

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

The body is exceptionally actionable and well-sequenced with strong validation/feedback loops, but it fails conciseness and progressive disclosure: it is a verbose monolith that explains domain concepts and inlines content that should be split into reference files. It reads as a reference manual rather than a lean SKILL.md overview.

Suggestions

Move the per-path Python implementations (Paths 0–8, GPCR detection, DisGeNET, Pharos, DepMap, InterProSCAN, BindingDB, PubChem) into separate files under references/ or scripts/ and replace them with brief overview pointers, keeping SKILL.md a lean hub.

Extract the full 14-section report template into a references/report_template.md and the tool-parameter reference table into references/tool_reference.md, linking to them from the body instead of inlining them.

Cut explanatory prose that assumes Claude lacks knowledge (e.g., 'Why HPA for Target Research', affinity interpretation tables, the GPCR '~35% of approved drugs' preamble) to reduce tokens while keeping the concrete parameters and fallback logic.

Dimension	Reasoning	Score
Conciseness	At ~1500 lines the body is a monolithic manual: it embeds full Python implementations for every research path, a large report template, repeated report-section markdown samples, and explanatory prose ('Why HPA for Target Research', affinity interpretation tables) that pads rather than earns its place, matching the verbose 'explains concepts / padded with unnecessary context' anchor.	1 / 3
Actionability	Highly actionable throughout — concrete executable Python, specific tool names with verified parameters, a parameter-correction table, fallback chains, and copy-paste-ready output format templates, matching the 'fully executable' top anchor.	3 / 3
Workflow Clarity	Clear sequencing with explicit checkpoints: Phase 0 verification first, identifier resolution, ordered paths with 'ALWAYS FIRST' gating, retry/backoff, fallback chains, and a mandatory completeness-audit checklist with feedback loops for batch operations, matching the top anchor.	3 / 3
Progressive Disclosure	No references/, scripts/, or assets/ bundle files exist and all per-path implementation details, the report template, and tool-reference tables are inlined into one ~1500-line file — a monolithic wall with content that should be separate and no one-level-deep references, matching the bottom anchor.	1 / 3
	Total	8 / 12 Passed

Description

100%

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 is specific, trigger-rich, complete, and distinctive — it names concrete capabilities, gives an explicit 'Use when...' clause, and uses consistent third-person voice. It is a strong, well-scoped description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across 9 named research paths — 'covering protein info, structure, interactions, pathways, expression, variants, drug interactions, and literature' plus 'evidence grading (T1-T4)' and 'mandatory completeness auditing', matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (the 9 research paths and features) and when with a clear 'Use when users ask about...' trigger clause, matching the top anchor.	3 / 3
Trigger Term Quality	Natural user phrasing is well covered — 'drug targets, proteins, genes', 'target validation', 'druggability assessment', 'target profiling' are terms a user would actually say, though it leans slightly technical.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — comprehensive biological target intelligence with evidence grading and Open Targets coverage — unlikely to trigger for the wrong skill; the body's 'When NOT to Use' section further reinforces distinctiveness.	3 / 3
	Total	12 / 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 (1511 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/tooluniverse-target-research/SKILL.md
Commit: df37802

Reviewed: 2 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.