tooluniverse-cell-line-profiling

Cancer cell-line selection and profiling for experimental model choice. Cross-references DepMap, Cellosaurus, COSMIC, PharmacoDB to deliver identity verification, mutation/CNV profile, gene dependencies, drug sensitivities, and druggable targets. Use to answer 'which cell line should I use for studying gene X?' or 'is this cell line a good model for cancer Y?'. Outputs ranked recommendations with rationale, growth characteristics, and known pitfalls.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

82%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.

The body is a highly actionable, well-sequenced reference with concrete tool calls, thresholds, and a validation checklist, scoring at the top of the actionability dimension. Its main weakness is mild verbosity from duplicated facts and bulk reference data inlined rather than split into separate files.

Suggestions

De-duplicate the HPA 10-supported-cell-line list (Phase 2B and Error Handling) and the Chronos < -0.5 threshold (Phase 3 prose and the bundled-script note) — state each once and reference back.

Move the large Phase 0 tool-parameter table and the Quick Reference cancer-type table into separate reference files under ./references/, leaving concise summaries inline with clear links, to improve progressive disclosure.

Add an explicit validate→fix→retry loop for the bundled depmap_gene_dependency.py invocation (e.g., on download/cache failure, fall back to cBioPortal + the Quick Reference table) to push workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	Mostly lean reference material and concrete tool calls with little conceptual padding, but the HPA 10-line list appears twice (Phase 2B and Error Handling) and Chronos < -0.5 thresholds are repeated, so minor trimming is possible.	4 / 5
Actionability	Fully executable guidance throughout — exact tool calls with real parameters, a concrete study ID (ccle_broad_2019), a runnable bundled script with copy-paste bash, numeric decision thresholds, and a scoring matrix — covering the common cases via the patterns and Quick Reference tables.	5 / 5
Workflow Clarity	A clear five-phase sequence with per-phase GOAL/OUTPUT, a Completeness Checklist validation checkpoint, and an Error Handling table; not a 5 because per-step validate→fix→retry feedback loops are less explicit than the anchor-5 example.	4 / 5
Progressive Disclosure	One well-signaled, real bundle reference (scripts/depmap_gene_dependency.py, which exists) at one level deep, but the large inlined tool-parameter table and cancer-type Quick Reference could arguably live in separate reference files — good structure with minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is specific, complete, and rich in natural trigger phrases, covering concrete capabilities and explicit use-when guidance with minimal conflict risk. Third-person imperative voice is used throughout, so no person-voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('identity verification, mutation/CNV profile, gene dependencies, drug sensitivities, and druggable targets') plus ranked recommendations with rationale, growth characteristics, and pitfalls — comprehensive coverage matching the 5-anchor.	5 / 5
Completeness	Explicitly answers both 'what' (selection/profiling, cross-referencing four named databases, specific output deliverables) and 'when' (the 'Use to answer...' clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Includes verbatim natural-language user questions ('which cell line should I use for studying gene X?', 'is this cell line a good model for cancer Y?') that users would actually say, plus the core domain terms.	5 / 5
Distinctiveness Conflict Risk	A clearly defined niche (cancer cell-line profiling) anchored by named databases and specific trigger questions, making overlap with unrelated skills minimal.	5 / 5
	Total	20 / 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: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-cell-line-profiling/SKILL.md
Commit: 22661b6

Reviewed: 3 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.