CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

depmap

Retrieves and analyzes Cancer Dependency Map (DepMap) release data, including CRISPR Chronos gene effects, cancer model annotations, omics biomarkers, and PRISM drug sensitivity. Supports cancer-selective dependency, co-essentiality, and candidate synthetic-lethality analyses with release-aware identifiers and statistical checks.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 content is an exemplary operational skill: executable, helper-verified code with strong validation checkpoints and a final reporting checklist, plus well-signaled one-level references. The only refinement opportunities are minor — a few hedge sentences could be trimmed and some detail duplicated with the reference file could be consolidated to sharpen the split between the overview and the deep-dive material.

DimensionReasoningScore

Conciseness

The body is dense with non-inferable operational detail (endpoint contracts, md5 columns, identifier levels, per-file contracts) and avoids explaining anything Claude already knows, but a few hedge sentences and caveats repeated between the body and the reference file (e.g. catalogue verification warnings) could be trimmed, matching anchor 4 rather than the every-token-earns-its-place bar of 5.

4 / 5

Actionability

Code examples are fully executable and copy-paste ready, verified against the actual bundled helpers (fetch_catalogue, select_file, verify_md5, load_gene_effect, load_models, gene_profile, biomarker_scan, coessentiality all exist with matching signatures), and they cover the common analysis cases from release discovery through co-essentiality.

5 / 5

Workflow Clarity

The numbered sections 1-5 form a clear pipeline with explicit validation checkpoints (md5 verification, HTML-rejection, unique-index checks, empty-cohort ValueError) plus a 'Before reporting' verification checklist, matching the top anchor's 'explicit validation steps... checklists for complex processes'.

5 / 5

Progressive Disclosure

Structure is good with verified one-level-deep references (references/dependency_analysis.md and scripts/depmap_data.py both exist and are clearly signaled from the body), but the main body inlines substantial contract detail — notably PRISM specifics and mapping guidance — that overlaps with the reference file, a minor organization gap that falls short of the optimal split of anchor 5.

4 / 5

Total

18

/

20

Passed

Description

75%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, third-person, and highly distinctive, with excellent coverage of the skill's data types and analysis modes. Its main weaknesses are the absence of an explicit 'Use when...' trigger clause (capping completeness at 3) and a few missing natural synonyms users might say, such as 'cell line' or 'gene essentiality'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about DepMap, cancer cell line dependencies, CRISPR gene essentiality scores, or PRISM drug sensitivity data', to resolve the completeness gap.

Include natural user phrasings and synonyms — 'cell line', 'gene essentiality', 'dependency scores' — alongside the portal terminology to strengthen trigger term coverage.

Trim the trailing qualifier 'with release-aware identifiers and statistical checks', which adds padding without a concrete trigger or capability, keeping the description tight.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities — 'Retrieves and analyzes... CRISPR Chronos gene effects, cancer model annotations, omics biomarkers, and PRISM drug sensitivity' plus named analysis modes ('cancer-selective dependency, co-essentiality, and candidate synthetic-lethality analyses') — giving comprehensive, domain-complete coverage rather than the minor gaps of anchor 4.

5 / 5

Completeness

The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; 'when' is only weakly implied by the domain vocabulary.

3 / 5

Trigger Term Quality

Strong natural keywords are present ('DepMap', 'Cancer Dependency Map', 'CRISPR', 'PRISM', 'drug sensitivity', 'synthetic lethality', 'biomarkers'), but a few common user phrasings such as 'cell line', 'gene essentiality', and 'dependency scores' are missing, matching the 'good coverage, a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche with distinct triggers ('DepMap', 'Chronos', 'PRISM') that virtually no other skill would claim, and it uses correct third-person voice ('Retrieves', 'Supports'), so conflict risk is minimal.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

K-Dense-AI/scientific-agent-skills

Path

skills/depmap/SKILL.md

Revision

a25cf9e

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill