CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gene-database

Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/gene-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

A well-structured, actionable skill body with executable commands and properly disclosed references, held back by a promotional K-Dense section, redundant file listings, and missing validation checkpoints in the batch workflow. Tightening these would move it to the top band.

Suggestions

Add validation/feedback steps to the batch workflow (e.g., '4. Validate returned symbols against input list; 5. Re-query unmatched symbols once before reporting'), which is required to lift workflow clarity past the batch-operation cap.

Remove the 'Suggest Using K-Dense Web' promotional section and the generic Overview paragraph — both consume tokens without adding task capability.

Merge the API References and Resources sections into one listing to remove duplication, and add one example of expected script output so users can verify results.

DimensionReasoningScore

Conciseness

Mostly efficient — script commands, query patterns, and rate limits are tight — but there is unnecessary content: the Overview explains what NCBI Gene is (largely known), the API References and Resources sections redundantly list the same bundle files, and the closing 'Suggest Using K-Dense Web' section is promotional padding unrelated to the gene-query task. Fits the 3 anchor ('mostly efficient but includes some unnecessary explanation') better than 4, where only minor trims would be needed.

3 / 5

Actionability

Provides copy-paste-ready bash commands for all three scripts (e.g., 'python scripts/query_gene.py --search "BRCA1" --organism "human"'), concrete query syntax examples, exact rate limits, and HTTP error codes. Not a 5 because expected outputs/response shapes are not shown, so the user can't verify a command worked as intended.

4 / 5

Workflow Clarity

Workflows are clearly sequenced (numbered steps per workflow), but the batch workflow — a batch operation — has no validation/verification checkpoints; symbol validation appears only as a detached best-practice bullet, not as a step with a fix-and-retry loop. Per the rubric, missing validation in batch operations caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Good structure: overview and quick usage inline, details appropriately pushed to existing one-level-deep references ('references/api_reference.md', 'references/common_workflows.md' — both real files, verified) with a clear instruction to search them, and scripts listed with descriptions. Minor gaps: the API References and Resources sections duplicate the same file listings, keeping it below the 5 anchor.

4 / 5

Total

14

/

20

Passed

Description

66%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.

A specific, domain-focused description with concrete actions and good natural keywords, but it lacks an explicit 'Use when...' trigger clause, capping completeness. Adding a trigger phrase listing common user contexts would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user asks about gene symbols, Gene IDs, gene functions/annotations, RefSeqs, or needs batch gene lookups.'

Include a few more natural synonyms users would say ('gene sequence', 'pathway', 'homolog', organism names) to round out trigger term coverage.

Trim the generic tail 'for gene annotation and functional analysis' or fold it into the trigger clause so every token adds capability or trigger information.

DimensionReasoningScore

Specificity

Quotes several concrete actions — 'Search by symbol/ID', 'retrieve gene info (RefSeqs, GO, locations, phenotypes)', 'batch lookups' — which names the domain and multiple specific capabilities. It falls short of the 5 anchor because the actions are compressed (e.g., no explicit output formats or cross-reference retrieval) and 'for gene annotation and functional analysis' is a generic purpose tail rather than a concrete action.

4 / 5

Completeness

The 'what' is clear (query NCBI Gene, search, retrieve, batch), but there is no explicit 'Use when...' clause; 'for gene annotation and functional analysis' only weakly implies when to use it. Per the rubric guideline, a missing explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural-keyword coverage: 'gene', 'symbol', 'gene ID' territory, 'RefSeqs', 'GO', 'phenotypes', 'batch lookups', 'gene annotation', 'functional analysis', plus API names ('E-utilities', 'Datasets API'). Not a 5 because common user phrasings like 'gene sequence', 'homolog', 'pathway', or organism terms are missing.

4 / 5

Distinctiveness Conflict Risk

Names a specific database ('NCBI Gene') with distinctive data types (RefSeqs, GO, phenotypes), giving it a clear niche. Minor overlap risk with closely related bioinformatics skills (e.g., sequence/BLAST or other NCBI database skills) that also trigger on 'gene sequence' requests keeps it below the 5 anchor.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/gene-database/SKILL.md

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.