CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gtex-database

Use when you want to retrieve quantitative RNA expression data and variant eQTL information from the GTEx (Genotype-Tissue Expression) Project across 54 non-diseased tissue sites.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/gtex_database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable — all five subcommands are documented with verified, executable examples matching the actual CLI — with clear sequencing of prerequisites and workflows. Its weaknesses are redundancy (the capability-to-command mapping appears three times) and a couple of missed validation steps and an unreferenced bundle file (citation.bib).

Suggestions

Merge "When to Use" and "Command Selection Guide" into one mapping of user intent to subcommand, and drop the duplicated Quick Start example from the Commands section.

Reference references/citation.bib from the body (e.g. a short "Citation" section) so the bundled file is discoverable and GTEx attribution is surfaced.

Add a validation step to the workflow: check that Step 1's output contains a valid GENCODE ID (and what to do on failure or multiple matches) before running Step 2.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no padding about concepts Claude already knows, but it is noticeably redundant: the "When to Use" bullet list, the "Command Selection Guide", and each "Commands" subsection restate the same capability-to-command mapping three times; the intro paragraph repeats the frontmatter description; and the Quick Start `resolve-gencode-id TNF` example reappears verbatim in Commands. This matches 'Mostly efficient but... could be tightened' — not 4 because the triplicated mapping is more than a minor trim.

3 / 5

Actionability

Every command is fully executable copy-paste-ready `uv run scripts/gtex_cli.py ...` lines with real argument values (e.g. `get-eqtls-in-region chr17 7000000 7100000 "Esophagus - Muscularis"`), and the documented subcommands, positional args, flags, and defaults were verified to match the actual CLI in scripts/gtex_cli.py. The common cases (resolve ID, get expression, top tissues, gene/region eQTLs) are each covered by a concrete example.

5 / 5

Workflow Clarity

Multi-step processes are clearly sequenced: numbered Prerequisites (uv setup, license notification gate) and a Typical Workflow showing the symbol-to-GENCODE-ID-to-query dependency chain with Step 1/Step 2. Not 5 because there are no validation or error-recovery checkpoints (e.g. what to do if symbol resolution fails or returns an empty result before proceeding to Step 2); not 3 because the operations are read-only API queries, the sequence is explicit, and the licensing checkpoint does gate execution.

4 / 5

Progressive Disclosure

Good structure with well-organized sections (Prerequisites, When to Use, Commands, Workflows) and the bundled script scripts/gtex_cli.py is consistently and correctly referenced by every command. Minor gaps keep it from 5: the bundled references/citation.bib is never mentioned or linked anywhere in the body (an orphaned bundle file), and the triplicated command mapping is inline content that could be consolidated; not 3 because navigation is easy, references that exist are clearly signaled, and nothing is nested or buried.

4 / 5

Total

16

/

20

Passed

Description

68%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 has a clear niche with strong distinctiveness and explicit what/when structure, but it is thin on concrete capabilities and uses second-person voice ("Use when you want to..."), which costs it specificity. Rewriting in third person with a fuller action list and genuine trigger contexts would lift it substantially.

Suggestions

Rewrite in third-person voice, e.g. "Retrieves median TPM RNA expression and significant eQTLs for genes and variants across 54 normal GTEx tissues; maps gene symbols to GENCODE IDs and finds top-expressed tissues."

Add concrete trigger phrases instead of restating the capability: "Use when the user asks about gene expression levels, TPM, eQTLs, or tissue-specific expression in normal (non-diseased) tissues, or mentions GTEx."

Include common synonyms such as "gene expression", "transcriptomics", and "TPM" so natural user phrasings match.

DimensionReasoningScore

Specificity

The description names the domain ("GTEx (Genotype-Tissue Expression) Project", "RNA expression data", "variant eQTL information") with only one generic action verb ("retrieve") covering two data types, matching the anchor 'Names the domain but actions are minimal or generic' — base 3, reduced by 1 because the capability is framed in second person ("Use when you want to retrieve...") instead of third-person voice per the judging guideline. It is not a 4 because there is no enumeration of several concrete operations (no mention of tissue-ranking, region queries, or ID resolution), and the voice penalty rules out staying at 3.

2 / 5

Completeness

Both elements are present — what ("retrieve quantitative RNA expression data and variant eQTL information from the GTEx... Project") and an explicit when ("Use when you want to..."). Not 5 because the 'when' clause merely restates the 'what' ("when you want to retrieve" the very things it does) rather than naming concrete trigger contexts or user situations; not 3 because the 'when' is explicit, not merely implied.

4 / 5

Trigger Term Quality

Includes natural terms users would say — "GTEx", "eQTL", "RNA expression", "tissue" — giving good keyword coverage. Not 5 because common synonyms and specifics are missing: users would say "gene expression", "TPM", "expression Quantitative Trait Loci", or "transcriptomics"; not 3 because the core GTEx/eQTL vocabulary is exactly what a user with this need would mention.

4 / 5

Distinctiveness Conflict Risk

"GTEx" and "eQTL" are highly specific niche triggers that no other generic expression or genomics skill would claim, giving a clear niche with minimal conflict risk. The 4 anchor's 'minor overlap risk with closely related skills' does not apply — no plausible competing skill shares these triggers.

5 / 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

google-deepmind/science-skills

Path

skills/gtex_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.