CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gget

Unified CLI/Python interface for querying genomic, proteomic, structure, and expression data across 20+ bioinformatics databases; use when you need fast, scriptable retrieval by gene/protein IDs or keywords.

Quality

75%

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 ./scientific-skills/Evidence Insight/gget/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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, appropriately disclosed skill body with executable examples and a genuine one-level-deep reference file. The main improvements are removing the duplicated module lists between Key Features and Implementation Details and making the AlphaFold section concrete.

Suggestions

Merge 'Key Features' with the 'Supported modules/functions' list — they enumerate the same six modules twice, wasting tokens.

Replace the vague AlphaFold note ('requires additional setup depending on the environment') with the actual setup steps or a pointer to the specific section of module_reference.md.

Use a real, complete sequence (or a documented way to fetch one) in the alphafold example instead of the "MKWMFK..." placeholder, and add one expression/enrichment example command.

DimensionReasoningScore

Conciseness

The body is mostly lean with no tutorials on concepts Claude already knows, but 'Key Features' and 'Implementation Details → Supported modules' list the same six modules (search, info, seq, structure, expression, enrichment) twice, and 'Notes on AlphaFold' is vague filler ("requires additional setup depending on the environment (e.g., model/data availability)"). This matches anchor 3 ('mostly efficient but... could be tightened') better than anchor 4, since the duplication is section-level, not a minor trim.

3 / 5

Actionability

Four concrete, runnable commands (e.g., `python scripts/wrapper.py search --keywords "insulin" --species "human"`) plus an install command give mostly executable guidance. Minor gaps keep it below anchor 5: the alphafold example uses a placeholder sequence (`--sequence "MKWMFK..."`), and structure/expression/enrichment subcommands have no inline examples (their parameters live in references/module_reference.md).

4 / 5

Workflow Clarity

Usage is unambiguous (install → run wrapper subcommand) with numbered example scenarios, and the operations are read-only queries so the destructive/batch validation cap does not apply. However, there is no error-handling guidance for API failures and the AlphaFold setup note gives no concrete steps, fitting anchor 4 ('clear sequence... minor validation gaps') rather than anchor 5's explicit checkpoints and feedback loops.

4 / 5

Progressive Disclosure

The body is a clean overview that delegates module-level documentation to references/module_reference.md (verified to exist, one level deep — it references no further files), clearly signaled via 'See references/module_reference.md for detailed module-level documentation and parameters', with the wrapper script present in scripts/. This matches anchor 5 ('clear overview with well-signaled one-level-deep references; content appropriately split').

5 / 5

Total

16

/

20

Passed

Description

70%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 solid description with a clear niche, explicit when-guidance, and good natural trigger terms. Its weaknesses are the second-person voice (per rubric penalty), action enumeration that stays at the domain level, and omission of the specific database names users would most likely mention.

Suggestions

Rewrite in third person to avoid the voice penalty, e.g., 'Provides a unified CLI/Python interface for querying...; use when fast, scriptable retrieval by gene/protein IDs or keywords is needed.'

Name the concrete actions and databases users would say — Ensembl, UniProt, NCBI, 'fetch sequences', 'AlphaFold structure prediction', 'enrichment analysis' — to raise specificity and trigger coverage.

Broaden the when-clause beyond retrieval to cover search, expression-query, and enrichment scenarios.

DimensionReasoningScore

Specificity

The description names four data domains ("genomic, proteomic, structure, and expression data") and concrete retrieval modes ("retrieval by gene/protein IDs or keywords"), which sits near anchor 4, but the second-person phrasing "use when you need" triggers the rubric's 1-point voice penalty, lowering it to 3. It also enumerates domains rather than distinct actions (search, fetch sequences, predict structures), which anchor 3 ('names domain and 1-2 concrete actions') fits better than anchor 5's multi-action comprehensiveness.

3 / 5

Completeness

Both parts are present: a clear 'what' ("Unified CLI/Python interface for querying... 20+ bioinformatics databases") and an explicit 'when' ("use when you need fast, scriptable retrieval by gene/protein IDs or keywords"). The when-clause covers only retrieval scenarios and omits search, expression, and enrichment use cases, so it matches anchor 4 ('when' could be more explicit or specific) rather than anchor 5's concrete multi-trigger phrasing.

4 / 5

Trigger Term Quality

Good natural-term coverage: "gene/protein IDs", "keywords", "genomic", "proteomic", "expression data", "bioinformatics databases" are phrases users would say. A few commonly used terms are missing — the database names (Ensembl, UniProt, NCBI) appear only in the body, not the description — so it does not reach anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The bioinformatics database-retrieval niche ("20+ bioinformatics databases", "gene/protein IDs") is distinct with targeted triggers. Minor overlap risk remains with dedicated structure-prediction or expression-analysis skills, placing it at anchor 4 ('mostly distinct; minor overlap risk') rather than anchor 5's minimal-conflict profile.

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Evidence Insight/gget/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.