CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

jaspar-database

Query the JASPAR database for Transcription Factor (TF) binding profiles. Use when retrieving Position Frequency Matrices (PFMs) or Position Weight Matrices (PWMs) for specific TFs, resolving gene symbols to JASPAR Matrix IDs, or getting TF metadata. Supports multiple output formats (MEME, TRANSFAC, PFM, JASPAR, YAML).

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

Highly actionable content with executable commands for every subcommand, clear core rules, and useful anti-patterns. Weaknesses are minor: a slightly redundant intro, no explicit validation/feedback loops in the query workflow, and an unreferenced bundled citation file.

Suggestions

Trim the opening background paragraph ('JASPAR is the definitive open-access database...') to a single line or fold it into the usage statement to save tokens.

Add an explicit validation step to the workflow, e.g., verify the resolved Matrix ID exists (and retry with a different tax_id or name variant on failure) before calling get_tf_motif.

Reference the bundled references/citation.bib in the body (e.g., a 'Citation' section) so the reference file is discoverable and its purpose is clear.

DimensionReasoningScore

Conciseness

The body is largely lean and operational, but the opening background sentence 'JASPAR is the definitive open-access database for Transcription Factor (TF) binding profiles' plus the following framing paragraph restate context Claude largely already knows and could be trimmed.

4 / 5

Actionability

All six subcommands are given as copy-paste-ready 'uv run scripts/jaspar_api.py ...' invocations with concrete example arguments, and supported output formats and constraints (100kb window, tax_id 9606) are explicitly enumerated.

5 / 5

Workflow Clarity

The critical resolve-then-fetch sequence is explicit ('If a user provides a gene symbol ... you must resolve it first using resolve_tf_id') and prerequisites are a numbered two-step process, but there are no explicit output-validation or error-recovery checkpoints beyond the TFFM 500-error aside.

4 / 5

Progressive Disclosure

The body is well-sectioned and the bundled script (scripts/jaspar_api.py) is real and consistently referenced, but the bundle's references/citation.bib is never mentioned or linked anywhere in the body, leaving a navigation gap for an existing reference file.

4 / 5

Total

17

/

20

Passed

Description

87%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 strong description with an explicit 'Use when' trigger clause, concrete capabilities, and a clearly distinct niche. Its only weaknesses are a missing 'motif' synonym in the triggers and incomplete coverage of the tool's full capability set (sequence inference, TFFM).

DimensionReasoningScore

Specificity

Lists several concrete actions ('retrieving Position Frequency Matrices (PFMs) or Position Weight Matrices (PWMs)', 'resolving gene symbols to JASPAR Matrix IDs', 'getting TF metadata') but omits two tool capabilities shown in the body (sequence inference and TFFM retrieval), leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' ('Query the JASPAR database for Transcription Factor (TF) binding profiles') and 'when' with three concrete trigger clauses introduced by 'Use when', matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Good natural keyword coverage (JASPAR, Transcription Factor/TF, binding profiles, PFM, PWM, gene symbols, MEME, TRANSFAC, YAML), but it misses the most natural user phrasing 'motif' and concrete gene-name triggers like 'CTCF' that the body itself identifies as core use cases.

4 / 5

Distinctiveness Conflict Risk

The JASPAR/TF-binding-profile niche with domain-specific triggers (Matrix IDs, PFMs, PWMs, MEME, TRANSFAC) is highly distinct from any generic skill, giving minimal conflict risk.

5 / 5

Total

18

/

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/jaspar_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.