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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

87%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-organized skill body with copy-paste commands and a clean single-script progressive-disclosure structure. Its main gap is the absence of explicit validation/error-recovery checkpoints in the resolve-then-fetch workflow, including around the noted TFFM 500 errors.

Suggestions

Add an explicit validation step after resolve_tf_id (e.g., confirm the returned MA... ID is non-empty and species-correct before passing it to get_tf_motif), with a retry/fix loop.

Provide concrete error-handling guidance for the TFFM 500 errors already flagged in the note (e.g., retry once, then fall back to get_tf_metadata), turning the warning into an actionable workflow.

Reference the bundled references/citation.bib from the body (or remove it) so every bundle file has a clear, signaled navigation entry.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-centric with copy-paste examples for every operation; the brief intro and 'map abstract sequence motifs to biological regulators' framing are short and genuinely useful for orientation rather than padded explanation, matching the score-3 anchor for lean and efficient content where every token earns its place.	3 / 3
Actionability	Every one of the six operations ships a fully executable 'uv run scripts/jaspar_api.py ...' invocation with concrete flags and example arguments, and output formats are enumerated, matching the score-3 anchor for fully executable, copy-paste-ready commands.	3 / 3
Workflow Clarity	Prerequisites and core rules sequence the resolve-then-fetch flow and flag mandatory steps ('you must resolve it first using resolve_tf_id'), but there are no explicit validation checkpoints or error-recovery feedback loops (e.g., confirm a resolved matrix ID, handle API/TFFM 500 errors), which caps the score at 2 per the rubric's validation-gap rule.	2 / 3
Progressive Disclosure	The body is a well-organized single overview (Prerequisites, Core Rules, six Utility Scripts, Output Formats, Anti-Patterns) with the bundled scripts/jaspar_api.py correctly signaled one level deep via 'uv run scripts/jaspar_api.py'; content is appropriately split between inline commands and the one script, matching the score-3 anchor for a clear overview with well-signaled one-level-deep references.	3 / 3
	Total	11 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 explicit trigger guidance, concrete enumerated actions, and a clearly distinct domain niche. Its main weakness is jargon-heavy trigger language that underuses the natural phrasings a user would actually say.

Suggestions

Add common layperson trigger phrasings alongside the technical terms, e.g. 'Use when a user asks for the binding motif of a transcription factor like CTCF, or what TFs bind a given sequence.'

Consider mentioning the protein-sequence inference and TFFM capabilities in the description for fuller trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'retrieving Position Frequency Matrices (PFMs) or Position Weight Matrices (PWMs)', 'resolving gene symbols to JASPAR Matrix IDs', 'getting TF metadata' — plus enumerated output formats, matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	An explicit 'Use when' clause answers both what (query JASPAR for TF binding profiles) and when (retrieving PFMs/PWMs, resolving gene symbols, getting metadata), matching the score-3 anchor for clearly answering both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Includes relevant domain keywords ('Use when retrieving PFMs or PWMs', 'TF binding profiles') but leans heavily on technical jargon (PFM/PWM/matrix IDs) and omits common layperson phrasings a user would naturally say like 'motif for CTCF', matching the score-2 anchor of some keywords but missing common variations.	2 / 3
Distinctiveness Conflict Risk	Targets a clearly specific niche — the named JASPAR database and TF binding profiles — with domain-distinct triggers unlikely to overlap with other skills, matching the score-3 anchor for a clear niche with distinct triggers.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: google-deepmind/science-skills
Path: skills/jaspar_database/SKILL.md
Commit: 0b42509

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.