Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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).
.claude/skills/mkurman-jaspar-database/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 35% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -27% | 0% |
JASPAR is the definitive open-access database for Transcription Factor (TF) binding profiles, stored as Position Frequency Matrices (PFMs).
Use this skill to map abstract sequence motifs or genomic regions to specific biological regulators (e.g., "what TFs bind here?" or "what is the motif for CTCF?").
uv: Read the uv skill and follow its Setup instructions to ensureuv is installed and on PATH.
this skill directory then (1) prominently notify the user to check the terms at https://jaspar.elixir.no/ and https://jaspar.elixir.no/api/, then (2) create the file recording the notification text and timestamp.
CRITICAL: You MUST respect the JASPAR API Terms of Use by adhering to the following:
database rather than accessing the database directly. The scripts automatically enforce the required rate limit gracefully.
NOT exceed 100,000 bp (100kb). The jaspar_api.py script automatically chunks larger requests for you to bypass this limitation when querying larger regions.
get_tf_motif, get_tf_metadata, and get_tf_pwmrequire a stable JASPAR Matrix ID (e.g., MA0488.2). If a user provides a gene symbol (e.g., JUN), you must resolve it first using resolve_tf_id.
tax_id to ensure targetedsearches. Common IDs: Human=9606, Mouse=10090.
output.
Run all commands using the bundled Python script:
Maps a transcription factor name to a stable Matrix ID. Required step before fetching motifs if only a gene name is provided.
bashuv run scripts/jaspar_api.py resolve_tf_id --name "JUN" --tax-id 9606
Retrieves the raw Position Frequency Matrix for a specific TF. Supports --format flag.
bashuv run scripts/jaspar_api.py get_tf_motif --matrix-id "MA0488.2" uv run scripts/jaspar_api.py get_tf_motif --matrix-id "MA0488.2" --format meme
Retrieves TF class, family, and links to external databases (e.g., UniProt). Supports --format flag.
bashuv run scripts/jaspar_api.py get_tf_metadata --matrix-id "MA0488.2" uv run scripts/jaspar_api.py get_tf_metadata --matrix-id "MA0488.2" --format yaml
Fetches the PFM for a matrix and converts it to log-odds scores (PWM).
bashuv run scripts/jaspar_api.py get_tf_pwm --matrix-id "MA0488.2" uv run scripts/jaspar_api.py get_tf_pwm --matrix-id "MA0488.2" --pseudocount 0.1
Infers potential JASPAR matrix profiles from a raw transcription factor protein sequence.
bashuv run scripts/jaspar_api.py infer_from_sequence --sequence "QAQLLPSHHVG"
Retrieves metadata for a JASPAR TF Flexible Model. (Note: The JASPAR TFFM endpoints occasionally experience 500 Internal Server errors).
bashuv run scripts/jaspar_api.py get_tffm --tffm-id "TFFM0001.1"
The get_tf_motif and get_tf_metadata commands accept an optional --format flag. Supported formats: json (default), jsonp, jaspar, meme, transfac, pfm, yaml.
JUN) to get_tf_motif. You must passthe MA... Matrix ID.
--tax-id when resolving a TF name.availability (JASPAR shows potential binding, not actual tissue expression context).
binding.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 12,208 | 6,780 | -44% | 1 | 1 | 0% | 2,375 | 1,586 | -33% | 0 | 0 | — |
case-02 | fail→fail | 12,699 | 6,189 | -51% | 1 | 1 | 0% | 2,120 | 1,468 | -31% | 0 | 0 | — |
case-15 | fail→fail | 13,562 | 7,951 | -41% | 1 | 1 | 0% | 2,223 | 1,668 | -25% | 0 | 0 | — |
case-03 | fail→fail | 20,557 | 5,298 | -74% | 1 | 1 | 0% | 4,392 | 1,469 | -67% | 0 | 0 | — |
case-04 | fail→fail | 18,283 | 6,677 | -63% | 1 | 1 | 0% | 2,944 | 1,557 | -47% | 0 | 0 | — |
case-05 | fail→fail | 11,326 | 10,103 | -11% | 1 | 1 | 0% | 1,785 | 1,572 | -12% | 0 | 0 | — |
case-06 | fail→pass | 13,088 | 10,335 | -21% | 1 | 1 | 0% | 2,165 | 2,922 | +35% | 0 | 0 | — |
case-07 | pass→pass | 13,476 | 11,348 | -16% | 1 | 1 | 0% | 2,153 | 2,603 | +21% | 0 | 0 | — |
case-08 | pass→pass | 7,141 | 6,879 | -4% | 1 | 1 | 0% | 1,202 | 2,434 | +102% | 0 | 0 | — |
case-09 | fail→fail | 21,466 | 6,797 | -68% | 1 | 1 | 0% | 3,947 | 1,821 | -54% | 0 | 0 | — |
case-10 | fail→pass | 14,729 | 3,435 | -77% | 1 | 1 | 0% | 2,808 | 1,732 | -38% | 0 | 0 | — |
case-11 | fail→fail | 8,493 | 6,700 | -21% | 1 | 1 | 0% | 1,448 | 1,575 | +9% | 0 | 0 | — |
case-12 | fail→fail | 6,993 | 7,085 | +1% | 1 | 1 | 0% | 1,190 | 1,696 | +43% | 0 | 0 | — |
case-13 | fail→pass | 12,598 | 11,976 | -5% | 1 | 1 | 0% | 2,061 | 2,477 | +20% | 0 | 0 | — |
case-14 | pass→pass | 8,552 | 13,314 | +56% | 1 | 1 | 0% | 1,351 | 3,130 | +132% | 0 | 0 | — |
case-16 | fail→pass | 9,251 | 3,597 | -61% | 1 | 1 | 0% | 1,665 | 1,718 | +3% | 0 | 0 | — |
case-17 | pass→pass | 4,470 | 3,315 | -26% | 1 | 1 | 0% | 683 | 1,729 | +153% | 0 | 0 | — |
case-18 | pass→pass | 10,027 | 7,365 | -27% | 1 | 1 | 0% | 1,512 | 1,779 | +18% | 0 | 0 | — |
case-19 | fail→fail | 10,015 | 5,601 | -44% | 1 | 1 | 0% | 1,636 | 1,404 | -14% | 0 | 0 | — |
case-20 | pass→pass | 2,572 | 12,541 | +388% | 1 | 1 | 0% | 337 | 1,965 | +483% | 0 | 0 | — |
case-21 | pass→pass | 6,754 | 7,278 | +8% | 1 | 1 | 0% | 1,157 | 2,571 | +122% | 0 | 0 | — |
case-22 | fail→pass | 13,982 | 2,617 | -81% | 1 | 1 | 0% | 2,215 | 1,626 | -27% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 12 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +23 percentage points is the difference between those two pass rates over the 12 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.