Source profileQuality 70/100

xuzhougeng/wisp-science/skills/borzoi/SKILL.md

borzoi

Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a variant on expression/accessibility, (2) Generating predicted coverage tracks for a locus, (3) Prioritising non-coding variants by predicted track delta.

Source repository stars
560
Declared platforms
0
Static risk flags
0
Last source update
2026-07-28
Source checked
2026-07-28
DecisionCompatibilityInstallWorkflowPermissionsEvidenceSource

Decision brief

What it does—and where it fits

Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi.

Best for

  • Use this skill when: (1) Scoring the regulatory effect of a variant on expression/accessibility, (2) Generating predicted coverage tracks for a locus, (3) Prioritising non-coding variants by predicted track delta.

Not for

  • Next: combine track deltas with evo2 likelihood deltas for a two-axis variant prioritisation.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/xuzhougeng/wisp-science --skill "skills/borzoi"
Safe inspection promptEditorial

Inspect the Agent Skill "borzoi" from https://github.com/xuzhougeng/wisp-science/blob/95d2c13d1665d46a388b5bdc998dcce0d5ec2eee/skills/borzoi/SKILL.md at commit 95d2c13d1665d46a388b5bdc998dcce0d5ec2eee. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    How to run

    python from borzoipytorch import Borzoi

    python from borzoipytorch import Borzoimodel = Borzoi.frompretrained("johahi/borzoi-replicate-0").cuda().eval()
  2. 02

    Prerequisites

    Review the “Prerequisites” section in the pinned source before continuing.

    Review and apply the “Prerequisites” source section.
  3. 03

    input: (batch, 4, 524288) one-hot DNA → output: (batch, tracks, 6144) bins

    json { "contextid": "ssh:gpu-box", "title": "Borzoi prediction for one locus", "command": "source /miniforge3/etc/profile.d/conda.sh && conda activate borzoi && HFHOME=/srv/model-cache python borzoirun.py --output /home/me/wisp-results/borzoi/tracks.npz", "timeoutsecs": 1800, "i…

    json { "contextid": "ssh:gpu-box", "title": "Borzoi prediction for one locus", "command": "source /miniforge3/etc/profile.d/conda.sh && conda activate borzoi && HFHOME=/srv/model-cache python borzoirun.py --output /home…Replace context, environment, cache, and output paths with discovered values. Call monitorrun once to wait, getrun once for a snapshot, or cancelrun to stop.Next: combine track deltas with evo2 likelihood deltas for a two-axis variant prioritisation.
  4. 04

    Output format

    (B, T, L) tensor — T tracks × L 32-bp bins. Track metadata (assay, biosample) is in borzoipytorch.pytorchborzoimodel.TRACKSDF (or model.tracksdf when using the AnnotatedBorzoi subclass) — the base Borzoi model has no targets attribute.

    (B, T, L) tensor — T tracks × L 32-bp bins. Track metadata (assay, biosample) is in borzoipytorch.pytorchborzoimodel.TRACKSDF (or model.tracksdf when using the AnnotatedBorzoi subclass) — the base Borzoi model has no ta…

Permission review

Static risk signals and limitations

No configured static risk pattern was detected

This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score70/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars560SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
xuzhougeng/wisp-science
Skill path
skills/borzoi/SKILL.md
Commit
95d2c13d1665d46a388b5bdc998dcce0d5ec2eee
License
AGPL-3.0
Collected
2026-07-28
Default branch
main
View the original SKILL.md

Borzoi — DNA → Functional Track Prediction

Prerequisites

RequirementMinimumRecommended
Python3.10+3.11
CUDA12.1+12.4+
GPU VRAM16 GB24 GB+

How to run

from borzoi_pytorch import Borzoi

model = Borzoi.from_pretrained("johahi/borzoi-replicate-0").cuda().eval()
# input: (batch, 4, 524288) one-hot DNA  → output: (batch, tracks, 6144) bins

Borzoi consumes ~524 kb one-hot windows and emits binned predictions across 7,611 human tracks (the separate 2,608-track mouse head is off by default; enable via enable_mouse_head=True and select with forward(..., is_human=False)). For variant scoring, run ref/alt windows centred on the variant and compare per-track output.

Output format

(B, T, L) tensor — T tracks × L 32-bp bins. Track metadata (assay, biosample) is in borzoi_pytorch.pytorch_borzoi_model.TRACKS_DF (or model.tracks_df when using the AnnotatedBorzoi subclass) — the base Borzoi model has no targets attribute.

Remote compute

Needs ≥24 GB VRAM and either pre-cached HF weights or egress to huggingface.co. Use a selected and probed ssh:<alias> context and load remote-compute-ssh. Confirm borzoi-pytorch and the cache location, then submit a self-contained runner with run_in_context:

{
  "context_id": "ssh:gpu-box",
  "title": "Borzoi prediction for one locus",
  "command": "source ~/miniforge3/etc/profile.d/conda.sh && conda activate borzoi && HF_HOME=/srv/model-cache python borzoi_run.py --output /home/me/wisp-results/borzoi/tracks.npz",
  "timeout_secs": 1800,
  "input_paths": ["runs/borzoi_run.py"],
  "output_specs": [
    {
      "glob": "ssh://gpu-box/home/me/wisp-results/borzoi/tracks.npz",
      "kind": "npz",
      "residency": "remote"
    }
  ]
}

Replace context, environment, cache, and output paths with discovered values. Call monitor_run once to wait, get_run once for a snapshot, or cancel_run to stop.

Troubleshooting

SymptomCauseFix
module has no __version__Package exposes no attrUse importlib.metadata.version("borzoi-pytorch")
Shape mismatch on inputWrong window lengthPad/crop to 524288 bp (fixed; not exposed as a model attribute)

Next: combine track deltas with evo2 likelihood deltas for a two-axis variant prioritisation.

Alternatives

Compare before choosing

Computed 10042,015

coreyhaines31/marketingskills

ab-testing

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program

2026-07-270 platforms
Computed 1007

event4u-app/agent-config

design-intelligence

Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.

2026-07-280 platforms
Computed 1007

event4u-app/agent-config

existing-ui-audit

Use BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for the ui directive set.

2026-07-280 platforms
Computed 9982,073

nexu-io/open-design

emil-design-eng

This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

2026-07-280 platforms