Agent skill

Evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model.

Apache-2.0Auto-check passedResearch & Science

Install Evo2

skills CLI

$ npx skills add JimLiu/science-skills --skill evo2 -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills evo2 --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evo2 .claude/skills/evo2 && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "evo2" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/evo2 into .claude/skills/evo2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evo2", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/JimLiu/science-skills/tree/main/skills/evo2

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add JimLiu/science-skills --skill evo2 -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills evo2 --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/evo2 .agents/skills/evo2 && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "evo2" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/evo2 into .agents/skills/evo2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evo2", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add JimLiu/science-skills --skill evo2 -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills evo2 --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/evo2 .cursor/skills/evo2 && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "evo2" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/evo2 into .cursor/skills/evo2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evo2", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/JimLiu/science-skills.git --path skills/evo2

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add JimLiu/science-skills --skill evo2 -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills evo2 --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/evo2 .gemini/skills/evo2 && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "evo2" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/evo2 into .gemini/skills/evo2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evo2", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install JimLiu/science-skills evo2

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add JimLiu/science-skills --skill evo2 -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/evo2 .github/skills/evo2 && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "evo2" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/evo2 into .github/skills/evo2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evo2", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add JimLiu/science-skills --skill evo2 -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install JimLiu/science-skills evo2 --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/evo2 .opencode/skills/evo2 && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "evo2" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/evo2 into .opencode/skills/evo2/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evo2", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: evo2
GitHub stars: 227
Used in: 4 other repos
Token cost: ~1.3k tokens
SKILL.md length: 338 words
Files: 1
Skills in repo: 27
Repo updated: Jul 1, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model.

Computing per-nucleotide
SKILL.md covers Prerequisites, How to run, Models and Output format, plus 4 more sections
Calls pip
Per-sequence likelihoods for variant effect scoring

What it does

Evo2 is an agent skill from JimLiu/science-skills. Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring regulatory or coding regions across species.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Bioinformatics and Embeddings. The licence is Apache-2.0.

When your agent uses it

Computing per-nucleotide
Per-sequence likelihoods for variant effect scoring
Embedding genomic windows for downstream classification
Generating DNA conditioned on a prefix

Example prompts

“/evo2”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit fb309c3. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Evo2 loads about 1.3k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 338 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~93
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from JimLiu/science-skills at commit fb309c3, republished under its Apache-2.0 licence (© JimLiu). 338 words, ~1,343 tokens.

Download SKILL.mdSave it as .claude/skills/evo2/SKILL.md (or your agent's skills folder).

name: evo2
description: Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring regulatory or coding regions across species.
license: Apache-2.0
category: biomodels
requirements: gpu
metadata.display-name: Evo 2

Evo 2 — DNA Language Model

Prerequisites

Requirement	Minimum	Recommended
Python	3.11	3.12 (<3.13)
CUDA	12.1+	12.4+
GPU VRAM	24 GB (7B bf16)	80 GB (40B)
RAM	32 GB	128 GB

How to run

Installation

bash

pip install evo2
# Weights pulled from Hugging Face on first model load.

Loading and scoring

python

from evo2 import Evo2

model = Evo2("evo2_7b")        # or "evo2_40b" — see model table
seqs = ["ATCG" * 50, "GGGCTTAA" * 25]
ll = model.score_sequences(seqs)   # → list[float], mean per-token log-likelihood
print(ll)

Generation

python

out = model.generate(
    prompt_seqs=["ATGAAAGCT"],
    n_tokens=256,
    temperature=0.7,
)
print(out.sequences[0])

Models

Name	Params	Context	VRAM (bf16)	Notes
`evo2_7b`	7 B	1 M nt	~22 GB	Default; fits on a single 24 GB+ GPU
`evo2_40b`	40 B	1 M nt	~78 GB	H100 80 GB or multi-GPU
`evo2_1b_base`	1 B	8 K nt	~6 GB	FP8 path requires sm_89+ (H100)

Output format

score_sequences returns a list[float] (or np.ndarray) of mean log-likelihoods, one per input sequence. More negative ⇒ less likely under the model. For variant effect, compute Δll = ll_alt - ll_ref over a fixed window.

generate returns a GenerationOutput with .sequences (list[str]), .logits (list[Tensor]), and .logprobs_mean (list[float]) — always populated, no flag required.

Decision tree

Need a DNA model?
│
├─ Per-base/per-sequence likelihood, generation → Evo 2 ✓
├─ Predict experimental tracks (expression, accessibility) → borzoi
└─ Protein, not DNA → fair-esm2 / esmfold2

Remote compute

7B/40B inference is GPU-bound (≥24 GB / 80 GB VRAM). Read compute_details({provider, mode:'read'}) for an environment with evo2 + flash-attn and a pre-cached HF weight mount, then submit:

python

c = host.compute.create(provider)
job = c.submit_job(
    intent="Evo2-7B score 200bp variant window — 1×GPU, ~2 min",
    inputs=[{"src": "score_evo2.py", "dst_filename": "score_evo2.py"}],
    command="python3 score_evo2.py",   # env selection is host-specific — see compute_details for your provider
    outputs=["scores.json"],
    timeout_seconds=1800,
)
print(job.job_id)   # cell ends here — kernel never blocks on compute

Then call the wait_for_notification brain-tool. When the compute_done notification arrives, act on its payload:

python

save_artifacts(payload["featured_files"])   # paths under hpc/<job_id>/

For the full result dict (output_files, remote_workdir, …), re-enter the kernel: c.attach_job(job_id).result() then c.close(). See the remote-compute-ssh / remote-compute-modal skill for the orchestration details.

Inside score_evo2.py, point HF_HOME at the provider's weight-cache mount (path is in compute_details) and set HF_HUB_OFFLINE=1 so the loader doesn't try to write refs/ into a read-only mount. Weight footprint: ~15 GB (7B), ~80 GB (40B).

Typical performance

Task	7B on H100	Notes
Model load (cached)	~5-7 min	First call hydrates weights
`score_sequences`, 200×200bp	~10-20 s	After load
`generate`, 1×512 nt	~15 s

Troubleshooting

Symptom	Cause	Fix
`Transformer Engine not installed`	No FP8 — falls back to bf16	Informational only on non-H100; ignore
OOM on load	40B on <80 GB GPU	Use `evo2_7b` or shard with `device_map`
HF tries to write `refs/main`	`HF_HOME` points at RO mount	Set `HF_HUB_OFFLINE=1`
`dtype mismatch` in `score_sequences`	Passing tensors not strings	Pass `list[str]`; the API tokenises for you

Next: pair with borzoi to predict track-level effects of the same variants.

Files

Just SKILL.md in skills/evo2 of JimLiu/science-skills.

Open the folder on GitHubat commit fb309c3

Used in 4 other repositories

We found 4 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in JimLiu/science-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Evo2 next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Evo2 compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Evo2 this skillJimLiu/science-skills	227	4 repos	~1.3k	Automated safety check: Pass	Apache-2.0	3 mo ago
Genimldavila7/claude-code-templates	32k	12 repos	~2.5k	Automated safety check: Pass	MIT	today
Celltype Specificity ProfilerClawBio/ClawBio	1.2k	—	~4.3k	Automated safety check: Pass	MIT	yesterday
Umap Tsne Analysisaipoch/medical-research-skills	2k	—	~2.7k	Automated safety check: Pass	MIT	20 days ago
Genimlaipoch/medical-research-skills	2k	—	~1.9k	Automated safety check: Pass	MIT	20 days ago
Sc ClusteringTianGzlab/OmicsClaw	161	—	~1.3k	Automated safety check: Pass	MIT	2 mo ago

Similar skills

Geniml
davila7/claude-code-templates
This skill should be used when working with genomic interval data (BED files) for machine learning tasks.
32k GitHub starsUsed in 12 repos~2.5k tokens
Research & ScienceAuto-check passed
Celltype Specificity Profiler
ClawBio/ClawBio
Given a gene and a single-cell atlas, compute how cell-type-specific its expression is — the tau specificity index, Sarle's expression bimodality coefficient, and the cell types that drive the…
1.2k GitHub stars~4.3k tokensUpdated yesterday
Research & ScienceAuto-check passed
Umap Tsne Analysis
aipoch/medical-research-skills
A skill your agent uses when performing sample-level dimensionality reduction and visualization on abundance or OTU-style matrices with a companion group file, generating UMAP and/or t-SNE…
2k GitHub stars~2.7k tokensUpdated 20 days ago
Research & ScienceAuto-check passed
Geniml
aipoch/medical-research-skills
Machine learning toolkit for genomic interval (BED) data; use it when you need to tokenize BED collections and train embeddings for regions/cells/labels, build consensus peak universes, or run…
2k GitHub stars~1.9k tokensUpdated 20 days ago
Research & ScienceAuto-check passed
Sc Clustering
TianGzlab/OmicsClaw
Load when building the neighbour graph, embedding (UMAP/t-SNE/diffmap/PHATE), and clustering (Leiden/Louvain) on a normalised single-cell AnnData.
161 GitHub stars~1.3k tokensUpdated 2 mo ago
Research & ScienceAuto-check passed
Sc Metacell
TianGzlab/OmicsClaw
Load when aggregating single cells into metacells (sample-aware coarse-grained pseudo-cells) on a normalised scRNA AnnData via SEACells or KMeans on a low-D embedding.
161 GitHub stars~1.6k tokensUpdated 2 mo ago
Research & ScienceAuto-check passed

Questions about Evo2

What does Evo2 do?

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Evo2 is an agent skill from JimLiu/science-skills. Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model.

When should I use Evo2?

Evo2 fits situations like: computing per-nucleotide; per-sequence likelihoods for variant effect scoring; embedding genomic windows for downstream classification; generating DNA conditioned on a prefix.

How do I install Evo2 in Claude Code?

Run `npx skills add JimLiu/science-skills --skill evo2 -a claude-code`. Or copy the skill folder (skills/evo2 in JimLiu/science-skills) into .claude/skills/evo2 in your project. Claude Code loads it when a task matches its description.

How do I install Evo2 in Codex?

Run `npx skills add JimLiu/science-skills --skill evo2 -a codex`. Or copy the skill folder (skills/evo2 in JimLiu/science-skills) into .agents/skills/evo2 in your project. Codex loads it when a task matches its description.

Can I use Evo2 in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JimLiu/science-skills --skill evo2 -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evo2, .gemini/skills/evo2, .github/skills/evo2 and .opencode/skills/evo2 in your project.

What does Evo2 need to run?

Going by SKILL.md and its folder, Evo2 needs the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Evo2 access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Evo2 safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Evo2 use?

Evo2 is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Evo2 use?

About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Evo2?

Skills that share tags, products or a category with Evo2: Geniml (davila7/claude-code-templates, 32k stars), Celltype Specificity Profiler (ClawBio/ClawBio, 1.2k stars), Umap Tsne Analysis (aipoch/medical-research-skills, 2k stars) and Geniml (aipoch/medical-research-skills, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evo2?

JimLiu (a GitHub user) maintains it in JimLiu/science-skills, which has 227 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on July 1, 2026.

Source: JimLiu/science-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Evo2

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Evo 2 — DNA Language Model

Prerequisites

How to run

Installation

Loading and scoring

Generation

Models

Output format

Decision tree

Remote compute

Typical performance

Troubleshooting

Files

Used in 4 other repositories

Compare with similar skills

Similar skills

More from JimLiu/science-skills

Related

Questions about Evo2