GitHub Deep Research
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al.
Install Boltz
$ npx skills add JimLiu/science-skills --skill boltz -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install JimLiu/science-skills boltz --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/boltz .claude/skills/boltz && rm -rf skills-srcUse ~/.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/
Install the "boltz" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/boltz into .claude/skills/boltz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boltz", 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 install https://github.com/JimLiu/science-skills/tree/main/skills/boltzType 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.
$ npx skills add JimLiu/science-skills --skill boltz -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install JimLiu/science-skills boltz --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/boltz .agents/skills/boltz && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "boltz" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/boltz into .agents/skills/boltz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boltz", 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.
$ npx skills add JimLiu/science-skills --skill boltz -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install JimLiu/science-skills boltz --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/boltz .cursor/skills/boltz && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "boltz" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/boltz into .cursor/skills/boltz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boltz", 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 https://github.com/JimLiu/science-skills.git --path skills/boltz--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add JimLiu/science-skills --skill boltz -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install JimLiu/science-skills boltz --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/boltz .gemini/skills/boltz && rm -rf skills-srcUse ~/.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/
Install the "boltz" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/boltz into .gemini/skills/boltz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boltz", 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.
$ gh skill install JimLiu/science-skills boltzInstalls 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).
$ npx skills add JimLiu/science-skills --skill boltz -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/boltz .github/skills/boltz && rm -rf skills-srcUse ~/.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/
Install the "boltz" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/boltz into .github/skills/boltz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boltz", 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.
$ npx skills add JimLiu/science-skills --skill boltz -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install JimLiu/science-skills boltz --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/JimLiu/science-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/boltz .opencode/skills/boltz && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "boltz" agent skill from https://github.com/JimLiu/science-skills/tree/main/skills/boltz into .opencode/skills/boltz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "boltz", 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
boltz- GitHub stars
- 227
- Used in
- 4 other repos
- Token cost
- ~1.3k tokens
- SKILL.md length
- 515 words
- Files
- 1
- Skills in repo
- 27
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al.
- Tasks that involve Drug discovery and cheminformatics
- SKILL.md covers Running it, Affinity head, msa: empty is an accuracy hit,… and Missing fast kernels are slow,…, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Boltz is an agent skill from JimLiu/science-skills. Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or CCD ligand, or to get an open-source AlphaFold3 alternative with optional binding-affinity prediction.
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 Drug discovery and cheminformatics. It works with GitHub. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Drug discovery and cheminformatics
Example prompts
- “/boltz”
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
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Boltz loads about 1.3k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 515 words of instructions outside code blocks.
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). 515 words, ~1,317 tokens.
Download SKILL.mdSave it as
.claude/skills/boltz/SKILL.md (or your agent's skills folder).- name
- boltz
- description
- Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or CCD ligand, or to get an open-source AlphaFold3 alternative with optional binding-affinity prediction.
- license
- Apache-2.0
- category
- biomodels
- requirements
- gpu
Boltz-2
Boltz-2 is the open-weights diffusion co-folder closest in surface to
AlphaFold3: a YAML describing protein, DNA, RNA, and ligand chains in, mmCIF
plus pTM/ipTM/pLDDT confidences out, with an optional small-molecule affinity
head. Among our four co-fold skills it is the default for binder-validation
campaigns — fully open MIT weights and the fastest sampler; pick chai1 when
you want a second independent model for consensus, openfold3 when AF3-faithful
settings matter, and esmfold2 when you can live without an MSA. Code and
weights are MIT (PyPI boltz, github.com/jwohlwend/boltz).
Running it
# complex.yaml
version: 1
sequences:
- protein:
id: A
sequence: MVTPEGNVSLVDESLLVGVTDEDRAVRS... # target
- protein:
id: B
sequence: AIQRTPKIQVYSRHPAENG... # binder
- ligand:
id: L
smiles: 'N[C@@H](Cc1ccc(O)cc1)C(=O)O' # or ccd: SAHboltz predict complex.yaml \
--use_msa_server --out_dir out/ --recycling_steps 3 --diffusion_samples 5Each protein chain needs an MSA; without one the run exits before the model
loads. --use_msa_server queries api.colabfold.com (expect a 30–90 s pause
per chain) and is the right default unless you already have an .a3m to name
under msa: in the YAML. Setting msa: empty forces single-sequence mode —
that is an accuracy sacrifice, not a speed or memory optimization, because the
MSA search runs on CPU before the GPU stage starts.
Per input the output lands at out/boltz_results_complex/predictions/complex/.
Read confidence_complex_model_0.json first: iptm > 0.5 is the community
pass line for an interface, complex_plddt > 0.7 for the fold itself, and
confidence_score is the weighted aggregate the structures are ranked by.
Structures themselves are complex_model_{0..N-1}.cif (or .pdb with
--output_format pdb).
Affinity head
Add a properties: block naming one ligand chain as the binder and Boltz-2
predicts protein–small-molecule binding affinity alongside the structure:
properties:
- affinity:
binder: L # the ligand chain id, not the proteinOutput gains affinity_complex.json next to the confidence file:
affinity_pred_value is log10(IC50 in μM) — lower is tighter (≈0 → 1 μM,
−3 → 1 nM); affinity_probability_binary is the 0–1 binder-vs-non-binder
score and is what to rank hits by. One affinity ligand per input; the binder
must be a ligand chain (no protein–protein affinity), and Boltz v2.2.x caps
affinity ligands at 128 atoms. FASTA inputs cannot request affinity at all.
Show full SKILL.md (221 more words)Show less
msa: empty is an accuracy hit, not a memory save
Single-sequence mode has been suggested elsewhere as a way to fit smaller GPUs.
It does not help: the MSA search is CPU-side, so --use_msa_server versus
msa: empty changes nothing about peak VRAM. If you OOM, lower
--diffusion_samples or --max_parallel_samples, or move to an 80 GB tier;
do not trade away the MSA for it.
Missing fast kernels are slow, not fatal
ImportError for cuequivariance_ops_torch or its libcue_ops.so means the
compiled triangle-kernel package is not on the loader path. --no_kernels
falls back to the reference PyTorch path — roughly 2× slower, numerically
identical, so it is the right unblock for a one-off and the wrong choice for a
campaign.
Errors worth recognizing
| You see | It means / do this |
|---|---|
Missing MSA's in input and --use_msa_server flag not set | A protein chain has no MSA — add --use_msa_server or set msa: to an .a3m path in the YAML. |
ImportError: ... cuequivariance_ops_torch / libcue_ops.so | Fast-kernel wheel not visible — add --no_kernels (slower, correct) or fix the env's LD_LIBRARY_PATH. |
KeyError: 'iptm' reading the confidence JSON | Single-chain input — ipTM is interface-only; read ptm instead. |
No affinity_*.json in output | Used FASTA input, or the YAML is missing the properties: block — see Affinity head above. |
Next: compute clash and interface metrics on passing complexes, or feed
them back to proteinmpnn for another design round.
© JimLiu, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/boltz 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
Boltz 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Boltz this skillJimLiu/science-skills | 227 | 4 repos | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| GitHub Deep Researchbytedance/deer-flow | 84k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Last30daysmvanhorn/last30days-skill | 64k | — | ~7.9k | Automated safety check: Notes | MIT | |
| MolecodeAtomFlow-AI/MoleCode | 306 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Read GitHubAgentTeam-TaichuAI/ScienceClaw | 671 | 2 repos | ~638 | Automated safety check: Pass | None | |
| Drug DiscoveryTommy-yw/RunbookHermes | 546 | 1 repos | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
Last30days
mvanhorn/last30days-skill
Research what people actually say about any topic in the last 30 days.
Molecode
AtomFlow-AI/MoleCode
A skill your agent uses for deterministic molecule understanding, graph-level editing, generation, and validation with MoleCode — an explicit Mermaid graph in which every atom and bond is a typed…
Read GitHub
AgentTeam-TaichuAI/ScienceClaw
Read and search GitHub repository documentation via gitmcp.io MCP service.
Drug Discovery
Tommy-yw/RunbookHermes
Pharmaceutical research assistant for drug discovery workflows.
DiffDock Molecular Docking
K-Dense-AI/scientific-agent-skills
Predicts how small molecules bind to a protein with DiffDock, covering batch docking, pose ranking by confidence and checks on the results; not for binding affinity.
More from JimLiu/science-skills
All 27 skills in this repoEsmfold2
JimLiu/science-skills
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.
Compute Env Setup
JimLiu/science-skills
Set up a compute environment on a remote provider so Claude Science jobs can run there.
Borzoi
JimLiu/science-skills
Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi.
Evo2
JimLiu/science-skills
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model.
Fair Esm2
JimLiu/science-skills
Embed proteins with Meta AI's ESM-2 (fair-esm package). An agent skill from JimLiu/science-skills.
Openfold3
JimLiu/science-skills
Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.
Related
Works with
Categories
Questions about Boltz
What does Boltz do?
Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. Boltz is an agent skill from JimLiu/science-skills. Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al.
When should I use Boltz?
Boltz fits situations like: tasks that involve Drug discovery and cheminformatics.
How do I install Boltz in Claude Code?
Run `npx skills add JimLiu/science-skills --skill boltz -a claude-code`. Or copy the skill folder (skills/boltz in JimLiu/science-skills) into .claude/skills/boltz in your project. Claude Code loads it when a task matches its description.
How do I install Boltz in Codex?
Run `npx skills add JimLiu/science-skills --skill boltz -a codex`. Or copy the skill folder (skills/boltz in JimLiu/science-skills) into .agents/skills/boltz in your project. Codex loads it when a task matches its description.
Can I use Boltz 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 boltz -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/boltz, .gemini/skills/boltz, .github/skills/boltz and .opencode/skills/boltz in your project.
What does Boltz need to run?
SKILL.md names no scripts, command-line tools or credentials: Boltz is instructions for the agent only.
Does Boltz access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Boltz 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 Boltz use?
Boltz 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 Boltz use?
About 1.3k tokens (SKILL.md is roughly 5.3k 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 Boltz?
Skills that share tags, products or a category with Boltz: GitHub Deep Research (bytedance/deer-flow, 84k stars), Last30days (mvanhorn/last30days-skill, 64k stars), Molecode (AtomFlow-AI/MoleCode, 306 stars) and Read GitHub (AgentTeam-TaichuAI/ScienceClaw, 671 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Boltz?
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.