Rfdiffusion
PKU-YuanGroup/OpenAI4S
Generate de novo protein backbones with RFdiffusion for protein-target binders, hotspot-conditioned interfaces, motif scaffolding, partial diffusion, or symmetric assemblies.
End-to-end Proteina-Complexa design pipeline driver. An agent skill from NVIDIA-BioNeMo/bionemo-agent-toolkit.
Install Complexa Design
$ npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA-BioNeMo/bionemo-agent-toolkit complexa-design --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/NVIDIA-BioNeMo/bionemo-agent-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bionemo-agent-toolkit/skills/complexa-design .claude/skills/complexa-design && 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 "complexa-design" agent skill from https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/skills/bionemo-agent-toolkit/skills/complexa-design into .claude/skills/complexa-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "complexa-design", 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/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/skills/bionemo-agent-toolkit/skills/complexa-designType 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 NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA-BioNeMo/bionemo-agent-toolkit complexa-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/bionemo-agent-toolkit/skills/complexa-design .agents/skills/complexa-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "complexa-design" agent skill from https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/skills/bionemo-agent-toolkit/skills/complexa-design into .agents/skills/complexa-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "complexa-design", 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 NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA-BioNeMo/bionemo-agent-toolkit complexa-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/bionemo-agent-toolkit/skills/complexa-design .cursor/skills/complexa-design && 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 "complexa-design" agent skill from https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/skills/bionemo-agent-toolkit/skills/complexa-design into .cursor/skills/complexa-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "complexa-design", 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/NVIDIA-BioNeMo/bionemo-agent-toolkit.git --path skills/bionemo-agent-toolkit/skills/complexa-design--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 NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA-BioNeMo/bionemo-agent-toolkit complexa-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/bionemo-agent-toolkit/skills/complexa-design .gemini/skills/complexa-design && 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 "complexa-design" agent skill from https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/skills/bionemo-agent-toolkit/skills/complexa-design into .gemini/skills/complexa-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "complexa-design", 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 NVIDIA-BioNeMo/bionemo-agent-toolkit complexa-designInstalls 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 NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/bionemo-agent-toolkit/skills/complexa-design .github/skills/complexa-design && 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 "complexa-design" agent skill from https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/skills/bionemo-agent-toolkit/skills/complexa-design into .github/skills/complexa-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "complexa-design", 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 NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NVIDIA-BioNeMo/bionemo-agent-toolkit complexa-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/bionemo-agent-toolkit/skills/complexa-design .opencode/skills/complexa-design && 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 "complexa-design" agent skill from https://github.com/NVIDIA-BioNeMo/bionemo-agent-toolkit/tree/main/skills/bionemo-agent-toolkit/skills/complexa-design into .opencode/skills/complexa-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "complexa-design", 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
complexa-design- GitHub stars
- 478
- Token cost
- ~4.1k tokens
- SKILL.md length
- 1,572 words
- Files
- 6
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
End-to-end Proteina-Complexa design pipeline driver. An agent skill from NVIDIA-BioNeMo/bionemo-agent-toolkit.
- Works in 7 steps: Pre-flight → Pick the pipeline → Gather parameters → …
- The user wants to design a binder
- SKILL.md covers What this skill enables, Step 1: Pre-flight, Step 2: Pick the pipeline and Step 3: Gather parameters, plus 7 more sections
- Calls bash, python and python3
What it does
Complexa Design is an agent skill from NVIDIA-BioNeMo/bionemo-agent-toolkit. End-to-end Proteina-Complexa design pipeline driver. Use when the user wants to "design a binder", "design binders for X", "run complexa design", "de novo binder", "PDL1 binder", "TrkA binder", "design proteins for target", "protein binder design", "ligand binder", "design a small-molecule binder", "ATP-binding protein", "AME motif scaffolding", "scaffold a motif near a ligand", "motif + ligand design", "enzyme scaffolding", "flow matching protein design", "beam-search binder", "FK steering", "MCTS protein…
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `evals/evals.json`, `evals/trigger_evals.json` and `reference/overrides.md`). Compatibility notes: complexa CLI installed (pip install -e .); environment file populated; 1x CUDA GPU =40GB VRAM (A100/H100/L40S); 24 CPUs; ~50GB disk
It sits in Research & Science, covering Project scaffolding and Protein structure and design. The repository describes itself as: Turn any agent into a life science expert with NVIDIA BioNeMo skills.
When your agent uses it
- The user wants to design a binder
- Design binders for X
- Run complexa design
- Design proteins for target
Example prompts
- “design a binder”
- “design binders for X”
- “run complexa design”
- “/complexa-design”
Requirements
- Python 3
- Compatibility (from SKILL.md): complexa CLI installed (pip install -e .); environment file populated; 1x CUDA GPU >=40GB VRAM (A100/H100/L40S); 24 CPUs; ~50GB disk
- Pre-approved tools (allowed-tools): Bash, Read, Write, AskUserQuestion
Workflow steps
7 steps, taken from the step headings in SKILL.md.
- Pre-flight
- Pick the pipeline
- Gather parameters
- Validate
- Run the pipeline
- Collect results
- Emit manifest
What it can do on your machine
Read from SKILL.md and the folder at commit 2113472. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadWriteAskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
bashpythonpython3
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.
Compatibility
complexa CLI installed (pip install -e .); environment file populated; 1x CUDA GPU >=40GB VRAM (A100/H100/L40S); 24 CPUs; ~50GB disk
From compatibility in the SKILL.md frontmatter.
Context cost
Complexa Design loads about 4.1k tokens when it runs. Until then it costs about 194 tokens; SKILL.md has 1,572 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:316
yError: AF2_DIR` | colabdesign eval but `.env` does not set `AF2_DIR` | Set `AF2_DIR` in `.env` or `++metric.binder_fold - NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, Write, AskUserQuestion
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,572 words (~4,120 tokens).
“Drive the full four-stage complexa design pipeline: generate (flow matching + search) -> filter (top-N by reward) -> evaluate (refold with AF2/RF3) -> analyze (success rate, FoldSeek/MMseqs diversity). Pick the right pipeline config for the design intent, validate the run…”
- name
- complexa-design
- allowed-tools
- Bash, Read, Write, AskUserQuestion
- compatibility
- complexa CLI installed (pip install -e .); environment file populated; 1x CUDA GPU >=40GB VRAM (A100/H100/L40S); 24 CPUs; ~50GB disk
Files
SKILL.md and 5 other files in skills/bionemo-agent-toolkit/skills/complexa-design of NVIDIA-BioNeMo/bionemo-agent-toolkit.
- SKILL.md
- evals/evals.json
- evals/trigger_evals.json
- reference/overrides.md
- reference/pipelines.md
- reference/troubleshooting.md
Open the folder on GitHubat commit 2113472
Compare with similar skills
Complexa Design 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 |
|---|---|---|---|---|---|---|
| Complexa Design this skillNVIDIA-BioNeMo/bionemo-agent-toolkit | 478 | — | ~4.1k | Automated safety check: Notes | Custom licence | |
| RfdiffusionPKU-YuanGroup/OpenAI4S | 617 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Rfdiffusionadaptyvbio/protein-design-skills | 163 | 4 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Tooluniverse Protein Therapeutic Designwu-yc/LabClaw | 1.1k | 2 repos | ~4.4k | Automated safety check: Pass | None | |
| Gtdscunning1975/MixtapeTools | 470 | — | ~2.9k | Automated safety check: Notes | None | |
| Scaffold Exercisespedrohcgs/claude-code-my-workflow | 1.6k | — | ~2k | Automated safety check: Notes | MIT |
Similar skills
Rfdiffusion
adaptyvbio/protein-design-skills
Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generation.
Tooluniverse Protein Therapeutic Design
wu-yc/LabClaw
Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design.
Gtd
scunning1975/MixtapeTools
Warrant-first research GTD system. An agent skill from scunning1975/MixtapeTools.
Scaffold Exercises
pedrohcgs/claude-code-my-workflow
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types.
- Official
Rfdiffusion Nim
NVIDIA/skills
Run RFDiffusion protein backbone design via NVIDIA NIM. An agent skill from NVIDIA/skills.
More from NVIDIA-BioNeMo/bionemo-agent-toolkit
All 14 skills in this repoComplexa Binder Design
NVIDIA-BioNeMo/bionemo-agent-toolkit
Run a complete protein binder design campaign with NVIDIA Proteina-Complexa: resolve a target structure and hotspots from a name/sequence/PDB, co-design binder sequence+structure with reward-guided…
Parabricks
NVIDIA-BioNeMo/bionemo-agent-toolkit
Route NVIDIA Parabricks pbrun tools, assess GPU/runtime readiness, and provide version-aware command guidance for FASTQ/BAM processing, RNA-seq, variant calling, BAM QC, and GVCF workflows.
Protein Binder Design
NVIDIA-BioNeMo/bionemo-agent-toolkit
Orchestrate an end-to-end de novo protein binder design campaign against a protein target by composing BioNeMo NIM skills.
Cuequivariance
NVIDIA-BioNeMo/bionemo-agent-toolkit
Build and debug cuEquivariance irreps, custom Irrep subclasses, Clebsch-Gordan tensor products, and equivariant or segmented polynomials.
Genomics Workflow Acceleration
NVIDIA-BioNeMo/bionemo-agent-toolkit
A skill your agent uses when accelerating existing genomics workflows with NVIDIA Parabricks, improving runtime or price/performance, converting pipeline steps to GPUs, or comparing CPU and GPU…
Complexa Evaluate Pdbs
NVIDIA-BioNeMo/bionemo-agent-toolkit
Standalone evaluation of an existing PDB directory with Proteina-Complexa.
Related
Categories
Questions about Complexa Design
What does Complexa Design do?
End-to-end Proteina-Complexa design pipeline driver. An agent skill from NVIDIA-BioNeMo/bionemo-agent-toolkit. Complexa Design is an agent skill from NVIDIA-BioNeMo/bionemo-agent-toolkit. End-to-end Proteina-Complexa design pipeline driver.
When should I use Complexa Design?
Complexa Design fits situations like: the user wants to design a binder; design binders for X; run complexa design; design proteins for target.
How do I install Complexa Design in Claude Code?
Run `npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a claude-code`. Or copy the skill folder (skills/bionemo-agent-toolkit/skills/complexa-design in NVIDIA-BioNeMo/bionemo-agent-toolkit) into .claude/skills/complexa-design in your project. Claude Code loads it when a task matches its description.
How do I install Complexa Design in Codex?
Run `npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a codex`. Or copy the skill folder (skills/bionemo-agent-toolkit/skills/complexa-design in NVIDIA-BioNeMo/bionemo-agent-toolkit) into .agents/skills/complexa-design in your project. Codex loads it when a task matches its description.
Can I use Complexa Design 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 NVIDIA-BioNeMo/bionemo-agent-toolkit --skill complexa-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/complexa-design, .gemini/skills/complexa-design, .github/skills/complexa-design and .opencode/skills/complexa-design in your project.
What does Complexa Design need to run?
Going by SKILL.md and its folder, Complexa Design needs the command-line tools its instructions call (bash, python and python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Write, AskUserQuestion. Compatibility (from SKILL.md): complexa CLI installed (pip install -e .); environment file populated; 1x CUDA GPU >=40GB VRAM (A100/H100/L40S); 24 CPUs; ~50GB disk.
Does Complexa Design 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 Complexa Design safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Complexa Design use?
Complexa Design has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Complexa Design use?
About 4.1k tokens (SKILL.md is roughly 16k 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 Complexa Design?
Skills that share tags, products or a category with Complexa Design: Rfdiffusion (PKU-YuanGroup/OpenAI4S, 617 stars), Rfdiffusion (adaptyvbio/protein-design-skills, 163 stars), Tooluniverse Protein Therapeutic Design (wu-yc/LabClaw, 1.1k stars) and Gtd (scunning1975/MixtapeTools, 470 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Complexa Design?
NVIDIA-BioNeMo (a GitHub organization) maintains it in NVIDIA-BioNeMo/bionemo-agent-toolkit, which has 478 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.
Source: NVIDIA-BioNeMo/bionemo-agent-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.