Complexa Setup

What it does

When your agent uses it

• Tasks that involve Protein structure and design
• Tasks that involve Containers

Example prompts

• “set up complexa”
• “install complexa”
• “configure my environment file”
• “/complexa-setup”

Requirements

• Python 3
• Docker
• A credential in WANDB_API_KEY
• Compatibility (from SKILL.md): complexa CLI installed (pip install -e .); bash 4+; nvidia-smi optional
• Pre-approved tools (allowed-tools): Bash, Read, Write, AskUserQuestion

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Pre-flight check
2. 2Create .env
3. 3Edit .env
4. 4Download checkpoints
5. 5Validate
6. 6Emit setup artifact

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:

  • Bash
  • Read
  • Write
  • AskUserQuestion

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • bash
  • python
  • 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 these keys or tokens, usually read from environment variables:

  • HF_TOKEN
  • WANDB_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  complexa CLI installed (pip install -e .); bash 4+; nvidia-smi optional

  From compatibility in the SKILL.md frontmatter.

Context cost

Complexa Setup loads about 3.5k tokens when it runs. Until then it costs about 217 tokens; SKILL.md has 1,448 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~217

When it runs · the whole SKILL.md, loaded when a task matches

~3.5k

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

• NoteMentions a .env fileSKILL.md:13

  env` end-to-end, edits the required `.env` keys, picks the right runtime (UV

• NoteMentions a .env fileSKILL.md:22

  design run: create `.env`, fetch model weights, and sanity-check the env.

• NoteMentions a .env fileSKILL.md:31

  | `.env` creation (Step 2) | **File edit** (copying the env template + 3 line swaps) or `complexa init` | `complexa init

• NoteMentions a .env fileSKILL.md:32

  | `.env` value edits (Step 3) | **File edit** (StrReplace `LOCAL_CODE_PATH=…` etc.) | No CLI for this — the values are u

• NoteMentions a .env fileSKILL.md:34

  ** (`complexa validate env`) or `test -f .env && test -d $DATA_PATH` | CLI prints a nicer report; the manual check is on

• NoteMentions a .env fileSKILL.md:39

  - A correctly-shaped `.env` for either UV or Docker runtime.

• NoteMentions a .env fileSKILL.md:41

  t.json` snapshot of the host (GPU, disk, .env, ckpts, tool binaries).

• NoteMentions a .env fileSKILL.md:48

  require `.env` to exist — it falls back to defaults — and it tells you whether

• NoteMentions a .env fileSKILL.md:60

  anything listed here must be edited in `.env` before validation passes.

• NoteMentions a .env fileSKILL.md:83

  ## Step 2: Create `.env`

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 1,448 words (~3,482 tokens).

name

complexa-setup

allowed-tools

Bash, Read, Write, AskUserQuestion

compatibility

complexa CLI installed (pip install -e .); bash 4+; nvidia-smi optional

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files in skills/bionemo-agent-toolkit/skills/complexa-setup of NVIDIA-BioNeMo/bionemo-agent-toolkit.

• SKILL.md
• config/skillspector-baseline.yml
• evals/evals.json
• reference/downloads.md
• reference/env_keys.md

Open the folder on GitHubat commit 2113472