Agent skill

Flow Bio

Flow.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance.

MITAuto-check passedResearch & Science

Install Flow Bio

skills CLI

$ npx skills add ClawBio/ClawBio --skill flow-bio -a claude-code

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

GitHub CLI

$ gh skill install ClawBio/ClawBio flow-bio --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/ClawBio/ClawBio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/flow-bio .claude/skills/flow-bio && 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 "flow-bio" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/flow-bio into .claude/skills/flow-bio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flow-bio", 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/ClawBio/ClawBio/tree/main/skills/flow-bio

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 ClawBio/ClawBio --skill flow-bio -a codex

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

GitHub CLI

$ gh skill install ClawBio/ClawBio flow-bio --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/flow-bio .agents/skills/flow-bio && 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 "flow-bio" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/flow-bio into .agents/skills/flow-bio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flow-bio", 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 ClawBio/ClawBio --skill flow-bio -a cursor

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

GitHub CLI

$ gh skill install ClawBio/ClawBio flow-bio --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/flow-bio .cursor/skills/flow-bio && 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 "flow-bio" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/flow-bio into .cursor/skills/flow-bio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flow-bio", 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/ClawBio/ClawBio.git --path skills/flow-bio

--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 ClawBio/ClawBio --skill flow-bio -a gemini-cli

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

GitHub CLI

$ gh skill install ClawBio/ClawBio flow-bio --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/ClawBio/ClawBio.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/flow-bio .gemini/skills/flow-bio && 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 "flow-bio" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/flow-bio into .gemini/skills/flow-bio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flow-bio", 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 ClawBio/ClawBio flow-bio

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 ClawBio/ClawBio --skill flow-bio -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/flow-bio .github/skills/flow-bio && 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 "flow-bio" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/flow-bio into .github/skills/flow-bio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flow-bio", 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 ClawBio/ClawBio --skill flow-bio -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 ClawBio/ClawBio flow-bio --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/flow-bio .opencode/skills/flow-bio && 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 "flow-bio" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/flow-bio into .opencode/skills/flow-bio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flow-bio", 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: flow-bio
GitHub stars: 1.2k
Used in: 1 other repo
Token cost: ~2.3k tokens
SKILL.md length: 641 words
Files: 5
Skills in repo: 104
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Flow.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance.

Works in 9 steps: Authentication — Login via… → Pipeline discovery — List and inspect… → Sample management — List, search, and… → …
Research & Science work in your project
SKILL.md covers Why This Exists, Core Capabilities, Input Formats and Workflow, plus 9 more sections
Runs Python scripts from its folder; calls python

What it does

Flow Bio is an agent skill from ClawBio/ClawBio. Flow.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files (for example `data/demo_cache.json`, `flow_bio.py` and `tests/__init__.py`).

It sits in Research & Science. The repository describes itself as: 🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free. The licence is MIT.

When your agent uses it

Research & Science work in your project

Example prompts

“/flow-bio”

Requirements

Python 3
A credential in FLOW_TOKEN

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

Authentication — Login via username/password, existing JWT token, or environment variables
Pipeline discovery — List and inspect available Nextflow pipelines with versions and parameter schemas
Sample management — List, search, and upload samples with metadata and organism tagging
Project browsing — List owned/shared projects and their contents
Execution tracking — Launch pipeline runs, poll status, and retrieve logs
Search — Full-text search across samples, projects, data, and executions
Data listing — Browse owned and shared data files
Organism & type discovery — List available organisms and sample types for uploads
Overview mode — Live overview of any Flow instance; public data without credentials, full account view with login

What it can do on your machine

Read from SKILL.md and the folder at commit 5e045e3. 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
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- flow.bio
- nextflow.io
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

Flow Bio loads about 2.3k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 641 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~43
When it runs · the whole SKILL.md, loaded when a task matches: ~2.3k

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 ClawBio/ClawBio at commit 5e045e3, republished under its MIT licence (© ClawBio). 641 words, ~2,326 tokens.

Download SKILL.mdSave it as .claude/skills/flow-bio/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.

name: flow-bio
description: Flow.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance.
license: MIT
metadata.version: 0.1.0
metadata.author: ClawBio Contributors
metadata.domain: bioinformatics
metadata.tags: flow, flow.bio, LIMS, pipelines, samples, nextflow, bioinformatics, cloud

Flow Bio Bridge

ClawBio's gateway to the Flow.bio platform — browse, search, upload, and launch bioinformatics pipelines on Flow from the command line.

Why This Exists

Flow.bio is a bioinformatics platform hosting curated Nextflow pipelines with managed compute, sample tracking, and collaborative project management. But interacting with Flow requires navigating the web UI or writing custom API scripts.

Flow Bio Bridge makes the platform agent-accessible: authenticate once, then list pipelines, upload samples, launch executions, and poll for results — all from the CLI or via the ClawBio orchestrator.

Without it: Users must switch between web UI and local analysis, manually track execution IDs, and write one-off upload scripts
With it: A single CLI covers discovery, upload, execution, and status checking across any Flow instance
Why ClawBio: Chain Flow pipeline outputs with local ClawBio skills (e.g. Flow RNA-seq → ClawBio diffviz)

Core Capabilities

Authentication — Login via username/password, existing JWT token, or environment variables
Pipeline discovery — List and inspect available Nextflow pipelines with versions and parameter schemas
Sample management — List, search, and upload samples with metadata and organism tagging
Project browsing — List owned/shared projects and their contents
Execution tracking — Launch pipeline runs, poll status, and retrieve logs
Search — Full-text search across samples, projects, data, and executions
Data listing — Browse owned and shared data files
Organism & type discovery — List available organisms and sample types for uploads
Overview mode — Live overview of any Flow instance; public data without credentials, full account view with login

Input Formats

Format	Extension	Required Fields	Example
FASTQ (single-end)	`.fq`, `.fastq`, `.fq.gz`	reads1	`sample_R1.fastq.gz`
FASTQ (paired-end)	`.fq`, `.fastq`, `.fq.gz`	reads1, reads2	`sample_R1.fastq.gz`, `sample_R2.fastq.gz`
Any data file	any	—	annotation, reference, BED, etc.

Workflow

When the user asks to interact with Flow.bio:

Authenticate: Use stored token, env vars, or prompt for credentials
Discover: List pipelines, sample types, organisms as needed
Act: Upload samples, launch executions, or query status
Report: Write structured output (JSON + markdown) to output directory
Bundle: Generate reproducibility commands and checksums

CLI Reference

bash

# Login (stores token for subsequent calls)
python skills/flow-bio/flow_bio.py --login --username USER --password PASS
python skills/flow-bio/flow_bio.py --login --token TOKEN

# Discovery
python skills/flow-bio/flow_bio.py --pipelines
python skills/flow-bio/flow_bio.py --samples
python skills/flow-bio/flow_bio.py --projects
python skills/flow-bio/flow_bio.py --organisms
python skills/flow-bio/flow_bio.py --sample-types
python skills/flow-bio/flow_bio.py --executions
python skills/flow-bio/flow_bio.py --data

# Inspect details
python skills/flow-bio/flow_bio.py --execution EXEC_ID
python skills/flow-bio/flow_bio.py --sample SAMPLE_ID
python skills/flow-bio/flow_bio.py --pipeline PIPELINE_ID

# Inspect details via clawbio.py runner (uses --*-detail flags)
python clawbio.py run flow --execution-detail EXEC_ID
python clawbio.py run flow --sample-detail SAMPLE_ID
python clawbio.py run flow --pipeline-detail PIPELINE_ID

# Search
python skills/flow-bio/flow_bio.py --search "RNA-seq tumor"

# Raw JSON output (for piping to jq, etc.)
python skills/flow-bio/flow_bio.py --samples --json

# Upload sample
python skills/flow-bio/flow_bio.py --upload-sample \
  --name "Tumour_01" --sample-type "RNA-Seq" \
  --reads1 R1.fastq.gz --reads2 R2.fastq.gz \
  --organism "Homo sapiens" --project PROJECT_ID

# Launch pipeline
python skills/flow-bio/flow_bio.py --run-pipeline PIPELINE_VERSION_ID \
  --run-samples SAMPLE_ID1,SAMPLE_ID2 --output /tmp/flow_run

# Check execution status
python skills/flow-bio/flow_bio.py --execution EXEC_ID --output /tmp/flow_status

# Overview (public endpoints, no credentials needed)
python skills/flow-bio/flow_bio.py --demo --output /tmp/flow_demo

# Overview with authentication (shows owned samples, projects, executions)
python skills/flow-bio/flow_bio.py --demo --username USER --password PASS --output /tmp/flow_demo

Demo

bash

# Public overview (no credentials)
python skills/flow-bio/flow_bio.py --demo --output /tmp/flow_demo

# Full overview with account data
python skills/flow-bio/flow_bio.py --demo --username USER --password PASS --output /tmp/flow_demo

Expected output: a live overview of the Flow.bio instance showing available pipelines, organisms, and sample types (public), plus owned samples, projects, and executions if authenticated.

Show full SKILL.md (281 more words)Show less

Algorithm / Methodology

Token acquisition: POST /login with credentials → JWT token (5-min access, 7-day refresh)
API traversal: RESTful GET/POST with Authorization: Bearer <token> header
Pagination: Offset-based (?page=N) with lazy loading
Chunked upload: Files split into 1 MB chunks, uploaded sequentially with progress tracking
Execution polling: GET /executions/<id> until status reaches terminal state

Key parameters:

Base URL: https://app.flow.bio/api (configurable via FLOW_URL)
Chunk size: 1 MB (configurable)
Rate limits: 1000 req/hr API, 100/hr uploads, 500/hr downloads

Example Queries

"What pipelines are available on Flow?"
"List my samples on Flow.bio"
"Upload these FASTQ files to Flow"
"Run the RNA-seq pipeline on my sample"
"What's the status of my Flow execution?"
"Search Flow for breast cancer samples"

Output Structure

output_dir/
├── report.md              # Summary of Flow API interaction
├── result.json            # Machine-readable response data
└── reproducibility/
    ├── commands.sh        # Portable replay recipe (CLAWBIO_ROOT / OUTPUT_DIR)
    ├── environment.yml    # Conda environment for the run (python + requests)
    └── checksums.sha256   # SHA-256 of report.md and result.json

Dependencies

Required:

requests >= 2.28 — HTTP client for REST API calls

Optional:

tqdm — progress bars during file upload (graceful degradation without it)

Safety

Credentials never stored on disk — tokens held in memory or via environment variables only
No destructive defaults — delete/transfer operations are not exposed in v0.1
Audit trail: Every API interaction logged to reproducibility bundle
Disclaimer: ClawBio is a research and educational tool. It is not a medical device and does not provide clinical diagnoses. Consult a healthcare professional before making any medical decisions.

Integration with Bio Orchestrator

Trigger conditions — the orchestrator routes here when:

User mentions "flow", "flow.bio", "flow pipeline", "run on flow"
User wants to upload samples to a cloud platform
User asks about pipeline execution status on Flow

Chaining partners:

rnaseq-de — Flow RNA-seq pipeline output → ClawBio differential expression
diffviz — Flow DE results → ClawBio visualization
scrna-orchestrator — Flow Cell Ranger output → ClawBio scRNA analysis
illumina-bridge — Illumina DRAGEN → Flow upload → pipeline execution

Citations

Flow.bio — Bioinformatics platform
Nextflow — Workflow engine powering Flow pipelines

Files

SKILL.md and 4 other files in skills/flow-bio of ClawBio/ClawBio.

SKILL.md
data/demo_cache.json
flow_bio.py
tests/__init__.py
tests/test_flow_bio.py

Open the folder on GitHubat commit 5e045e3

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in ClawBio/ClawBio, which our catalogue first saw on October 7, 2026.

BioTender-max/awesome-bio-agent-skillsskills/clawbio/flow-bio

Compare with similar skills

Flow Bio 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.

Flow Bio compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Flow Bio this skillClawBio/ClawBio	1.2k	1 repos	~2.3k	Automated safety check: Pass	MIT	today
Hypothesis Generationspacering-net/codeg	3.8k	15 repos	~3.6k	Automated safety check: Notes	MIT	today
GitHub Deep Researchbytedance/deer-flow	83k	5 repos	~1.3k	Automated safety check: Pass	MIT	today
Nature Paper CardYuan1z0825/nature-skills	46k	2 repos	~2.1k	Automated safety check: Pass	Apache-2.0	yesterday
Read arXiv Paperkarpathy/nanochat	58k	2 repos	~494	Automated safety check: Pass	MIT	1 mo ago
Content Research Writerweapp-tailwindcss/weapp-tailwindcss	1.9k	25 repos	~3.5k	Automated safety check: Pass	MIT	today

Similar skills

Hypothesis Generation
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
3.8k GitHub starsUsed in 15 repos~3.6k tokens
Research & ScienceAuto-check: notes
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.
83k GitHub starsUsed in 5 repos~1.3k tokens
Research & ScienceAuto-check passed
Nature Paper Card
Yuan1z0825/nature-skills
Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.
46k GitHub starsUsed in 2 repos~2.1k tokens
Research & ScienceAuto-check passed
Read arXiv Paper
karpathy/nanochat
Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.
58k GitHub starsUsed in 2 repos~494 tokens
Research & ScienceAuto-check passed
Content Research Writer
weapp-tailwindcss/weapp-tailwindcss
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.
1.9k GitHub starsUsed in 25 repos~3.5k tokens
Research & ScienceAuto-check passed
Peer Review
spacering-net/codeg
Structured manuscript/grant review with checklist-based evaluation.
3.8k GitHub starsUsed in 18 repos~5.9k tokens
Research & ScienceAuto-check: notes

Questions about Flow Bio

What does Flow Bio do?

Flow.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance. Flow Bio is an agent skill from ClawBio/ClawBio.bio API bridge — authenticate, browse pipelines/samples/projects, search, upload data, launch pipeline executions, and check run status on any Flow instance.

When should I use Flow Bio?

Flow Bio fits situations like: research & Science work in your project.

How do I install Flow Bio in Claude Code?

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

How do I install Flow Bio in Codex?

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

Can I use Flow Bio 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 ClawBio/ClawBio --skill flow-bio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flow-bio, .gemini/skills/flow-bio, .github/skills/flow-bio and .opencode/skills/flow-bio in your project.

What does Flow Bio need to run?

Going by SKILL.md and its folder, Flow Bio needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3; A credential in FLOW_TOKEN.

Does Flow Bio access the network?

SKILL.md names 2 domains. As links in the text: flow.bio and nextflow.io. This is read from the text; nothing was executed.

Is Flow Bio 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 Flow Bio use?

Flow Bio is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Flow Bio use?

About 2.3k tokens (SKILL.md is roughly 9.3k 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 Flow Bio?

Skills that share tags, products or a category with Flow Bio: Hypothesis Generation (spacering-net/codeg, 3.8k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars), Nature Paper Card (Yuan1z0825/nature-skills, 46k stars) and Read arXiv Paper (karpathy/nanochat, 58k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flow Bio?

ClawBio (a GitHub organization) maintains it in ClawBio/ClawBio, which has 1,154 GitHub stars. The repository holds 104 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Flow Bio

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Flow Bio Bridge

Why This Exists

Core Capabilities

Input Formats

Workflow

CLI Reference

Demo

Algorithm / Methodology

Example Queries

Output Structure

Dependencies

Safety

Integration with Bio Orchestrator

Citations

Files

Used in 1 other repository

Compare with similar skills

Similar skills

More from ClawBio/ClawBio

Related

Questions about Flow Bio