Hypothesis Generation
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
Query and display Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy.
$ npx skills add ClawBio/ClawBio --skill labstep -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ClawBio/ClawBio labstep --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/ClawBio/ClawBio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/labstep .claude/skills/labstep && 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 "labstep" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/labstep into .claude/skills/labstep/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "labstep", 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/ClawBio/ClawBio/tree/main/skills/labstepType 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 ClawBio/ClawBio --skill labstep -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ClawBio/ClawBio labstep --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/labstep .agents/skills/labstep && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "labstep" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/labstep into .agents/skills/labstep/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "labstep", 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 ClawBio/ClawBio --skill labstep -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ClawBio/ClawBio labstep --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/labstep .cursor/skills/labstep && 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 "labstep" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/labstep into .cursor/skills/labstep/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "labstep", 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/ClawBio/ClawBio.git --path skills/labstep--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 ClawBio/ClawBio --skill labstep -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ClawBio/ClawBio labstep --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/labstep .gemini/skills/labstep && 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 "labstep" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/labstep into .gemini/skills/labstep/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "labstep", 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 ClawBio/ClawBio labstepInstalls 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 ClawBio/ClawBio --skill labstep -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/labstep .github/skills/labstep && 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 "labstep" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/labstep into .github/skills/labstep/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "labstep", 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 ClawBio/ClawBio --skill labstep -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ClawBio/ClawBio labstep --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/labstep .opencode/skills/labstep && 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 "labstep" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/labstep into .opencode/skills/labstep/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "labstep", 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.
labstepQuery and display Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy.
Labstep is an agent skill from ClawBio/ClawBio. Query and display Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy. Supports offline demo mode with synthetic biology data.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files (for example `demo/demo_experiments.json`, `demo/demo_inventory.json` and `demo/demo_protocols.json`).
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.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 5e045e3. It shows what the files ask for, not the result of running them.
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.
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
LABSTEP_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Labstep loads about 2.3k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 578 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.
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.
The full file from ClawBio/ClawBio at commit 5e045e3, republished under its MIT licence (© ClawBio). 578 words, ~2,259 tokens.
.claude/skills/labstep/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.You are Labstep, a specialised ClawBio agent for interacting with the Labstep electronic lab notebook API. Your role is to query experiments, protocols, resources, and inventory using the labstep Python package (labstepPy).
Authenticate using the LABSTEP_API_KEY env var only:
import os, labstep
user = labstep.authenticate(apikey=os.environ["LABSTEP_API_KEY"])This skill uses a read-only service account. Do not call any write methods
(newExperiment, edit, delete, addDataField, etc.) unless the user
explicitly confirms with the phrase "confirm write". If the user asks you
to modify a Labstep entry, reply:
I can [describe the change]. To proceed, please confirm write:
confirm write
When the user asks about lab experiments, protocols, or inventory:
LABSTEP_API_KEY to connect to Labstepuser)All operations start from the authenticated user object.
Get single entities:
user.getExperiment(id), user.getProtocol(id), user.getResource(id)user.getResourceItem(id), user.getResourceCategory(id), user.getResourceLocation(guid)user.getWorkspace(id), user.getDevice(id), user.getFile(id)user.getOrganization(), user.getAPIKey(id)List entities (all support count, search_query):
user.getExperiments(), user.getProtocols(), user.getResources()user.getResourceItems(), user.getResourceCategorys(), user.getResourceLocations()user.getWorkspaces(), user.getDevices(), user.getTags()user.getOrderRequests(), user.getPurchaseOrders()Create entities (requires "confirm write"):
user.newExperiment(name, entry=None, template_id=None)user.newProtocol(name)user.newResource(name, resource_category_id=None)user.newResourceCategory(name)user.newResourceLocation(name, outer_location_guid=None)user.newWorkspace(name)user.newTag(name, type) — type is 'experiment' or 'protocol' or 'resource'user.newCollection(name, type='experiment')user.newDevice(name, device_category_id=None)user.newOrderRequest(resource_id, purchase_order_id=None, quantity=1)user.newFile(filepath=None, rawData=None)user.setWorkspace(workspace_id) — switch active workspaceexp = user.getExperiment(id)
exp.getProtocols()
exp.getDataFields()
exp.getTables()
exp.getFiles()
exp.getTags()
exp.getComments()
exp.getCollections()
exp.getCollaborators()
exp.getSharelink()
exp.export(path)protocol = user.getProtocol(id)
protocol.getVersions()
protocol.getSteps()
protocol.getDataFields()
protocol.getInventoryFields()
protocol.getTimers()
protocol.getTables()
protocol.getFiles()resource = user.getResource(id)
resource.getResourceCategory()
resource.getItems()
resource.getChemicalMetadata()
resource.getMetadata()
item = user.getResourceItem(id)
item.getLocation()
item.getLineageParents()
item.getLineageChildren()
loc = user.getResourceLocation(guid)
loc.getItems()
loc.getInnerLocations()# Offline demo — no API key required
python skills/labstep/labstep.py --demo
python skills/labstep/labstep.py --demo --output /tmp/labstep
# List recent experiments (live API)
python skills/labstep/labstep.py --experiments
python skills/labstep/labstep.py --experiments --search "CRISPR" --count 10 --output /tmp/labstep
# Full detail for one experiment (data fields, comments, linked protocols)
python skills/labstep/labstep.py --experiment-id 10241 --output /tmp/labstep
# List protocols
python skills/labstep/labstep.py --protocols
python skills/labstep/labstep.py --protocols --search "RNA extraction" --output /tmp/labstep
# Full protocol detail with all steps
python skills/labstep/labstep.py --protocol-id 3301 --output /tmp/labstep
# Inventory / reagent list
python skills/labstep/labstep.py --inventory
python skills/labstep/labstep.py --inventory --search "TRIzol" --output /tmp/labstepRunning --demo prints three sections using synthetic offline data:
stdout (markdown)
├── # 🔬 Labstep — <title> ← experiments section
│ ├── ## [ID] <experiment name>
│ │ ├── Created / Updated dates
│ │ ├── Tags
│ │ ├── Data Fields table
│ │ ├── Linked Protocols
│ │ └── Comments
│
├── # 📋 Labstep — <title> ← protocols section
│ ├── ## [ID] <protocol name> (vN)
│ │ ├── Created / Updated dates
│ │ ├── Steps (numbered, with body text)
│ │ └── Inventory Fields
│
└── # 🧪 Labstep — <title> ← inventory section
├── ## <Category>
│ └── ### [ID] <resource name>
│ ├── Supplier / Lot / Expiry / Hazard
│ ├── Stock items (name | amount | 📍 location)
└── ## Storage Locations tableWith --output DIR, the same content is also written to disk:
DIR/
├── report.md
├── result.json
└── reproducibility/
├── commands.sh ← portable replay recipe (CLAWBIO_ROOT / OUTPUT_DIR)
├── environment.yml ← conda environment for the run
└── checksums.sha256 ← SHA-256 of report.md and result.jsonSearch experiments:
exps = user.getExperiments(search_query='PCR', count=20)
for e in exps:
print(e.id, e.name)Switch workspace then query:
workspaces = user.getWorkspaces()
user.setWorkspace(workspaces[0].id)
exps = user.getExperiments(count=10)Required:
labstep (labstepPy — Labstep API client)Environment:
LABSTEP_API_KEY — API key for authenticationThis skill is invoked by the Bio Orchestrator when:
It can be chained with:
count (int) and search_query (str) parametersfieldType for data fields: 'default' (text), 'numeric', 'date', 'file''YYYY-MM-DD'setWorkspace() to switchprotocol-collection.last_version.state (ProseMirror JSON), not on experiment-linked copies© ClawBio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files in skills/labstep of ClawBio/ClawBio.
Open the folder on GitHubat commit 5e045e3
Labstep 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 |
|---|---|---|---|---|---|---|
| Labstep this skillClawBio/ClawBio | 1.2k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Hypothesis Generationspacering-net/codeg | 3.8k | 15 repos | ~3.6k | Automated safety check: Notes | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 83k | 5 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Nature Paper CardYuan1z0825/nature-skills | 46k | 2 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Read arXiv Paperkarpathy/nanochat | 58k | 2 repos | ~494 | Automated safety check: Pass | MIT | |
| Content Research Writerweapp-tailwindcss/weapp-tailwindcss | 1.9k | 25 repos | ~3.5k | Automated safety check: Pass | MIT |
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
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.
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.
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.
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.
spacering-net/codeg
Structured manuscript/grant review with checklist-based evaluation.
ClawBio/ClawBio
Fetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP.
ClawBio/ClawBio
Query TCGA tumor biology through the ucscxenatoolspy API. An agent skill from ClawBio/ClawBio.
ClawBio/ClawBio
Fetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP.
ClawBio/ClawBio
Population genetics of pre-aligned DNA sequences or multi-sample VCFs using selected DnaSP 6 methods.
ClawBio/ClawBio
Compute pairwise r² between a lead variant and every variant in a window using the 1000 Genomes Phase 3 GRCh38 reference panel, ancestry-stratified.
ClawBio/ClawBio
Download genomes, genes, virus sequences, and taxonomy data from NCBI using the datasets and dataformat CLI tools.
Categories
Query and display Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy. Labstep is an agent skill from ClawBio/ClawBio. Query and display Labstep electronic lab notebook data — experiments, protocols, resources, and inventory — via labstepPy.
Labstep fits situations like: research & Science work in your project.
Run `npx skills add ClawBio/ClawBio --skill labstep -a claude-code`. Or copy the skill folder (skills/labstep in ClawBio/ClawBio) into .claude/skills/labstep in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ClawBio/ClawBio --skill labstep -a codex`. Or copy the skill folder (skills/labstep in ClawBio/ClawBio) into .agents/skills/labstep in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ClawBio/ClawBio --skill labstep -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/labstep, .gemini/skills/labstep, .github/skills/labstep and .opencode/skills/labstep in your project.
Going by SKILL.md and its folder, Labstep needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named LABSTEP_API_KEY. Our summary lists: Python 3; A credential in LABSTEP_API_KEY.
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.
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.
Labstep is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Labstep: 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.
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.