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.
Hardware-agnostic Python liquid-handler library: portable scripts run on Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulator without vendor lock-in.
$ npx skills add jaechang-hits/SciAgent-Skills --skill pylabrobot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills pylabrobot --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/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lab-automation/pylabrobot .claude/skills/pylabrobot && 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 "pylabrobot" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/lab-automation/pylabrobot into .claude/skills/pylabrobot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pylabrobot", 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/jaechang-hits/SciAgent-Skills/tree/main/skills/lab-automation/pylabrobotType 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 jaechang-hits/SciAgent-Skills --skill pylabrobot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills pylabrobot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/lab-automation/pylabrobot .agents/skills/pylabrobot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pylabrobot" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/lab-automation/pylabrobot into .agents/skills/pylabrobot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pylabrobot", 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 jaechang-hits/SciAgent-Skills --skill pylabrobot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills pylabrobot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/lab-automation/pylabrobot .cursor/skills/pylabrobot && 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 "pylabrobot" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/lab-automation/pylabrobot into .cursor/skills/pylabrobot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pylabrobot", 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/jaechang-hits/SciAgent-Skills.git --path skills/lab-automation/pylabrobot--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 jaechang-hits/SciAgent-Skills --skill pylabrobot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills pylabrobot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/lab-automation/pylabrobot .gemini/skills/pylabrobot && 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 "pylabrobot" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/lab-automation/pylabrobot into .gemini/skills/pylabrobot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pylabrobot", 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 jaechang-hits/SciAgent-Skills pylabrobotInstalls 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 jaechang-hits/SciAgent-Skills --skill pylabrobot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/lab-automation/pylabrobot .github/skills/pylabrobot && 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 "pylabrobot" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/lab-automation/pylabrobot into .github/skills/pylabrobot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pylabrobot", 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 jaechang-hits/SciAgent-Skills --skill pylabrobot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills pylabrobot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/lab-automation/pylabrobot .opencode/skills/pylabrobot && 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 "pylabrobot" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/lab-automation/pylabrobot into .opencode/skills/pylabrobot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pylabrobot", 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.
pylabrobotHardware-agnostic Python liquid-handler library: portable scripts run on Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulator without vendor lock-in.
Pylabrobot is an agent skill from jaechang-hits/SciAgent-Skills. Hardware-agnostic Python liquid-handler library: portable scripts run on Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulator without vendor lock-in. For protocol automation, method dev, plate reformatting, serial dilutions, and Python lab workflows.
Its SKILL.md is about 4k 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. It works with Python. The repository describes itself as: 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 82c862c. 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.
Shell commands in SKILL.md call:
pipFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
docs.pylabrobot.orggithub.comcell.compypi.orgFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pylabrobot loads about 4k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 874 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 jaechang-hits/SciAgent-Skills at commit 82c862c, republished under its MIT licence (© jaechang-hits). 874 words, ~4,041 tokens.
.claude/skills/pylabrobot/SKILL.md (or your agent's skills folder).PyLabRobot is an open-source Python library that abstracts liquid handling robot hardware behind a unified API. Write a protocol once and run it on any supported robot — Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulated backend — without changing the protocol code. PyLabRobot handles deck layout, resource management, and aspirate/dispense operations through a clean, async-first interface.
opentrons Python SDK instead; for multi-vendor portability use PyLabRobot.pylabrobotpylabrobot[hamilton] for Hamilton STAR, pylabrobot[opentrons] for OT-2pip install pylabrobot
pip install "pylabrobot[hamilton]" # add Hamilton USB driver
pip install "pylabrobot[opentrons]" # add Opentrons REST driverimport asyncio
from pylabrobot.liquid_handling import LiquidHandler
from pylabrobot.liquid_handling.backends import SimulatorBackend
from pylabrobot.resources import Deck, Cos_96_Rd, HTF_L
async def main():
backend = SimulatorBackend(open_browser=False)
lh = LiquidHandler(backend=backend, deck=Deck())
await lh.setup()
plate = Cos_96_Rd(name="plate")
tips = HTF_L(name="tips")
lh.deck.assign_child_resource(plate, rails=2)
lh.deck.assign_child_resource(tips, rails=5)
await lh.pick_up_tips(tips["A1"])
await lh.aspirate(plate["A1"], vols=50)
await lh.dispense(plate["B1"], vols=50)
await lh.drop_tips(tips["A1"])
await lh.stop()
print("Transfer complete: 50 uL from A1 -> B1")
asyncio.run(main())The LiquidHandler class is the central controller. It wraps a backend and a Deck.
import asyncio
from pylabrobot.liquid_handling import LiquidHandler
from pylabrobot.liquid_handling.backends import SimulatorBackend
from pylabrobot.resources import Deck
async def main():
backend = SimulatorBackend(open_browser=False)
lh = LiquidHandler(backend=backend, deck=Deck())
await lh.setup() # connect to hardware / start simulator
print("LiquidHandler ready:", lh)
await lh.stop() # disconnect cleanly
asyncio.run(main())# Connecting to a real Hamilton STAR
from pylabrobot.liquid_handling.backends.hamilton import STAR
async def main():
backend = STAR()
lh = LiquidHandler(backend=backend, deck=Deck())
await lh.setup()
# lh is now connected to physical hardware
await lh.stop()Resources (plates, tip racks, reservoirs) are placed on the deck by rail position.
from pylabrobot.resources import (
Deck,
Cos_96_Rd, # Corning 96-well round-bottom plate
Cos_384_Sq, # Corning 384-well plate
HTF_L, # Hamilton tip rack (filtered, large)
Trough_1_Row_1_Col_4, # 4-channel reservoir
)
deck = Deck()
plate_96 = Cos_96_Rd(name="sample_plate")
plate_384 = Cos_384_Sq(name="assay_plate")
tips = HTF_L(name="tip_rack")
reservoir = Trough_1_Row_1_Col_4(name="buffer")
deck.assign_child_resource(plate_96, rails=1)
deck.assign_child_resource(plate_384, rails=4)
deck.assign_child_resource(tips, rails=8)
deck.assign_child_resource(reservoir, rails=11)
print("Deck resources:", [r.name for r in deck.children])Pick up and drop tips before and after liquid operations.
# Pick up tips from the first column of the tip rack
await lh.pick_up_tips(tips["A1:H1"]) # all 8 tips in column 1
# After liquid operations, drop tips back
await lh.drop_tips(tips["A1:H1"])
# Single tip
await lh.pick_up_tips(tips["A1"])
await lh.drop_tips(tips["A1"])
print("Tip operations complete")Aspirate liquid from wells. Accepts single wells, ranges, or lists.
# Aspirate 100 uL from a single well
await lh.aspirate(plate["A1"], vols=100)
# Aspirate different volumes from multiple wells simultaneously
await lh.aspirate(
plate["A1:A4"],
vols=[50, 75, 100, 125],
)
print("Aspiration complete")from pylabrobot.resources import Coordinate
# Aspirate with flow rate and liquid height control
await lh.aspirate(
plate["A1"],
vols=50,
flow_rates=100, # uL/s
offsets=Coordinate(0, 0, 1), # 1 mm above well bottom
)Dispense liquid into target wells.
# Dispense 100 uL into a single well
await lh.dispense(plate["B1"], vols=100)
# Multi-well dispense with different volumes
await lh.dispense(
plate["B1:B4"],
vols=[50, 75, 100, 125],
)
print("Dispense complete")transfer combines aspirate and dispense for simple source-to-destination moves.
# Transfer 50 uL from A1 -> B1
await lh.transfer(plate["A1"], plate["B1"], transfer_volume=50)
# Multi-well pairwise transfer
sources = plate["A1:A8"]
destinations = plate["B1:B8"]
await lh.transfer(sources, destinations, transfer_volume=75)
print("Transfer complete")The SimulatorBackend runs a browser-based visualizer for protocol debugging.
from pylabrobot.liquid_handling.backends import SimulatorBackend
# With visual browser (default — opens http://localhost:2121)
backend = SimulatorBackend(open_browser=True)
# Headless simulation (CI/testing)
backend = SimulatorBackend(open_browser=False)
# After setup(), liquid movements are visualized in real time
await lh.setup()
# Check browser for visual confirmation before running on real hardware
print("Simulator running at http://localhost:2121")All robot operations (setup, aspirate, dispense, transfer) are Python async coroutines. Run them inside an async def function using asyncio.run() or Jupyter's top-level await syntax.
import asyncio
async def run_protocol(lh, plate, tips):
await lh.pick_up_tips(tips["A1"])
await lh.aspirate(plate["A1"], vols=50)
await lh.dispense(plate["B1"], vols=50)
await lh.drop_tips(tips["A1"])
print("Protocol complete")
asyncio.run(run_protocol(lh, plate, tips))Wells are addressed by alphanumeric position ("A1") or slice notation ("A1:H1" for a column, "A1:A12" for a row).
well = plate["A1"] # single well
col1 = plate["A1:H1"] # 8 wells in column 1
row_a = plate["A1:A12"] # 12 wells in row A
print(f"Single: {well.name}")
print(f"Column: {len(col1)} wells")
print(f"Row: {len(row_a)} wells")Goal: Perform a 2-fold serial dilution across a 96-well plate.
import asyncio
from pylabrobot.liquid_handling import LiquidHandler
from pylabrobot.liquid_handling.backends import SimulatorBackend
from pylabrobot.resources import Deck, Cos_96_Rd, HTF_L, Trough_1_Row_1_Col_4
async def serial_dilution():
backend = SimulatorBackend(open_browser=False)
lh = LiquidHandler(backend=backend, deck=Deck())
await lh.setup()
plate = Cos_96_Rd(name="plate")
tips = HTF_L(name="tips")
diluent = Trough_1_Row_1_Col_4(name="diluent")
lh.deck.assign_child_resource(plate, rails=1)
lh.deck.assign_child_resource(tips, rails=5)
lh.deck.assign_child_resource(diluent, rails=9)
# Add 100 uL diluent to columns 2-12
for col in range(2, 13):
col_label = f"A{col}:H{col}"
await lh.pick_up_tips(tips[f"A{col}:H{col}"])
await lh.aspirate(diluent["A1:H1"], vols=100)
await lh.dispense(plate[col_label], vols=100)
await lh.drop_tips(tips[f"A{col}:H{col}"])
# Serial transfer: col 1 -> 2 -> ... -> 11
for col in range(1, 12):
src = f"A{col}:H{col}"
dst = f"A{col+1}:H{col+1}"
await lh.pick_up_tips(tips[f"A{col}:H{col}"])
await lh.aspirate(plate[src], vols=100)
await lh.dispense(plate[dst], vols=100)
await lh.drop_tips(tips[f"A{col}:H{col}"])
print("Serial dilution complete: 12 columns, 2-fold steps")
await lh.stop()
asyncio.run(serial_dilution())Goal: Transfer compounds from specified source wells to a destination plate based on a CSV hit list.
import asyncio
import pandas as pd
from pylabrobot.liquid_handling import LiquidHandler
from pylabrobot.liquid_handling.backends import SimulatorBackend
from pylabrobot.resources import Deck, Cos_96_Rd, HTF_L
async def cherry_pick(hit_list_csv: str, volume: float = 50.0):
# CSV must have columns: source_well, dest_well
hits = pd.read_csv(hit_list_csv)
print(f"Cherry-picking {len(hits)} hits at {volume} uL each")
backend = SimulatorBackend(open_browser=False)
lh = LiquidHandler(backend=backend, deck=Deck())
await lh.setup()
src = Cos_96_Rd(name="source")
dst = Cos_96_Rd(name="destination")
tips = HTF_L(name="tips")
lh.deck.assign_child_resource(src, rails=1)
lh.deck.assign_child_resource(dst, rails=4)
lh.deck.assign_child_resource(tips, rails=8)
# Get all well names from tip rack
tip_wells = [w.name for w in tips.wells]
for i, row in hits.iterrows():
await lh.pick_up_tips(tips[tip_wells[i]])
await lh.transfer(src[row["source_well"]], dst[row["dest_well"]],
transfer_volume=volume)
await lh.drop_tips(tips[tip_wells[i]])
print(f"Cherry-pick complete: {len(hits)} transfers done")
await lh.stop()
# asyncio.run(cherry_pick("hits.csv", volume=50))| Parameter | Module | Default | Range / Options | Effect |
|---|---|---|---|---|
vols | aspirate / dispense | required | 0 – robot max (µL) | Volume to aspirate or dispense per well |
flow_rates | aspirate / dispense | backend default | 10 – 1000 µL/s | Speed of liquid movement |
blow_out_air_volume | dispense | 0 | 0 – 30 µL | Air volume blown after dispense to empty tip |
offsets | aspirate / dispense | Coordinate(0,0,0) | Any Coordinate | Positional offset from well center (x, y, z mm) |
open_browser | SimulatorBackend | True | True, False | Open browser-based visual simulator on setup |
rails | deck assignment | required | 1 – max deck rails | Physical slot on the deck for a resource |
transfer_volume | transfer | required | 0 – robot max (µL) | Volume for high-level aspirate+dispense transfer |
Always test with the simulator first: Run your full protocol with SimulatorBackend(open_browser=True) before connecting to physical hardware. The browser visualizer shows deck layout and liquid movements in real time.
Use fresh tips for each transfer when contamination matters: Reusing tips in cherry-picking workflows risks cross-contamination. Track tip consumption against tip rack capacity programmatically.
Wrap protocols in try/finally for cleanup: If an exception occurs mid-protocol, always call await lh.stop() to release hardware connections.
try:
await run_my_protocol(lh)
finally:
await lh.stop()Define resources once at the top of your script: Create resource objects and assign them to the deck once. Reassigning the same resource mid-run can desynchronize the robot's internal state tracking.
Pre-calculate volume and tip requirements: For high-throughput runs, compute total volume and tip count needed before starting, and assert that resources are sufficient.
When to use: Reagent addition to cell culture wells requiring homogeneous mixing.
async def dispense_and_mix(lh, src, dst, tips, volume=50, mix_vol=40, mix_reps=3):
await lh.pick_up_tips(tips["A1"])
await lh.aspirate(src["A1"], vols=volume)
await lh.dispense(dst["A1"], vols=volume)
for _ in range(mix_reps):
await lh.aspirate(dst["A1"], vols=mix_vol)
await lh.dispense(dst["A1"], vols=mix_vol)
await lh.drop_tips(tips["A1"])
print(f"Dispensed {volume} uL and mixed {mix_reps}x")When to use: Replicate an entire 96-well plate to a second plate.
async def stamp_plate(lh, src_plate, dst_plate, tips, volume=100):
for col in range(1, 13):
col_label = f"A{col}:H{col}"
await lh.pick_up_tips(tips[col_label])
await lh.aspirate(src_plate[col_label], vols=volume)
await lh.dispense(dst_plate[col_label], vols=volume)
await lh.drop_tips(tips[col_label])
print(f"Full plate stamped: {volume} uL per well, 12 columns")http://localhost:2121 shows animated deck with per-well volume trackingpandas / CSV logging in wrapper code as needed| Problem | Cause | Solution |
|---|---|---|
RuntimeError: No backend connected | lh.setup() not awaited before operations | Ensure await lh.setup() completes before any liquid handling call |
ResourceNotFoundError | Resource name not assigned to deck | Call deck.assign_child_resource(resource, rails=N) before referencing wells |
asyncio.InvalidStateError | Coroutine called outside async context | Wrap top-level calls in async def main() and use asyncio.run(main()) |
Well address KeyError | Incorrect well label format | Use uppercase letter + integer: "A1", "H12", not "a1" or "A01" |
VolumeError: exceeds tip capacity | Requested volume larger than tip max | Use appropriate tip type; HTF_L holds up to 1000 µL |
| Simulator shows no movement | open_browser=False with no viewer | Set open_browser=True or open http://localhost:2121 manually |
ImportError: pylabrobot.hamilton | Backend extras not installed | pip install "pylabrobot[hamilton]" |
© jaechang-hits, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/lab-automation/pylabrobot of jaechang-hits/SciAgent-Skills.
Open the folder on GitHubat commit 82c862c
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 jaechang-hits/SciAgent-Skills, which our catalogue first saw on October 7, 2026.
Pylabrobot 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 |
|---|---|---|---|---|---|---|
| Pylabrobot this skilljaechang-hits/SciAgent-Skills | 374 | 1 repos | ~4k | Automated safety check: Pass | MIT | |
| 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 | |
| NetworkxzLanqing/codex-claude-academic-skills | 4.7k | 15 repos | ~3.2k | Automated safety check: Pass | BSD-3-Clause | |
| Nature-Style Scientific FiguresYuan1z0825/nature-skills | 47k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Citation ManagementK-Dense-AI/claude-scientific-writer | 2.4k | 2 repos | ~3.9k | Automated safety check: Notes | MIT |
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.
mvanhorn/last30days-skill
Research what people actually say about any topic in the last 30 days.
zLanqing/codex-claude-academic-skills
Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python.
Yuan1z0825/nature-skills
Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.
K-Dense-AI/claude-scientific-writer
Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.
LigphiDonk/Oh-my--paper
Searches bioRxiv life sciences preprints by keyword, author, date range or category with a Python script, returning JSON metadata and optional PDF downloads.
jaechang-hits/SciAgent-Skills
NEB-IRC activation energy pipeline for reaction barriers using GFN2-xTB and pysisyphus.
jaechang-hits/SciAgent-Skills
3Dmol.js WebGL molecular visualization emitted as self-contained HTML.
jaechang-hits/SciAgent-Skills
Constraint-based (COBRA) analysis of genome-scale metabolic models: FBA, FVA, knockouts, flux sampling, production envelopes, gapfilling, media optimization.
jaechang-hits/SciAgent-Skills
Read, write, and edit ChemDraw CDX/CDXML files with RDKit's rdkit.Chem.rdChemDraw plus direct XML editing, always paired with a rendered PNG.
jaechang-hits/SciAgent-Skills
Programmatic PubMed access via NCBI E-utilities REST API. An agent skill from jaechang-hits/SciAgent-Skills.
jaechang-hits/SciAgent-Skills
Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills.
Works with
Categories
Hardware-agnostic Python liquid-handler library: portable scripts run on Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulator without vendor lock-in. Pylabrobot is an agent skill from jaechang-hits/SciAgent-Skills. Hardware-agnostic Python liquid-handler library: portable scripts run on Hamilton STAR, Tecan Freedom EVO, Opentrons OT-2, or a simulator without vendor lock-in.
Pylabrobot fits situations like: research & Science work in your project.
Run `npx skills add jaechang-hits/SciAgent-Skills --skill pylabrobot -a claude-code`. Or copy the skill folder (skills/lab-automation/pylabrobot in jaechang-hits/SciAgent-Skills) into .claude/skills/pylabrobot in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jaechang-hits/SciAgent-Skills --skill pylabrobot -a codex`. Or copy the skill folder (skills/lab-automation/pylabrobot in jaechang-hits/SciAgent-Skills) into .agents/skills/pylabrobot 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 jaechang-hits/SciAgent-Skills --skill pylabrobot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pylabrobot, .gemini/skills/pylabrobot, .github/skills/pylabrobot and .opencode/skills/pylabrobot in your project.
Going by SKILL.md and its folder, Pylabrobot needs the command-line tools its instructions call (pip). Our summary lists: Python 3.
SKILL.md names 4 domains. As links in the text: docs.pylabrobot.org, github.com, cell.com and pypi.org. 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.
Pylabrobot is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k 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.
Skills that share tags, products or a category with Pylabrobot: GitHub Deep Research (bytedance/deer-flow, 84k stars), Last30days (mvanhorn/last30days-skill, 64k stars), Networkx (zLanqing/codex-claude-academic-skills, 4.7k stars) and Nature-Style Scientific Figures (Yuan1z0825/nature-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jaechang-hits (a GitHub user) maintains it in jaechang-hits/SciAgent-Skills, which has 374 GitHub stars. The repository holds 169 skills in this directory. The repository was last updated on September 29, 2026.
Source: jaechang-hits/SciAgent-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.