Agent Skillssynthetic-sciences/openscience › opentrons-integration

opentrons-integration

GitHub

用于为Opentrons OT-2和Flex机器人编写Protocol API v2协议。涵盖液体处理、硬件模块控制、板架配置及复杂移液操作,支持仿真测试,适用于生产级自动化流程开发。

backend/cli/skills/biology/opentrons-integration/SKILL.md synthetic-sciences/openscience

Trigger Scenarios

编写Opentrons Protocol API v2协议 自动化Flex或OT-2机器人的液体处理工作流 控制温度或磁吸等硬件模块 设置板架配置和甲板布局

Install

npx skills add synthetic-sciences/openscience --skill opentrons-integration -g -y
More Options

Non-standard path

npx skills add https://github.com/synthetic-sciences/openscience/tree/main/backend/cli/skills/biology/opentrons-integration -g -y

Use without installing

npx skills use synthetic-sciences/openscience@opentrons-integration

指定 Agent (Claude Code)

npx skills add synthetic-sciences/openscience --skill opentrons-integration -a claude-code -g -y

安装 repo 全部 skill

npx skills add synthetic-sciences/openscience --all -g -y

预览 repo 内 skill

npx skills add synthetic-sciences/openscience --list

SKILL.md

Frontmatter
{
    "name": "opentrons-integration",
    "license": "Unknown",
    "category": "biology",
    "metadata": {
        "skill-author": "Synthetic Sciences"
    },
    "description": "Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot."
}

Opentrons Integration

Overview

Opentrons is a Python-based lab automation platform for Flex and OT-2 robots. Write Protocol API v2 protocols for liquid handling, control hardware modules (heater-shaker, thermocycler), manage labware, for automated pipetting workflows.

When to Use This Skill

This skill should be used when:

  • Writing Opentrons Protocol API v2 protocols in Python
  • Automating liquid handling workflows on Flex or OT-2 robots
  • Controlling hardware modules (temperature, magnetic, heater-shaker, thermocycler)
  • Setting up labware configurations and deck layouts
  • Implementing complex pipetting operations (serial dilutions, plate replication, PCR setup)
  • Managing tip usage and optimizing protocol efficiency
  • Working with multi-channel pipettes for 96-well plate operations
  • Simulating and testing protocols before robot execution

Core Capabilities

1. Protocol Structure and Metadata

Every Opentrons protocol follows a standard structure:

from opentrons import protocol_api

# Metadata
metadata = {
    'protocolName': 'My Protocol',
    'author': 'Name <email@example.com>',
    'description': 'Protocol description',
    'apiLevel': '2.19'  # Use latest available API version
}

# Requirements (optional)
requirements = {
    'robotType': 'Flex',  # or 'OT-2'
    'apiLevel': '2.19'
}

# Run function
def run(protocol: protocol_api.ProtocolContext):
    # Protocol commands go here
    pass

Key elements:

  • Import protocol_api from opentrons
  • Define metadata dict with protocolName, author, description, apiLevel
  • Optional requirements dict for robot type and API version
  • Implement run() function receiving ProtocolContext as parameter
  • All protocol logic goes inside the run() function

2. Loading Hardware

Loading Instruments (Pipettes):

def run(protocol: protocol_api.ProtocolContext):
    # Load pipette on specific mount
    left_pipette = protocol.load_instrument(
        'p1000_single_flex',  # Instrument name
        'left',               # Mount: 'left' or 'right'
        tip_racks=[tip_rack]  # List of tip rack labware objects
    )

Common pipette names:

  • Flex: p50_single_flex, p1000_single_flex, p50_multi_flex, p1000_multi_flex
  • OT-2: p20_single_gen2, p300_single_gen2, p1000_single_gen2, p20_multi_gen2, p300_multi_gen2

Loading Labware:

# Load labware directly on deck
plate = protocol.load_labware(
    'corning_96_wellplate_360ul_flat',  # Labware API name
    'D1',                                # Deck slot (Flex: A1-D3, OT-2: 1-11)
    label='Sample Plate'                 # Optional display label
)

# Load tip rack
tip_rack = protocol.load_labware('opentrons_flex_96_tiprack_1000ul', 'C1')

# Load labware on adapter
adapter = protocol.load_adapter('opentrons_flex_96_tiprack_adapter', 'B1')
tips = adapter.load_labware('opentrons_flex_96_tiprack_200ul')

Loading Modules:

# Temperature module
temp_module = protocol.load_module('temperature module gen2', 'D3')
temp_plate = temp_module.load_labware('corning_96_wellplate_360ul_flat')

# Magnetic module
mag_module = protocol.load_module('magnetic module gen2', 'C2')
mag_plate = mag_module.load_labware('nest_96_wellplate_100ul_pcr_full_skirt')

# Heater-Shaker module
hs_module = protocol.load_module('heaterShakerModuleV1', 'D1')
hs_plate = hs_module.load_labware('corning_96_wellplate_360ul_flat')

# Thermocycler module (takes up specific slots automatically)
tc_module = protocol.load_module('thermocyclerModuleV2')
tc_plate = tc_module.load_labware('nest_96_wellplate_100ul_pcr_full_skirt')

3. Liquid Handling Operations

Basic Operations:

# Pick up tip
pipette.pick_up_tip()

# Aspirate (draw liquid in)
pipette.aspirate(
    volume=100,           # Volume in µL
    location=source['A1'] # Well or location object
)

# Dispense (expel liquid)
pipette.dispense(
    volume=100,
    location=dest['B1']
)

# Drop tip
pipette.drop_tip()

# Return tip to rack
pipette.return_tip()

Complex Operations:

# Transfer (combines pick_up, aspirate, dispense, drop_tip)
pipette.transfer(
    volume=100,
    source=source_plate['A1'],
    dest=dest_plate['B1'],
    new_tip='always'  # 'always', 'once', or 'never'
)

# Distribute (one source to multiple destinations)
pipette.distribute(
    volume=50,
    source=reservoir['A1'],
    dest=[plate['A1'], plate['A2'], plate['A3']],
    new_tip='once'
)

# Consolidate (multiple sources to one destination)
pipette.consolidate(
    volume=50,
    source=[plate['A1'], plate['A2'], plate['A3']],
    dest=reservoir['A1'],
    new_tip='once'
)

Advanced Techniques:

# Mix (aspirate and dispense in same location)
pipette.mix(
    repetitions=3,
    volume=50,
    location=plate['A1']
)

# Air gap (prevent dripping)
pipette.aspirate(100, source['A1'])
pipette.air_gap(20)  # 20µL air gap
pipette.dispense(120, dest['A1'])

# Blow out (expel remaining liquid)
pipette.blow_out(location=dest['A1'].top())

# Touch tip (remove droplets on tip exterior)
pipette.touch_tip(location=plate['A1'])

Flow Rate Control:

# Set flow rates (µL/s)
pipette.flow_rate.aspirate = 150
pipette.flow_rate.dispense = 300
pipette.flow_rate.blow_out = 400

4. Accessing Wells and Locations

Well Access Methods:

# By name
well_a1 = plate['A1']

# By index
first_well = plate.wells()[0]

# All wells
all_wells = plate.wells()  # Returns list

# By rows
rows = plate.rows()  # Returns list of lists
row_a = plate.rows()[0]  # All wells in row A

# By columns
columns = plate.columns()  # Returns list of lists
column_1 = plate.columns()[0]  # All wells in column 1

# Wells by name (dictionary)
wells_dict = plate.wells_by_name()  # {'A1': Well, 'A2': Well, ...}

Location Methods:

# Top of well (default: 1mm below top)
pipette.aspirate(100, well.top())
pipette.aspirate(100, well.top(z=5))  # 5mm above top

# Bottom of well (default: 1mm above bottom)
pipette.aspirate(100, well.bottom())
pipette.aspirate(100, well.bottom(z=2))  # 2mm above bottom

# Center of well
pipette.aspirate(100, well.center())

5. Hardware Module Control

Temperature Module:

# Set temperature
temp_module.set_temperature(celsius=4)

# Wait for temperature
temp_module.await_temperature(celsius=4)

# Deactivate
temp_module.deactivate()

# Check status
current_temp = temp_module.temperature  # Current temperature
target_temp = temp_module.target  # Target temperature

Magnetic Module:

# Engage (raise magnets)
mag_module.engage(height_from_base=10)  # mm from labware base

# Disengage (lower magnets)
mag_module.disengage()

# Check status
is_engaged = mag_module.status  # 'engaged' or 'disengaged'

Heater-Shaker Module:

# Set temperature
hs_module.set_target_temperature(celsius=37)

# Wait for temperature
hs_module.wait_for_temperature()

# Set shake speed
hs_module.set_and_wait_for_shake_speed(rpm=500)

# Close labware latch
hs_module.close_labware_latch()

# Open labware latch
hs_module.open_labware_latch()

# Deactivate heater
hs_module.deactivate_heater()

# Deactivate shaker
hs_module.deactivate_shaker()

Thermocycler Module:

# Open lid
tc_module.open_lid()

# Close lid
tc_module.close_lid()

# Set lid temperature
tc_module.set_lid_temperature(celsius=105)

# Set block temperature
tc_module.set_block_temperature(
    temperature=95,
    hold_time_seconds=30,
    hold_time_minutes=0.5,
    block_max_volume=50  # µL per well
)

# Execute profile (PCR cycling)
profile = [
    {'temperature': 95, 'hold_time_seconds': 30},
    {'temperature': 57, 'hold_time_seconds': 30},
    {'temperature': 72, 'hold_time_seconds': 60}
]
tc_module.execute_profile(
    steps=profile,
    repetitions=30,
    block_max_volume=50
)

# Deactivate
tc_module.deactivate_lid()
tc_module.deactivate_block()

Absorbance Plate Reader:

# Initialize and read
result = plate_reader.read(wavelengths=[450, 650])

# Access readings
absorbance_data = result  # Dict with wavelength keys

6. Liquid Tracking and Labeling

Define Liquids:

# Define liquid types
water = protocol.define_liquid(
    name='Water',
    description='Ultrapure water',
    display_color='#0000FF'  # Hex color code
)

sample = protocol.define_liquid(
    name='Sample',
    description='Cell lysate sample',
    display_color='#FF0000'
)

Load Liquids into Wells:

# Load liquid into specific wells
reservoir['A1'].load_liquid(liquid=water, volume=50000)  # µL
plate['A1'].load_liquid(liquid=sample, volume=100)

# Mark wells as empty
plate['B1'].load_empty()

7. Protocol Control and Utilities

Execution Control:

# Pause protocol
protocol.pause(msg='Replace tip box and resume')

# Delay
protocol.delay(seconds=60)
protocol.delay(minutes=5)

# Comment (appears in logs)
protocol.comment('Starting serial dilution')

# Home robot
protocol.home()

Conditional Logic:

# Check if simulating
if protocol.is_simulating():
    protocol.comment('Running in simulation mode')
else:
    protocol.comment('Running on actual robot')

Rail Lights (Flex only):

# Turn lights on
protocol.set_rail_lights(on=True)

# Turn lights off
protocol.set_rail_lights(on=False)

8. Multi-Channel and 8-Channel Pipetting

When using multi-channel pipettes:

# Load 8-channel pipette
multi_pipette = protocol.load_instrument(
    'p300_multi_gen2',
    'left',
    tip_racks=[tips]
)

# Access entire column with single well reference
multi_pipette.transfer(
    volume=100,
    source=source_plate['A1'],  # Accesses entire column 1
    dest=dest_plate['A1']       # Dispenses to entire column 1
)

# Use rows() for row-wise operations
for row in plate.rows():
    multi_pipette.transfer(100, reservoir['A1'], row[0])

9. Common Protocol Patterns

Serial Dilution:

def run(protocol: protocol_api.ProtocolContext):
    # Load labware
    tips = protocol.load_labware('opentrons_flex_96_tiprack_200ul', 'D1')
    reservoir = protocol.load_labware('nest_12_reservoir_15ml', 'D2')
    plate = protocol.load_labware('corning_96_wellplate_360ul_flat', 'D3')

    # Load pipette
    p300 = protocol.load_instrument('p300_single_flex', 'left', tip_racks=[tips])

    # Add diluent to all wells except first
    p300.transfer(100, reservoir['A1'], plate.rows()[0][1:])

    # Serial dilution across row
    p300.transfer(
        100,
        plate.rows()[0][:11],  # Source: wells 0-10
        plate.rows()[0][1:],   # Dest: wells 1-11
        mix_after=(3, 50),     # Mix 3x with 50µL after dispense
        new_tip='always'
    )

Plate Replication:

def run(protocol: protocol_api.ProtocolContext):
    # Load labware
    tips = protocol.load_labware('opentrons_flex_96_tiprack_1000ul', 'C1')
    source = protocol.load_labware('corning_96_wellplate_360ul_flat', 'D1')
    dest = protocol.load_labware('corning_96_wellplate_360ul_flat', 'D2')

    # Load pipette
    p1000 = protocol.load_instrument('p1000_single_flex', 'left', tip_racks=[tips])

    # Transfer from all wells in source to dest
    p1000.transfer(
        100,
        source.wells(),
        dest.wells(),
        new_tip='always'
    )

PCR Setup:

def run(protocol: protocol_api.ProtocolContext):
    # Load thermocycler
    tc_mod = protocol.load_module('thermocyclerModuleV2')
    tc_plate = tc_mod.load_labware('nest_96_wellplate_100ul_pcr_full_skirt')

    # Load tips and reagents
    tips = protocol.load_labware('opentrons_flex_96_tiprack_200ul', 'C1')
    reagents = protocol.load_labware('opentrons_24_tuberack_nest_1.5ml_snapcap', 'D1')

    # Load pipette
    p300 = protocol.load_instrument('p300_single_flex', 'left', tip_racks=[tips])

    # Open thermocycler lid
    tc_mod.open_lid()

    # Distribute master mix
    p300.distribute(
        20,
        reagents['A1'],
        tc_plate.wells(),
        new_tip='once'
    )

    # Add samples (example for first 8 wells)
    for i, well in enumerate(tc_plate.wells()[:8]):
        p300.transfer(5, reagents.wells()[i+1], well, new_tip='always')

    # Run PCR
    tc_mod.close_lid()
    tc_mod.set_lid_temperature(105)

    # PCR profile
    tc_mod.set_block_temperature(95, hold_time_seconds=180)

    profile = [
        {'temperature': 95, 'hold_time_seconds': 15},
        {'temperature': 60, 'hold_time_seconds': 30},
        {'temperature': 72, 'hold_time_seconds': 30}
    ]
    tc_mod.execute_profile(steps=profile, repetitions=35, block_max_volume=25)

    tc_mod.set_block_temperature(72, hold_time_minutes=5)
    tc_mod.set_block_temperature(4)

    tc_mod.deactivate_lid()
    tc_mod.open_lid()

Best Practices

  1. Always specify API level: Use the latest stable API version in metadata
  2. Use meaningful labels: Label labware for easier identification in logs
  3. Check tip availability: Ensure sufficient tips for protocol completion
  4. Add comments: Use protocol.comment() for debugging and logging
  5. Simulate first: Always test protocols in simulation before running on robot
  6. Handle errors gracefully: Add pauses for manual intervention when needed
  7. Consider timing: Use delays when protocols require incubation periods
  8. Track liquids: Use liquid tracking for better setup validation
  9. Optimize tip usage: Use new_tip='once' when appropriate to save tips
  10. Control flow rates: Adjust flow rates for viscous or volatile liquids

Troubleshooting

Common Issues:

  • Out of tips: Verify tip rack capacity matches protocol requirements
  • Labware collisions: Check deck layout for spatial conflicts
  • Volume errors: Ensure volumes don't exceed well or pipette capacities
  • Module not responding: Verify module is properly connected and firmware is updated
  • Inaccurate volumes: Calibrate pipettes and check for air bubbles
  • Protocol fails in simulation: Check API version compatibility and labware definitions

Resources

For detailed API documentation, see references/api_reference.md in this skill directory.

For example protocol templates, see scripts/ directory.

Version History

  • e9844a4 Current 2026-07-11 17:20

Same Skill Collection

.openscience/skill/bun-file-io/SKILL.md
backend/cli/skills/biology/anndata/SKILL.md
backend/cli/skills/biology/benchling-integration/SKILL.md
backend/cli/skills/biology/bioimage-analysis/SKILL.md
backend/cli/skills/biology/bioservices/SKILL.md
backend/cli/skills/biology/cancer-genomics-analysis/SKILL.md
backend/cli/skills/biology/clinical-imaging/SKILL.md
backend/cli/skills/biology/clinical-reports/SKILL.md
backend/cli/skills/biology/cobrapy/SKILL.md
backend/cli/skills/biology/curated-bio-datasets/SKILL.md
backend/cli/skills/biology/deeptools/SKILL.md
backend/cli/skills/biology/dnanexus-integration/SKILL.md
backend/cli/skills/biology/etetoolkit/SKILL.md
backend/cli/skills/biology/flow-cytometry-analysis/SKILL.md
backend/cli/skills/biology/flowio/SKILL.md
backend/cli/skills/biology/gget/SKILL.md
backend/cli/skills/biology/glycobiology/SKILL.md
backend/cli/skills/biology/histolab/SKILL.md
backend/cli/skills/biology/immunology-assays/SKILL.md
backend/cli/skills/biology/latchbio-integration/SKILL.md
backend/cli/skills/biology/microbial-dynamics/SKILL.md
backend/cli/skills/biology/molecular-cloning/SKILL.md
backend/cli/skills/biology/neurokit2/SKILL.md
backend/cli/skills/biology/neuropixels-analysis/SKILL.md
backend/cli/skills/biology/omero-integration/SKILL.md
backend/cli/skills/biology/pathml/SKILL.md
backend/cli/skills/biology/pharmacology-wetlab/SKILL.md
backend/cli/skills/biology/protocolsio-integration/SKILL.md
backend/cli/skills/biology/pydeseq2/SKILL.md
backend/cli/skills/biology/pyhealth/SKILL.md
backend/cli/skills/biology/pylabrobot/SKILL.md
backend/cli/skills/biology/pysam/SKILL.md
backend/cli/skills/biology/scanpy/SKILL.md
backend/cli/skills/biology/scikit-bio/SKILL.md
backend/cli/skills/biology/scikit-survival/SKILL.md
backend/cli/skills/biology/scvi-tools/SKILL.md
backend/cli/skills/biology/synthetic-biology/SKILL.md
backend/cli/skills/biology/treatment-plans/SKILL.md
backend/cli/skills/chemistry/admet-prediction/SKILL.md
backend/cli/skills/chemistry/admet-reasoning/SKILL.md
backend/cli/skills/chemistry/binding-affinity/SKILL.md
backend/cli/skills/chemistry/datamol/SKILL.md
backend/cli/skills/chemistry/deepchem/SKILL.md
backend/cli/skills/chemistry/denovo-design/SKILL.md
backend/cli/skills/chemistry/diffdock/SKILL.md
backend/cli/skills/chemistry/drug-design/SKILL.md
backend/cli/skills/chemistry/hypogenic/SKILL.md
backend/cli/skills/chemistry/matchms/SKILL.md
backend/cli/skills/chemistry/medchem/SKILL.md
backend/cli/skills/chemistry/molecular-docking/SKILL.md
backend/cli/skills/chemistry/molecular-optimization/SKILL.md
backend/cli/skills/chemistry/molecular-rag/SKILL.md
backend/cli/skills/chemistry/molecule-visualization/SKILL.md
backend/cli/skills/chemistry/molfeat/SKILL.md
backend/cli/skills/chemistry/pocket-detection/SKILL.md
backend/cli/skills/chemistry/pyopenms/SKILL.md
backend/cli/skills/chemistry/pytdc/SKILL.md
backend/cli/skills/chemistry/rdkit/SKILL.md
backend/cli/skills/chemistry/smiles-validation/SKILL.md
backend/cli/skills/chemistry/structure-prediction/SKILL.md
backend/cli/skills/chemistry/torchdrug/SKILL.md
backend/cli/skills/cloud-compute/fireworks-ai/SKILL.md
backend/cli/skills/cloud-compute/lambda-labs/SKILL.md
backend/cli/skills/cloud-compute/modal-ml-training/SKILL.md
backend/cli/skills/cloud-compute/modal-research-gpu/SKILL.md
backend/cli/skills/cloud-compute/modal/SKILL.md
backend/cli/skills/cloud-compute/skypilot/SKILL.md
backend/cli/skills/cloud-compute/tensorpool/SKILL.md
backend/cli/skills/cloud-compute/tinker-training-cost/SKILL.md
backend/cli/skills/cloud-compute/tinker/SKILL.md
backend/cli/skills/cloud-compute/together-ai/SKILL.md
backend/cli/skills/coding/arboreto/SKILL.md
backend/cli/skills/coding/audiocraft/SKILL.md
backend/cli/skills/coding/denario/SKILL.md
backend/cli/skills/coding/gtars/SKILL.md
backend/cli/skills/coding/multi-objective-optimization/SKILL.md
backend/cli/skills/coding/networkx/SKILL.md
backend/cli/skills/coding/pymc/SKILL.md
backend/cli/skills/coding/pymoo/SKILL.md
backend/cli/skills/coding/scikit-learn/SKILL.md
backend/cli/skills/coding/simpy/SKILL.md
backend/cli/skills/coding/slime/SKILL.md
backend/cli/skills/coding/statistical-analysis/SKILL.md
backend/cli/skills/coding/statsmodels/SKILL.md
backend/cli/skills/coding/torch_geometric/SKILL.md
backend/cli/skills/coding/umap-learn/SKILL.md
backend/cli/skills/data-engineering/aeon/SKILL.md
backend/cli/skills/data-engineering/dask/SKILL.md
backend/cli/skills/data-engineering/hdf5-pde-data-loading/SKILL.md
backend/cli/skills/data-engineering/hugging-face-datasets/SKILL.md
backend/cli/skills/data-engineering/polars/SKILL.md
backend/cli/skills/data-engineering/vaex/SKILL.md
backend/cli/skills/data-engineering/zarr-python/SKILL.md
backend/cli/skills/databases/alphafold-database/SKILL.md
backend/cli/skills/databases/biorxiv-database/SKILL.md
backend/cli/skills/databases/brenda-database/SKILL.md
backend/cli/skills/databases/cellxgene-census/SKILL.md
backend/cli/skills/databases/chembl-database/SKILL.md
backend/cli/skills/databases/clinicaltrials-database/SKILL.md
backend/cli/skills/databases/clinpgx-database/SKILL.md
backend/cli/skills/databases/clinvar-database/SKILL.md
backend/cli/skills/databases/cosmic-database/SKILL.md
backend/cli/skills/databases/datacommons-client/SKILL.md
backend/cli/skills/databases/drugbank-database/SKILL.md
backend/cli/skills/databases/ena-database/SKILL.md
backend/cli/skills/databases/ensembl-database/SKILL.md
backend/cli/skills/databases/fda-database/SKILL.md
backend/cli/skills/databases/gene-database/SKILL.md
backend/cli/skills/databases/gwas-database/SKILL.md
backend/cli/skills/databases/hmdb-database/SKILL.md
backend/cli/skills/databases/imaging-data-commons/SKILL.md
backend/cli/skills/databases/kegg-database/SKILL.md
backend/cli/skills/databases/metabolomics-workbench-database/SKILL.md
backend/cli/skills/databases/openalex-database/SKILL.md
backend/cli/skills/databases/opentargets-database/SKILL.md
backend/cli/skills/databases/pdb-database/SKILL.md
backend/cli/skills/databases/pubchem-database/SKILL.md
backend/cli/skills/databases/pubmed-database/SKILL.md
backend/cli/skills/databases/reactome-database/SKILL.md
backend/cli/skills/databases/string-database/SKILL.md
backend/cli/skills/databases/uniprot-database/SKILL.md
backend/cli/skills/databases/zinc-database/SKILL.md
backend/cli/skills/document-parsing/liteparse/SKILL.md
backend/cli/skills/llm-tools/autogpt/SKILL.md
backend/cli/skills/llm-tools/blip-2/SKILL.md
backend/cli/skills/llm-tools/chroma/SKILL.md
backend/cli/skills/llm-tools/clip/SKILL.md
backend/cli/skills/llm-tools/constitutional-ai/SKILL.md
backend/cli/skills/llm-tools/crewai/SKILL.md
backend/cli/skills/llm-tools/dspy/SKILL.md
backend/cli/skills/llm-tools/faiss/SKILL.md
backend/cli/skills/llm-tools/guidance/SKILL.md
backend/cli/skills/llm-tools/hugging-face-cli/SKILL.md
backend/cli/skills/llm-tools/hugging-face-tool-builder/SKILL.md
backend/cli/skills/llm-tools/huggingface-tokenizers/SKILL.md
backend/cli/skills/llm-tools/instructor/SKILL.md
backend/cli/skills/llm-tools/langchain/SKILL.md
backend/cli/skills/llm-tools/langsmith/SKILL.md
backend/cli/skills/llm-tools/llamaguard/SKILL.md
backend/cli/skills/llm-tools/llamaindex/SKILL.md
backend/cli/skills/llm-tools/llava/SKILL.md
backend/cli/skills/llm-tools/llm-as-judge-evaluation/SKILL.md
backend/cli/skills/llm-tools/long-context/SKILL.md
backend/cli/skills/llm-tools/nemo-guardrails/SKILL.md
backend/cli/skills/llm-tools/outlines/SKILL.md
backend/cli/skills/llm-tools/pinecone/SKILL.md
backend/cli/skills/llm-tools/qdrant/SKILL.md
backend/cli/skills/llm-tools/segment-anything/SKILL.md
backend/cli/skills/llm-tools/sentence-transformers/SKILL.md
backend/cli/skills/llm-tools/sentencepiece/SKILL.md
backend/cli/skills/llm-tools/stable-diffusion/SKILL.md
backend/cli/skills/llm-tools/transformers/SKILL.md
backend/cli/skills/llm-tools/whisper/SKILL.md
backend/cli/skills/ml-inference/gguf/SKILL.md
backend/cli/skills/ml-inference/groq/SKILL.md
backend/cli/skills/ml-inference/llama-cpp/SKILL.md
backend/cli/skills/ml-inference/miles/SKILL.md
backend/cli/skills/ml-inference/phoenix/SKILL.md
backend/cli/skills/ml-inference/sglang/SKILL.md
backend/cli/skills/ml-inference/speculative-decoding/SKILL.md
backend/cli/skills/ml-inference/tensorrt-llm/SKILL.md
backend/cli/skills/ml-inference/vllm/SKILL.md
backend/cli/skills/ml-training/accelerate/SKILL.md
backend/cli/skills/ml-training/awq/SKILL.md
backend/cli/skills/ml-training/axolotl/SKILL.md
backend/cli/skills/ml-training/bigcode-evaluation-harness/SKILL.md
backend/cli/skills/ml-training/bitsandbytes/SKILL.md
backend/cli/skills/ml-training/colab-finetuning/SKILL.md
backend/cli/skills/ml-training/deepspeed/SKILL.md
backend/cli/skills/ml-training/flash-attention/SKILL.md
backend/cli/skills/ml-training/geniml/SKILL.md
backend/cli/skills/ml-training/gptq/SKILL.md
backend/cli/skills/ml-training/grpo-rl-training/SKILL.md
backend/cli/skills/ml-training/hqq/SKILL.md
backend/cli/skills/ml-training/hugging-face-evaluation/SKILL.md
backend/cli/skills/ml-training/knowledge-distillation/SKILL.md
backend/cli/skills/ml-training/litgpt/SKILL.md
backend/cli/skills/ml-training/llama-factory/SKILL.md
backend/cli/skills/ml-training/lm-evaluation-harness/SKILL.md
backend/cli/skills/ml-training/mamba/SKILL.md
backend/cli/skills/ml-training/megatron-core/SKILL.md
backend/cli/skills/ml-training/ml-benchmark-evaluation/SKILL.md
backend/cli/skills/ml-training/mlflow/SKILL.md
backend/cli/skills/ml-training/model-economics/SKILL.md
backend/cli/skills/ml-training/model-merging/SKILL.md
backend/cli/skills/ml-training/model-pruning/SKILL.md
backend/cli/skills/ml-training/moe-training/SKILL.md
backend/cli/skills/ml-training/nanogpt/SKILL.md
backend/cli/skills/ml-training/nemo-curator/SKILL.md
backend/cli/skills/ml-training/nnsight/SKILL.md
backend/cli/skills/ml-training/openrlhf/SKILL.md
backend/cli/skills/ml-training/peft/SKILL.md
backend/cli/skills/ml-training/prime-intellect-lab/SKILL.md
backend/cli/skills/ml-training/pufferlib/SKILL.md
backend/cli/skills/ml-training/pytorch-fsdp/SKILL.md
backend/cli/skills/ml-training/pytorch-lightning/SKILL.md
backend/cli/skills/ml-training/pyvene/SKILL.md
backend/cli/skills/ml-training/rwkv/SKILL.md
backend/cli/skills/ml-training/saelens/SKILL.md
backend/cli/skills/ml-training/simpo/SKILL.md
backend/cli/skills/ml-training/stable-baselines3/SKILL.md
backend/cli/skills/ml-training/tensorboard/SKILL.md
backend/cli/skills/ml-training/torchforge/SKILL.md
backend/cli/skills/ml-training/torchtitan/SKILL.md
backend/cli/skills/ml-training/training-data-pipeline/SKILL.md
backend/cli/skills/ml-training/transformer-lens/SKILL.md
backend/cli/skills/ml-training/trl-fine-tuning/SKILL.md
backend/cli/skills/ml-training/unsloth/SKILL.md
backend/cli/skills/ml-training/verl/SKILL.md
backend/cli/skills/other/hugging-face-trackio/SKILL.md
backend/cli/skills/other/labarchive-integration/SKILL.md
backend/cli/skills/other/skill-installer/SKILL.md
backend/cli/skills/physics/astropy/SKILL.md
backend/cli/skills/physics/autoregressive-neural-pde-solver/SKILL.md
backend/cli/skills/physics/bayesian-inference/SKILL.md
backend/cli/skills/physics/conservation-law-discovery/SKILL.md
backend/cli/skills/physics/dimensional-analysis/SKILL.md
backend/cli/skills/physics/dynamical-systems/SKILL.md
backend/cli/skills/physics/fluid-dynamics/SKILL.md
backend/cli/skills/physics/fluidsim/SKILL.md
backend/cli/skills/physics/hamiltonian-mechanics/SKILL.md
backend/cli/skills/physics/neural-operator/SKILL.md
backend/cli/skills/physics/ode-solver/SKILL.md
backend/cli/skills/physics/pde-solver/SKILL.md
backend/cli/skills/physics/physics-databases/SKILL.md
backend/cli/skills/physics/physics-fitting/SKILL.md
backend/cli/skills/physics/physics-visualization/SKILL.md
backend/cli/skills/physics/pinn-training/SKILL.md
backend/cli/skills/physics/shock-capturing-neural-operators/SKILL.md
backend/cli/skills/physics/sindy-identification/SKILL.md
backend/cli/skills/physics/spectral-analysis/SKILL.md
backend/cli/skills/physics/statistical-mechanics/SKILL.md
backend/cli/skills/physics/symbolic-regression/SKILL.md
backend/cli/skills/physics/wave-propagation/SKILL.md
backend/cli/skills/quantum/cirq/SKILL.md
backend/cli/skills/quantum/pennylane/SKILL.md
backend/cli/skills/quantum/qiskit/SKILL.md
backend/cli/skills/quantum/qutip/SKILL.md
backend/cli/skills/research/hypothesis-generation/SKILL.md
backend/cli/skills/research/initialize-atlas-graph/SKILL.md
backend/cli/skills/research/market-research-reports/SKILL.md
backend/cli/skills/research/peer-review/SKILL.md
backend/cli/skills/research/research-grants/SKILL.md
backend/cli/skills/research/research-lookup/SKILL.md
backend/cli/skills/research/scientific-brainstorming/SKILL.md
backend/cli/skills/research/scientific-critical-thinking/SKILL.md
backend/cli/skills/visualization/dna-visualization/SKILL.md
backend/cli/skills/visualization/matplotlib/SKILL.md
backend/cli/skills/visualization/plotly/SKILL.md
backend/cli/skills/visualization/protein-diagram/SKILL.md
backend/cli/skills/visualization/scientific-visualization/SKILL.md
backend/cli/skills/visualization/seaborn/SKILL.md
backend/cli/skills/writing/citation-management/SKILL.md
backend/cli/skills/writing/hugging-face-paper-publisher/SKILL.md
backend/cli/skills/writing/latex-posters/SKILL.md
backend/cli/skills/writing/literature-review/SKILL.md
backend/cli/skills/writing/ml-paper-writing/SKILL.md
backend/cli/skills/writing/pptx-posters/SKILL.md
backend/cli/skills/writing/scientific-writing/SKILL.md
backend/cli/skills/writing/venue-templates/SKILL.md
backend/cli/skills/biology/clinical-decision-support/SKILL.md
backend/cli/skills/biology/esm/SKILL.md
backend/cli/skills/biology/lamindb/SKILL.md
backend/cli/skills/biology/pydicom/SKILL.md
backend/cli/skills/coding/exploratory-data-analysis/SKILL.md
backend/cli/skills/coding/matlab/SKILL.md
backend/cli/skills/coding/shap/SKILL.md
backend/cli/skills/coding/sympy/SKILL.md
backend/cli/skills/data-engineering/geopandas/SKILL.md
backend/cli/skills/ml-training/hugging-face-model-trainer/SKILL.md
backend/cli/skills/other/get-available-resources/SKILL.md
backend/cli/skills/other/hugging-face-jobs/SKILL.md
backend/cli/skills/other/iso-13485-certification/SKILL.md

Metadata

Files
0
Version
e9844a4
Hash
ae7c8fff
Indexed
2026-07-11 17:20

Home - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-14 10:54
浙ICP备14020137号-1 $Map of visitor$