New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Protocol Generation From Description

by InternScience in InternScience/scp

Generate detailed laboratory protocols from natural language descriptions using AI, producing step-by-step experimental procedures ready for lab execution.

MITAuto-check passed

Install Protocol Generation From Description

skills CLI
$ npx skills add InternScience/scp --skill protocol-generation-from-description -a claude-code

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

GitHub CLI
$ gh skill install InternScience/scp protocol-generation-from-description --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/InternScience/scp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/protocol-generation .claude/skills/protocol-generation-from-description && 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/

Facts

Skill name
protocol-generation-from-description
GitHub stars
169
Used in
1 other repo
Token cost
~1.4k tokens
SKILL.md length
384 words
Files
1
Skills in repo
73
Repo updated
First seen
Licence
MIT

At a glance

Generate detailed laboratory protocols from natural language descriptions using AI, producing step-by-step experimental procedures ready for lab execution.

  • Works in 2 steps: MCP Server Definition → Protocol Generation from User Description
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Protocol Generation From Description is an agent skill from InternScience/scp. Generate detailed laboratory protocols from natural language descriptions using AI, producing step-by-step experimental procedures ready for lab execution.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is MIT.

Example prompts

  • “/protocol-generation-from-description”

Requirements

  • Python 3

Workflow steps

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

  1. MCP Server Definition
  2. Protocol Generation from User Description

What it can do on your machine

Read from SKILL.md and the folder at commit cea5398. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Protocol Generation From Description loads about 1.4k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 InternScience/scp at commit cea5398, republished under its MIT licence (© InternScience). 384 words, ~1,425 tokens.

Download SKILL.mdSave it as .claude/skills/protocol-generation-from-description/SKILL.md (or your agent's skills folder).
name
protocol-generation-from-description
description
Generate detailed laboratory protocols from natural language descriptions using AI, producing step-by-step experimental procedures ready for lab execution.
license
MIT license
metadata.skill-author
PJLab

Laboratory Protocol Generation Workflow

Usage

1. MCP Server Definition

Use the same DrugSDAClient class pattern with Thoth-Plan server.

2. Protocol Generation from User Description

This workflow generates detailed laboratory protocols from natural language descriptions, useful for experimental planning and automation.

Workflow Steps:

  1. Input User Description - Provide natural language description of desired protocol
  2. Generate Detailed Protocol - AI generates step-by-step experimental procedure
  3. Optional: Convert to Executable Format - Transform protocol to machine-readable JSON for automation

Implementation:

python
client = DrugSDAClient("https://scp.intern-ai.org.cn/api/v1/mcp/19/Thoth-Plan")
if not await client.connect():
    print("connection failed")
    return

## Step 1: Provide protocol description
user_prompt = """
I need a PCR protocol for amplifying a 500bp DNA fragment.
Use a standard Taq polymerase with the following conditions:
- Annealing temperature: 55°C
- Extension time: 30 seconds
- 30 cycles total
Include primer concentrations and buffer composition.
"""

## Step 2: Generate detailed protocol
result = await client.session.call_tool(
    "protocol_generation",
    arguments={
        "user_prompt": user_prompt
    }
)

protocol_text = client.parse_result(result)["protocol"]

print("Generated Protocol:")
print("=" * 80)
print(protocol_text)
print("=" * 80)

## Step 3 (Optional): Convert to executable JSON for lab automation
result = await client.session.call_tool(
    "generate_executable_json",
    arguments={
        "protocol": protocol_text
    }
)

executable_json = client.parse_result(result)["executable_json"]
print("\nExecutable JSON for lab automation:")
print(executable_json)

## Step 4 (Optional): Execute protocol via lab automation system
result = await client.session.call_tool(
    "execute_json",
    arguments={
        "executable_json": executable_json
    }
)

execution_info = client.parse_result(result)
print("\nExecution Info:")
print(execution_info)

await client.disconnect()
Tool Descriptions

Thoth-Plan Server:

  • protocol_generation: Generate detailed laboratory protocol from description

    • Args: user_prompt (str) - Natural language description of desired protocol
    • Returns: protocol (str) - Detailed step-by-step protocol text

  • generate_executable_json: Convert protocol text to machine-readable format

    • Args: protocol (str) - Protocol text
    • Returns: executable_json (str) - JSON format for Opentrons/lab automation

  • execute_json: Execute protocol via connected lab automation systems

    • Args: executable_json (str) - Executable protocol JSON
    • Returns: Execution status and log
Input/Output

Input:

  • user_prompt: Natural language description of desired experimental protocol
    • Can include: reagents, conditions, equipment, expected outcomes
    • Can reference standard protocols or specific parameters

Output:

  • protocol: Detailed step-by-step protocol including:
    • Materials and reagents list
    • Equipment requirements
    • Detailed procedure steps
    • Safety considerations
    • Expected results
    • Troubleshooting tips
Example Protocol Types

The system can generate protocols for various laboratory procedures:

  • Molecular Biology: PCR, cloning, gel electrophoresis, DNA extraction, transformation
  • Protein Science: Protein purification, Western blot, ELISA, protein crystallization
  • Cell Culture: Cell passage, transfection, differentiation, cryopreservation
  • Biochemistry: Enzyme assays, metabolite extraction, chromatography
  • Analytical: Spectroscopy, mass spectrometry sample prep, HPLC
Show full SKILL.md (147 more words)Show less
Protocol Quality Guidelines

Generated protocols include:

  • ✓ Precise volumes and concentrations
  • ✓ Specific temperatures and times
  • ✓ Safety warnings where applicable
  • ✓ Quality control checkpoints
  • ✓ Troubleshooting guidance
Integration with Lab Automation

The generated protocols can be converted to executable JSON format compatible with:

  • Opentrons liquid handling robots
  • Hamilton automated workstations
  • Custom lab automation systems
  • Electronic lab notebooks (ELNs)
Best Practices

For optimal protocol generation:

  1. Be Specific: Include target specifications (e.g., "500bp fragment", "55°C annealing")
  2. Mention Equipment: Specify if using particular instruments or kits
  3. State Goals: Describe the experimental objective
  4. Include Constraints: Note any limitations (time, budget, available reagents)
  5. Reference Standards: Mention if following particular methods or publications

Example Good Prompts:

"Generate a Western blot protocol for detecting GAPDH (37 kDa) in HEK293 cell lysates using a standard semi-dry transfer system"

"I need a DNA extraction protocol from plant tissue (Arabidopsis leaves) optimized for downstream PCR. Yield target is 50 µg from 100mg tissue"

"Create a protein purification protocol for His-tagged recombinant protein from E. coli using IMAC chromatography. Starting culture volume is 500mL"
Limitations
  • Generated protocols should be reviewed by qualified personnel before execution
  • May require adjustment based on specific lab equipment and reagents
  • Safety protocols should be verified against institutional guidelines
  • Novel or untested procedures may need optimization

© InternScience, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/protocol-generation of InternScience/scp.

Open the folder on GitHubat commit cea5398

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 InternScience/scp, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Protocol Generation From Description 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.

Protocol Generation From Description compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Protocol Generation From Description this skillInternScience/scp1691 repos~1.4kAutomated safety check: PassMIT
Duplicate Descriptionthedaviddias/Front-End-Checklist74k—~695Automated safety check: PassMIT
Swift Protocol Di Testingaffaan-m/ECC274k4 repos~1.5kAutomated safety check: PassMIT
Protocol Reversesickn33/agentic-awesome-skills47k1 repos~689Automated safety check: PassMIT
Protocol Reversezhaoxuya520/reverse-skill40k2 repos~620Automated safety check: WarnMIT
Meta Descriptionthedaviddias/Front-End-Checklist74k—~513Automated safety check: PassMIT

Similar skills

  • Duplicate Description

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing a site's meta tag uniqueness, generating page-specific meta descriptions, or reviewing CMS templates that inject the same description globally.

    74k GitHub stars~695 tokensUpdated yesterday
    Marketing & SEOAuto-check passed

  • Swift Protocol Di Testing

    affaan-m/ECC

    Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.

    274k GitHub starsUsed in 4 repos~1.5k tokens
    MobileAuto-check passed

  • Protocol Reverse

    sickn33/agentic-awesome-skills

    Authorized reverse engineering of custom binary protocols, Protobuf/gRPC schemas, WebSocket frames, and PCAP-driven protocol recovery.

    47k GitHub starsUsed in 1 repo~689 tokens
    Backend & APIsAuto-check passed

  • Protocol Reverse

    zhaoxuya520/reverse-skill

    A skill your agent uses for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.

    40k GitHub starsUsed in 2 repos~620 tokens
    Backend & APIsAuto-check: warnings

  • Meta Description

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing page metadata or generating descriptions for new pages.

    74k GitHub stars~513 tokensUpdated yesterday
    Marketing & SEOAuto-check passed

  • Audio Descriptions

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Provide audio descriptions for video.

    74k GitHub stars~549 tokensUpdated yesterday
    Frontend & DesignAuto-check passed

More from InternScience/scp

All 73 skills in this repo

  • Comprehensive Variant Annotation

    InternScience/scp

    Given an rsID, query multiple databases (dbSNP, FAVOR, GWAS Catalog, ClinVar, gnomAD, PharmGKB, ClinGen) for comprehensive annotation.

    169 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

  • Drugsda Esmfold

    InternScience/scp

    Use ESMFold model to predict 3D structure of the input protein sequence.

    169 GitHub starsUsed in 2 repos~721 tokens
    Auto-check passed

  • Drugsda Prosst

    InternScience/scp

    Given a protein sequence and its structure, employ ProSST model to predict mutation effects and obtain the top-k mutated sequences.

    169 GitHub starsUsed in 2 repos~949 tokens
    Auto-check passed

  • Atmospheric Science Calculations

    InternScience/scp

    Calculate atmospheric parameters including Coriolis parameter, geostrophic wind, heat index, potential temperature, and dewpoint for meteorology and climate science.

    169 GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed

  • Biomedical Web Search

    InternScience/scp

    Search biomedical literature and web content using Tavily search engine for research and clinical information.

    169 GitHub starsUsed in 1 repo~598 tokens
    Auto-check passed

  • Buoyancy Acceleration Calculation

    InternScience/scp

    Calculate buoyancy forces and acceleration for fluid mechanics and hydrodynamics analysis.

    169 GitHub starsUsed in 1 repo~540 tokens
    Auto-check passed

Questions about Protocol Generation From Description

What does Protocol Generation From Description do?

Generate detailed laboratory protocols from natural language descriptions using AI, producing step-by-step experimental procedures ready for lab execution. Protocol Generation From Description is an agent skill from InternScience/scp. Generate detailed laboratory protocols from natural language descriptions using AI, producing step-by-step experimental procedures ready for lab execution.

How do I install Protocol Generation From Description in Claude Code?

Run `npx skills add InternScience/scp --skill protocol-generation-from-description -a claude-code`. Or copy the skill folder (skills/protocol-generation in InternScience/scp) into .claude/skills/protocol-generation-from-description in your project. Claude Code loads it when a task matches its description.

How do I install Protocol Generation From Description in Codex?

Run `npx skills add InternScience/scp --skill protocol-generation-from-description -a codex`. Or copy the skill folder (skills/protocol-generation in InternScience/scp) into .agents/skills/protocol-generation-from-description in your project. Codex loads it when a task matches its description.

Can I use Protocol Generation From Description 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 InternScience/scp --skill protocol-generation-from-description -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/protocol-generation-from-description, .gemini/skills/protocol-generation-from-description, .github/skills/protocol-generation-from-description and .opencode/skills/protocol-generation-from-description in your project.

What does Protocol Generation From Description need to run?

SKILL.md names no scripts, command-line tools or credentials: Protocol Generation From Description is instructions for the agent only. Our summary lists: Python 3.

Does Protocol Generation From Description access the network?

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.

Is Protocol Generation From Description 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 Protocol Generation From Description use?

Protocol Generation From Description 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 Protocol Generation From Description use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Protocol Generation From Description?

Skills that share tags, products or a category with Protocol Generation From Description: Duplicate Description (thedaviddias/Front-End-Checklist, 74k stars), Swift Protocol Di Testing (affaan-m/ECC, 274k stars), Protocol Reverse (sickn33/agentic-awesome-skills, 47k stars) and Protocol Reverse (zhaoxuya520/reverse-skill, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Protocol Generation From Description?

InternScience (a GitHub organization) maintains it in InternScience/scp, which has 169 GitHub stars. The repository holds 73 skills in this directory. The repository was last updated on June 3, 2026.

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