Skip to content
Get packs

protocols.io Integration

Read, validate and safely export protocols.io protocols, or draft non-executing write plans

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
15 files

What it does

This skill teaches an AI agent how to work with protocols.io, a platform for sharing scientific lab protocols. Once installed, the agent checks saved protocol files and configuration offline first, then can read protocols, steps, materials and PDFs through the official protocols.io web service, but only when you explicitly allow network access. For any change to a protocol (create, edit, publish, delete, upload), it only drafts a plan for you to review and never executes the change itself.

Great for

  • Researchers or lab staff who want an agent to find, summarise or export protocols.io protocols with their citation details intact
  • Developers building a read-only protocols.io integration who want validated, bounded API helper scripts
  • Teams auditing saved protocol JSON for missing fields or unsafe content before reuse

Skip it if

  • Tasks unrelated to protocols.io, since the skill is written to refuse anything not explicitly targeting it (it would add little value elsewhere)
  • Anyone wanting the agent to publish or edit protocols automatically, because the skill deliberately only produces plans and needs a human to confirm each change
  • Handling private or organisation data without a properly scoped token, since broad write-capable OAuth grants carry more risk than read-only public access

Try asking

  • “Search protocols.io for single cell RNA protocols and list the first 20 results with their DOIs”
  • “Get version 2 of a specific protocol and check its JSON against the offline validator”
  • “Export the PDF of a protocol to a local file for a lab binder”
  • “Draft a plan to update a protocol's description, showing the current state and the exact request, without sending anything”
Step-by-step guide: how to use protocols.io IntegrationInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    protocolsio-integration.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip protocolsio-integration.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip protocolsio-integration.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Start with offline validation and planning; only add --execute after you have reviewed the exact URL and limits
  • Keep your token in your host's secret store and never paste it into chat or command lines; the skill is designed to refuse this
  • Use a public-data client token for simple discovery rather than an OAuth grant with readwrite scope

What's inside

  • assets/protocol-snapshot.schema.json
  • references/additional_features.md
  • references/authentication.md
  • references/discussions.md
  • references/file_manager.md
  • references/protocols_api.md
  • references/workspaces.md
  • scripts/__init__.py
  • scripts/_common.py
  • scripts/pagination_helper.py
  • scripts/plan_write_request.py
  • scripts/protocols_read.py
  • scripts/validate_auth_config.py
  • scripts/validate_protocol_json.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.