Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

protocols.io Integration

Safely read, validate, and export protocols.io data using the current v3/v4 endpoint contracts, with mutations limited to non-executing dry-run plans.

Web & APIIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Gives an accurate map of the current protocols.io endpoints (a mix of /api/v3 and /api/v4) so the agent stops guessing or reviving deprecated paths.
  • Ships Python CLIs for searching protocols, fetching a protocol and its steps, and exporting PDFs. Everything plans by default; real network calls require an explicit --execute gate.
  • Validates saved JSON offline — field types, linked step GUID ordering, version/authorship/DOI metadata — and checks any server-provided next_page before following it.
  • Turns every write (create, update, publish, step delete, comment delete, trash, upload, org export) into a redacted dry-run plan with a confirmation phrase; the tooling has no execution mode at all.
  • Reads only the named PROTOCOLS_IO_ACCESS_TOKEN variable, never prints values, talks only to official HTTPS hosts, and treats remote protocol text as untrusted data.

Who it's for

  • Researchers and lab managers who store, version, or cite experimental protocols on protocols.io.
  • Data curators who must preserve DOI, version_uri, and attribution when linking protocols to papers or repositories.
  • Developers scripting against the protocols.io API who want a hard guardrail against accidental publishes or deletions.

Examples

  1. Bounded public search: python3 -B scripts/protocols_read.py --execute list --query "single cell RNA" --page-size 10 --max-pages 2 --max-items 20.
  2. Fetch an exact archived version (protocol-uri/v2) and build a citation that keeps the DOI and version URI intact instead of silently using /latest.
  3. Before editing a protocol, run plan_write_request.py --operation update-protocol --payload reviewed-update.json and hand the plan to a human for approval.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/protocolsio-integration/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/protocolsio-integration folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/protocolsio-integration/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/protocolsio-integration ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and check your Python version: python3 --version (3.11 or newer required).
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/protocolsio-integration ~/.claude/skills/
  5. (Optional) For authenticated reads, get a token from the signed-in protocols.io Developer resources page and set PROTOCOLS_IO_ACCESS_TOKEN via your shell profile or host secret manager — never paste it into chat or a command argument.
  6. From the skill folder, run python3 -B scripts/validate_auth_config.py --require read to confirm the setup without exposing the value.
  7. Restart Claude Code, then ask something like "fetch this exact protocols.io protocol version and summarize its steps."
View source on GitHub ↗License: MIT