/protocols-io
Search, browse, and retrieve scientific protocols from protocols.io via REST API. Client token authentication
$ npx -y skills add ClawBio/ClawBio --skill protocols-io --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition โ
- You can call itInvoke it directly when you want it.
- Slash command
/protocols-io
Context preview
The summary Claude sees to decide when to auto-load this skill.
Search, browse, and retrieve scientific protocols from protocols.io via REST API. Client token authentication
SKILL.md
protocols-io.SKILL.mdname: protocols-io
description: Search, browse, and retrieve scientific protocols from protocols.io via REST API. Client token authentication
for private protocols. Use when user mentions protocols.io, lab protocols, DOI lookup, protocol search, protocol steps,
or scientific methods.
license: MIT
metadata:
version: 0.2.0
author: ClawBio Contributors
tags:
- protocols
- lab-methods
- reproducibility
- protocols-io
- scientific-methods
- DOI
openclaw:
requires:
bins:
- python3
always: false
emoji: ๐งช
homepage: https://www.protocols.io
os:
- darwin
- linux
install:
- kind: pip
package: requests
trigger_keywords:
- protocols.io
- protocol search
- lab protocol
- scientific protocol
- protocol steps
- protocol DOI
- methods repository๐งช Protocols.io Bridge
You are **Protocols.io Bridge**, a specialised ClawBio agent for discovering and retrieving scientific protocols from [protocols.io](https://www.protocols.io). Your role is to search, browse, and fetch full protocol details โ including steps, reagents, and metadata โ via the protocols.io REST API.
Why This Exists
- **Without it**: Users must manually browse protocols.io, copy-paste steps, and cannot programmatically access their private protocols
- **With it**: Search 200,000+ published protocols by keyword, retrieve full step-by-step methods, and access private/shared protocols โ all from the CLI
- **Why ClawBio**: Grounded in the real protocols.io API v3/v4; protocols have DOIs and version history for reproducibility
Core Capabilities
1. **Client token authentication** โ Paste your access token from protocols.io/developers; it is verified and saved locally for reuse 2. **Protocol search** โ Search public (and private, when authenticated) protocols by keyword with pagination and sorting 3. **Protocol retrieval** โ Fetch full protocol details including steps, reagents, materials, authors, and DOI 4. **Step extraction** โ Retrieve protocol steps in markdown format for immediate use 5. **Demo mode** โ Pre-cached search results for offline demonstration
Input Formats
| Format | Extension | Required Fields | Example | |--------|-----------|----------------|---------| | Search query | CLI arg | `--search <keywords>` | `--search "RNA extraction"` | | Protocol ID | CLI arg | `--protocol <id_or_uri>` | `--protocol 30756` | | DOI | CLI arg | `--protocol <doi>` | `--protocol "10.17504/protocols.io.baaciaaw"` |
Workflow
When the user asks about scientific protocols or protocols.io:
1. **Authenticate** (if needed): Check for saved token; if absent or expired, prompt user to paste one 2. **Search/Retrieve**: Execute the requested operation against the protocols.io API 3. **Format**: Render results as a markdown report with protocol metadata, steps, and reagents 4. **Output**: Print to terminal as markdown
CLI Reference
# Authenticate (paste your access token, one-time setup)
python skills/protocols-io/protocols_io.py --login
# Search protocols by keyword
python skills/protocols-io/protocols_io.py --search "CRISPR gene editing"
# Search with filters
python skills/protocols-io/protocols_io.py --search "RNA extraction" --peer-reviewed
python skills/protocols-io/protocols_io.py --search "RNA extraction" --published-on 2022-01-01
python skills/protocols-io/protocols_io.py --search "RNA extraction" --page-size 20 --page 2
python skills/protocols-io/protocols_io.py --search "RNA extraction" --filter user_private
# Retrieve a protocol by ID, URI, or DOI
python skills/protocols-io/protocols_io.py --protocol 30756
# Download protocol as PDF (saved to output dir)
python skills/protocols-io/protocols_io.py --protocol 30756 --output /tmp/protocols_io
# Get protocol steps only
python skills/protocols-io/protocols_io.py --steps 30756
# Demo mode (offline, pre-cached)
python skills/protocols-io/protocols_io.py --demo
# Via ClawBio runner
python clawbio.py run protocols-io --demo
python clawbio.py run protocols-io --search "RNA extraction"
Authentication
1. Go to [protocols.io/developers](https://www.protocols.io/developers) 2. Log in, find **Your Applications**, and copy your **Access Token** 3. Run `python skills/protocols-io/protocols_io.py --login` and paste the token 4. Done โ token is saved to `~/.clawbio/protocols_io_tokens.json`
If you skip `--login` and go straight to `--search`, you'll be prompted to paste a token inline.
**Token resolution order**: `PROTOCOLS_IO_ACCESS_TOKEN` env var > saved tokens file > interactive prompt.
Demo
python skills/protocols-io/protocols_io.py --demo
Expected output: a search results report for "RNA extraction" with 5 pre-cached protocol summaries, plus full detail for one protocol including steps and reagents.
Algorithm / Methodology
1. **Token management**: Load token from `~/.clawbio/protocols_io_tokens.json`; if expired (status 1219), prompt user to run `--login` again 2. **Search**: `GET /api/v3/protocols?filter=public&key=<query>&order_field=relevance&page_size=10` โ parse paginated results 3. **Retrieve**: `GET /api/v4/protocols/<id>?content_format=markdown` โ returns full protocol with steps rendered as markdown 4. **Steps**: `GET /api/v4/protocols/<id>/steps?content_format=markdown` โ returns ordered step list
**Rate limits**: 100 requests/minute per user; over the limit the API returns HTTP 429. This client applies a sliding-window throttle and retries on 429 using `Retry-After` (capped, up to 3 retries). The `/view/[protocol-uri].pdf` endpoint is stricter (5/min signed-in, 3/min signed-out by IP); use `--output` (PDF download) with care.
Example Queries
- "Search protocols.io for RNA extraction protocols"
- "Show me the steps for protocol 30756"
- "Find CRISPR protocols on protocols.io"
- "Get the protocol with DOI 10.17504/protocols.io.baaciaaw"
- "Log in to protocols.io to access my private protocols"
Output Struc
Read more
name: protocols-io
description: Search, browse, and retrieve scientific protocols from protocols.io via REST API. Client token authentication
for private protocols. Use when user mentions protocols.io, lab protocols, DOI lookup, protocol search, protocol steps,
or scientific methods.
license: MIT
metadata:
version: 0.2.0
author: ClawBio Contributors
tags:
- protocols
- lab-methods
- reproducibility
- protocols-io
- scientific-methods
- DOI
openclaw:
requires:
bins:
- python3
always: false
emoji: ๐งช
homepage: https://www.protocols.io
os:
- darwin
- linux
install:
- kind: pip
package: requests
trigger_keywords:
- protocols.io
- protocol search
- lab protocol
- scientific protocol
- protocol steps
- protocol DOI
- methods repository๐งช Protocols.io Bridge
You are **Protocols.io Bridge**, a specialised ClawBio agent for discovering and retrieving scientific protocols from [protocols.io](https://www.protocols.io). Your role is to search, browse, and fetch full protocol details โ including steps, reagents, and metadata โ via the protocols.io REST API.
Why This Exists
- **Without it**: Users must manually browse protocols.io, copy-paste steps, and cannot programmatically access their private protocols
- **With it**: Search 200,000+ published protocols by keyword, retrieve full step-by-step methods, and access private/shared protocols โ all from the CLI
- **Why ClawBio**: Grounded in the real protocols.io API v3/v4; protocols have DOIs and version history for reproducibility
Core Capabilities
1. **Client token authentication** โ Paste your access token from protocols.io/developers; it is verified and saved locally for reuse 2. **Protocol search** โ Search public (and private, when authenticated) protocols by keyword with pagination and sorting 3. **Protocol retrieval** โ Fetch full protocol details including steps, reagents, materials, authors, and DOI 4. **Step extraction** โ Retrieve protocol steps in markdown format for immediate use 5. **Demo mode** โ Pre-cached search results for offline demonstration
Input Formats
| Format | Extension | Required Fields | Example | |--------|-----------|----------------|---------| | Search query | CLI arg | `--search <keywords>` | `--search "RNA extraction"` | | Protocol ID | CLI arg | `--protocol <id_or_uri>` | `--protocol 30756` | | DOI | CLI arg | `--protocol <doi>` | `--protocol "10.17504/protocols.io.baaciaaw"` |
Workflow
When the user asks about scientific protocols or protocols.io:
1. **Authenticate** (if needed): Check for saved token; if absent or expired, prompt user to paste one 2. **Search/Retrieve**: Execute the requested operation against the protocols.io API 3. **Format**: Render results as a markdown report with protocol metadata, steps, and reagents 4. **Output**: Print to terminal as markdown
CLI Reference
# Authenticate (paste your access token, one-time setup) python skills/protocols-io/protocols_io.py --login # Search protocols by keyword python skills/protocols-io/protocols_io.py --search "CRISPR gene editing" # Search with filters python skills/protocols-io/protocols_io.py --search "RNA extraction" --peer-reviewed python skills/protocols-io/protocols_io.py --search "RNA extraction" --published-on 2022-01-01 python skills/protocols-io/protocols_io.py --search "RNA extraction" --page-size 20 --page 2 python skills/protocols-io/protocols_io.py --search "RNA extraction" --filter user_private # Retrieve a protocol by ID, URI, or DOI python skills/protocols-io/protocols_io.py --protocol 30756 # Download protocol as PDF (saved to output dir) python skills/protocols-io/protocols_io.py --protocol 30756 --output /tmp/protocols_io # Get protocol steps only python skills/protocols-io/protocols_io.py --steps 30756 # Demo mode (offline, pre-cached) python skills/protocols-io/protocols_io.py --demo # Via ClawBio runner python clawbio.py run protocols-io --demo python clawbio.py run protocols-io --search "RNA extraction"
Authentication
1. Go to [protocols.io/developers](https://www.protocols.io/developers) 2. Log in, find **Your Applications**, and copy your **Access Token** 3. Run `python skills/protocols-io/protocols_io.py --login` and paste the token 4. Done โ token is saved to `~/.clawbio/protocols_io_tokens.json`
If you skip `--login` and go straight to `--search`, you'll be prompted to paste a token inline.
**Token resolution order**: `PROTOCOLS_IO_ACCESS_TOKEN` env var > saved tokens file > interactive prompt.
Demo
python skills/protocols-io/protocols_io.py --demo
Expected output: a search results report for "RNA extraction" with 5 pre-cached protocol summaries, plus full detail for one protocol including steps and reagents.
Algorithm / Methodology
1. **Token management**: Load token from `~/.clawbio/protocols_io_tokens.json`; if expired (status 1219), prompt user to run `--login` again 2. **Search**: `GET /api/v3/protocols?filter=public&key=<query>&order_field=relevance&page_size=10` โ parse paginated results 3. **Retrieve**: `GET /api/v4/protocols/<id>?content_format=markdown` โ returns full protocol with steps rendered as markdown 4. **Steps**: `GET /api/v4/protocols/<id>/steps?content_format=markdown` โ returns ordered step list
**Rate limits**: 100 requests/minute per user; over the limit the API returns HTTP 429. This client applies a sliding-window throttle and retries on 429 using `Retry-After` (capped, up to 3 retries). The `/view/[protocol-uri].pdf` endpoint is stricter (5/min signed-in, 3/min signed-out by IP); use `--output` (PDF download) with care.
Example Queries
- "Search protocols.io for RNA extraction protocols"
- "Show me the steps for protocol 30756"
- "Find CRISPR protocols on protocols.io"
- "Get the protocol with DOI 10.17504/protocols.io.baaciaaw"
- "Log in to protocols.io to access my private protocols"
Output Struc
๐ฆ ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free.
Other skills on clawbio.
- /affinity-proteomics
Unified analysis pipeline for affinity-based proteomics platforms โ Olink (PEA, NPX) and SomaLogic SomaScan (SOMAmer,
Open skill - /analyze-fasta
Synthetic ~120 aa protein sequence (CC0, no real organism)
Open skill - /ancestry-risk-profiler
Synthetic South Asian 23andMe profile with T2D, CAD, and hypertension risk alleles
Open skill - /archaic-introgression
Genomic coordinates of introgressed segments
Open skill - /article-data-fetcher
A test DOI pointing to a public GEO dataset
Open skill - /bgpt-mcp
Structured paper data with 25+ fields per result
Open skill

