tinyfish-integration skill
Integrate TinyFish web toolkit (search, fetch, browser automation) into Hermes Agent
Is the tinyfish-integration skill safe?
Clean: nothing in its files matched our rules. We read 4 files in the folder on 2026-09-28.
No findings.
Install the tinyfish-integration skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/kevinnft/ai-agent-skills.git /tmp/ai-agent-skills mkdir -p ~/.claude/skills cp -r /tmp/ai-agent-skills/skills/devops/tinyfish-integration ~/.claude/skills/tinyfish-integration
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
TinyFish Integration
TinyFish is a web toolkit for AI agents that provides search, fetch, and browser automation capabilities. Search and fetch are free for every account — no credits, no cost.
Available Tools
tinyfish_search
Search the live web and get structured, agent-ready results.
Use cases:
- Current information, news, prices
- Finding URLs before fetching content
- Anything that changes over time
Parameters:
- query (required): Search query string
- location (optional): 2-letter country code (e.g., "US", "FR", "ID")
- language (optional): 2-letter language code (e.g., "en", "fr", "id")
- page (optional): Page number for pagination (default: 0)
Example:
tinyfish_search(query="Hermes Agent AI", location="US", language="en")Response format:
{
"results": [
{
"title": "Page Title",
"url": "https://example.com",
"snippet": "Description text...",
"site_name": "Example Site"
}
]
}tinyfish_fetch
Pull the full content of any web page as clean extracted text.
Use cases:
- Reading articles, docs, product pages
- Extracting content without ads/navigation
- Batch processing multiple URLs (max 10)
Parameters:
- urls (required): Single URL or comma-separated list (max 10)
Examples:
# Single URL
tinyfish_fetch(urls="https://example.com")
# Multiple URLs
tinyfish_fetch(urls="https://site1.com, https://site2.com, https://site3.com")Response format:
{
"results": [
{
"url": "https://example.com",
"final_url": "https://example.com",
"title": "Page Title",
"description": "Meta description",
"language": "en",
"text": "# Heading\n\nClean extracted content..."
}
],
"errors": []
}Setup
1. Get API Key
Visit https://agent.tinyfish.ai/api-keys to get your API key.
2. Configure Hermes
Add to ~/.hermes/.env:
TINYFISH_API_KEY=sk-tinyfish-YOUR_KEY_HERE3. Enable Toolset
Add to ~/.hermes/config.yaml:
toolsets:
- tinyfish4. Verify Installation
hermes chat -q "Search for 'Hermes Agent' using tinyfish_search"Tool Implementation
The TinyFish tools are implemented in ~/.hermes/hermes-agent/tools/tinyfish_search.py:
- tinyfishsearch**: GET request to https://api.search.tinyfish.ai
- tinyfishfetch**: POST request to https://api.fetch.tinyfish.ai with JSON body
Both tools:
- Use X-API-Key header for authentication
- Return JSON responses
- Handle errors gracefully
- Support 60-second timeout for fetch (30s for search)
When to Use Each Tool
Supported Content Types (Fetch)
- ✅ HTML pages (clean text extraction)
- ✅ PDF files (text extraction)
- ✅ JSON endpoints (raw JSON)
- ❌ Binary files (images, video) — returns error
Limitations
- Search: No explicit rate limit documented
- Fetch: Max 10 URLs per request
- Timeout: 60 seconds for fetch, 30 seconds for search
- Free tier: Search and fetch are free with no credit cost
Troubleshooting
"TINYFISHAPIKEY environment variable not set"
- Check ~/.hermes/.env has the key
- Restart Hermes after adding the key
"HTTP 401: Unauthorized"
- Verify API key is correct
- Check key hasn't expired at https://agent.tinyfish.ai/api-keys
"HTTP 405: Method Not Allowed"
- This was the old bug — fetch now uses POST correctly
- Update to latest tool version if you see this
Timeout errors
- Fetch has 60s timeout — some pages may be slow
- Try fetching fewer URLs at once
- Check if the target site is accessible
Advanced Usage
Batch Fetch with Error Handling
# Fetch multiple URLs — errors don't affect other URLs
result = tinyfish_fetch(urls="https://site1.com, https://site2.com, https://invalid-url.com")
# Response includes both results and errors
{
"results": [...], # Successful fetches
"errors": [...] # Failed URLs with error messages
}Geo-Targeted Search
# Search from specific country
tinyfish_search(query="best pizza", location="IT", language="it")Pagination
# Get page 2 of results
tinyfish_search(query="AI agents", page=1)More skills from kevinnft/ai-agent-skills
- Aaddyosmani-tddDrives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
- AairtableAirtable REST API via curl. Records CRUD, filters, upserts.
- Aapi-and-interface-designGuides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
- Aapi-monitoring-botsBuild monitoring bots that poll APIs and send notifications on state changes (new listings, price alerts, status updates)
- Aapple-notesManage Apple Notes via memo CLI: create, search, edit.
- Aapple-remindersApple Reminders via remindctl: add, list, complete.
- Aarchitecture-diagramDark-themed SVG architecture/cloud/infra diagrams as HTML.
- AarxivSearch arXiv papers by keyword, author, category, or ID.
- Aascii-artASCII art: pyfiglet, cowsay, boxes, image-to-ascii.
- Aascii-videoASCII video: convert video/audio to colored ASCII MP4/GIF.
- AaudiocraftAudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
- CaxolotlAxolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).