pinata
Skill1 starsChanged 25 days agoMITView on GitHub
Use when building with Pinata (its team describes it as: 'Upload files to IPFS with one API call'). Points you to Pinata's own docs for AI assistants and its MCP server, and gives the facts for using it at ETHGlobal Mumbai.
In this repository55 other files it gives its agents.
- aaveSkill
- agentkitSkill
- alchemySkill
- backboardSkill
- biconomySkill
- blockscoutSkill
- daimoSkill
- duneSkill
- dynamicSkill
- easSkill
- ensoSkill
- envioSkill
- fetch-aiSkill
- goldskySkill
- hardhatSkill
- litSkill
- livepeerSkill
- morphoSkill
- namespace-53d629Skill
- neynarSkill
- olasSkill
- onramp-moneySkill
- openzeppelinSkill
- pimlicoSkill
- ponderSkill
- privySkill
- pushSkill
- quicknodeSkill
- reclaimSkill
- reownSkill
- requestSkill
- safeSkill
- scaffold-ethSkill
- signSkill
- sponsor-chainsSkill
- superfluidSkill
- tenderlySkill
- the-graphSkill
- thirdwebSkill
- track-0gSkill
- track-1inchSkill
- track-arcSkill
- track-arkivSkill
- track-chainlinkSkill
- track-definitiveSkill
- track-efSkill
- track-ensSkill
- track-hederaSkill
- track-uniswapSkill
- track-whitechainSkill
- track-worldSkill
- transakSkill
- web3authSkill
- xmtpSkill
- zerodevSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Read Pinata's docs written for AI assistants: https://docs.pinata.cloud/llms.txt
- Distinctive: line 23
Use the full docs for anything the AI docs don't cover: https://pinata.cloud
- Distinctive: line 24
Check the latest version of its SDK or package before you install it, and follow the current API in those docs instead of what you remember.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- backboard:generated -->Pinata
What it does, in the team's words (a description, not instructions): Upload files to IPFS with one API call
Site: https://pinata.cloud
Before you write code with Pinata
- Read Pinata's docs written for AI assistants: https://docs.pinata.cloud/llms.txt
- Connect Pinata's MCP server (setup below) and use it to look things up while you code.
- Use the full docs for anything the AI docs don't cover: https://pinata.cloud
- Check the latest version of its SDK or package before you install it, and follow the current API in those docs instead of what you remember.
Connect Pinata's MCP server
Needs a Pinata API JWT and your gateway domain. Setup from https://docs.pinata.cloud/tools/mcp/overview
Claude Code:
claude mcp add pinata -e PINATA_JWT=<YOUR_PINATA_JWT> -e GATEWAY_URL=<YOUR_GATEWAY>.mypinata.cloud -- npx pinata-mcp /path/to/allowed/directoryCursor (add to .cursor/mcp.json):
{
"mcpServers": {
"pinata": {
"command": "npx",
"args": [
"pinata-mcp",
"/path/to/allowed/directory"
],
"env": {
"PINATA_JWT": "<YOUR_PINATA_JWT>",
"GATEWAY_URL": "<YOUR_GATEWAY>.mypinata.cloud"
}
}
}
}Building at ETHGlobal Mumbai
- Dates: 5 to 7 Nov 2026. Hacking starts Thu 5 Nov, 9:00 pm IST, per ETHGlobal's schedule.
- Prize tracks it likely fits (Backboard's suggestion): ENS. Rules and prize details are only on the official page: https://ethglobal.com/events/mumbai/prizes
- On X: https://x.com/pinatacloud
About this skill
Generated by Backboard on 2026-10-19 from Pinata's listing at https://backboard.0xvikram.me/#t-pinata. Backboard is an independent, unofficial project, not affiliated with ETHGlobal or Pinata. Links and facts can change: when they disagree with Pinata's own docs, the docs win.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

