agentleFS
Sign inStart free
1Shot-API1Shot-API/skills/AGENTS.md

skills

AGENTS.md1 starsChanged 7 days agoMITView on GitHub

This repository is the canonical source for first-party 1Shot Agent Skills. Product repos (CoinOperated, embedded-wallet, relayer, …) point here and never vendor these skills; developers install them at user level with npx skills add 1Shot-API/skills/<skill> -g -a claude-code -y (~/.claude/skills is read by both Claude Code and Cursor).

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,843 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository9 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep SKILL.md short and procedural.

    line 9
  2. Very specific:

    When a product surface changes (1Shot API SDK, embedded wallet Host RPC / EIP-1193, public-relayer JSON-RPC, CoinOperated REST API), update …

    line 15
  3. Very specific:

    After editing coinoperated, agent-wallet, or public-relayer, regenerate the hosted discovery archives from the CoinOperated repo (yarn …

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

1Shot skills — AGENTS.md

This repository is the canonical source for first-party 1Shot Agent Skills. Product repos (CoinOperated, embedded-wallet, relayer, …) point here and never vendor these skills; developers install them at user level with npx skills add 1Shot-API/skills/<skill> -g -a claude-code -y (~/.claude/skills is read by both Claude Code and Cursor).

Layout

  • One skill per top-level folder: <skill>/SKILL.md (required) plus optional references/, scripts/, assets/, README.md.
  • SKILL.md starts with YAML frontmatter (name, description, license, metadata.version, metadata.repository). The description is what triggers the skill, so keep it specific to the task the skill solves.
  • Keep SKILL.md short and procedural; move long schemas, examples, and background into references/*.md and link to them.
  • Scripts must be non-interactive, print JSON to stdout, and never print secrets (see agent-wallet/references/security.md).

Conventions

  • Install snippets use -g -a claude-code -y. Do not reintroduce -a cursor or ~/.cursor/skills paths (the coinoperated script keeps ~/.cursor/skills only as a lookup fallback for older installs).
  • When a product surface changes (1Shot API SDK, embedded wallet Host RPC / EIP-1193, public-relayer JSON-RPC, CoinOperated REST API), update the matching skill here in the same effort and bump metadata.version.
  • After editing coinoperated, agent-wallet, or public-relayer, regenerate the hosted discovery archives from the CoinOperated repo (yarn skills:sync-discovery) and commit them there.
  • skills-lock.json tracks the project-installed skill-creator helper only; .claude/, .cursor/, and .agents/ are gitignored so local installs are never committed.

Agent Tooling (Claude Code + Cursor)

  • AGENTS.md is the single source of truth. Cursor reads it natively; CLAUDE.md just imports it (@AGENTS.md). Do not add .cursorrules, .cursor/rules, or Claude-only guidance elsewhere.
  • There are no project skills, hooks, or MCP servers configured for this repo.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free