agentleFS
Sign inStart free
ProjectOpenSeaProjectOpenSea/opensea-skill/AGENTS.md

opensea-skill

AGENTS.md53 starsChanged 7 months agoMITView on GitHub

Modular AI agent skills for interacting with OpenSea. Shell scripts, reference docs, and SKILL.md files for LLM consumption. There is no build or test step. Validate shell scripts and docs manually.

  • Reads credentials
  • 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 31,774 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 repository6 other files it gives its agents.

The file

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

2 rules. About 0 are common, 0 are distinctive, and 2 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.

  • 2

    Very specific

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

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

    SKILL.md files are the source of truth for agents: Keep CLI commands, API endpoints, and shell script examples current.

    line 27
  2. Very specific:

    No duplication across sub-skills: Put wallet-provider tables in opensea-wallet/ and shared scripts in opensea-api/scripts/.

    line 28

≈ “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

skill — Agent Conventions

Modular AI agent skills for interacting with OpenSea. Shell scripts, reference docs, and SKILL.md files for LLM consumption.

Quick commands

There is no build or test step. Validate shell scripts and docs manually.

# Syntax-check scripts (they live in per-domain subdirectories)
find . -name '*.sh' -exec bash -n {} +
# What CI runs: shellcheck, plus every opensea-*/scripts/*.sh must be executable
shellcheck $(find . -name '*.sh')
find . -name '*.sh' ! -perm -u+x
# Run the skill sync check
../../scripts/check-skill-sync.sh

Responsibilities

  • SKILL.md router and five sub-skills: opensea-api, opensea-marketplace, opensea-swaps, opensea-wallet, opensea-tool-sdk.
  • Reference docs and standalone curl/jq scripts per sub-skill.
  • Mirror opensea-tool-sdk/ to packages/tool-sdk/skill/.

Rules

  1. SKILL.md files are the source of truth for agents. Keep CLI commands, API endpoints, and shell script examples current.
  2. No duplication across sub-skills. Put wallet-provider tables in opensea-wallet/ and shared scripts in opensea-api/scripts/; link elsewhere.
  3. Shell scripts are self-contained. Each script should work with OPENSEA_API_KEY and curl + jq only.
  4. Security. This package mirrors to a public repo; never include API keys, internal URLs, or private infra.
  5. Skill sync. packages/tool-sdk/skill/ and packages/skill/opensea-tool-sdk/ must remain identical. Run scripts/check-skill-sync.sh locally.
  6. Releases. /release skill is the full flow: bump package.json by hand, prepend CHANGELOG.md, tag skill-vX.Y.Z, and let the GitHub/ClawHub chain publish. Do not run pnpm changeset for skill — it is excluded from the pnpm workspace.

Conventions

  • Shell scripts use #!/usr/bin/env bash and read OPENSEA_API_KEY.
  • Scripts output JSON by default (pipe through jq when available).
  • SKILL.md frontmatter declares env vars and dependencies.

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