agentleFS
GetStreamGetStream/agent-skills/AGENTS.md

agent-skills

AGENTS.md21 starsChanged 7 days agoApache-2.0View on GitHub

This repository contains the Stream skill pack. Skill source lives under skills/. Router: skills/stream/SKILL.md - Stream overview, CLI discovery, and routing to platform skills. SDK documentation is available through getstream docs. Each platform skill contains its own integration guidance and supporting files. For Sendbird data migration, use the shared skills/stream/sendbird-data-migration.md runbook. Installation instructions are in README.md.

The file

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

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Keep skill instructions focused on workflows, observed integration pitfalls, command/docs pointers, and concrete verification.

    line 26
  2. Very specific:

    Use getstream -h, getstream <command> -h, and getstream docs for CLI and SDK reference details.

    line 27
  3. Distinctive:

    When moving or removing skill files, update their callers, the skills table in README.md, and the contents list in CONTRIBUTING.md, then …

    line 33
  4. Very specific:

    ASCII only: all files in this repo must contain ASCII characters only.

    line 34

≈ “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

AGENTS.md - Codex entrypoint for the Stream skill pack

This repository contains the Stream skill pack. Skill source lives under skills/.

Router: skills/stream/SKILL.md - Stream overview, CLI discovery, and routing to platform skills. SDK documentation is available through getstream docs. Each platform skill contains its own integration guidance and supporting files.

Sub-skills

Sub-skillUse for
skills/stream-react/SKILL.mdDefault for web React/Next.js. Scaffold, enhance, audit, or migrate a React/Next.js app with Chat/Video/Feeds/Moderation, including AI assistants and agentic chat (stream-chat-react/ai-components, generative UI with A2UI / OpenUI) and apps built on Stream Agents
skills/stream-react-native/SKILL.mdBuild or integrate Stream Chat/Video/Feeds in React Native or Expo apps
skills/stream-swift/SKILL.mdBuild or integrate Stream Chat/Video/Feeds in Swift/SwiftUI/UIKit/iOS apps, including AI assistants and agentic chat (StreamChatAI)
skills/stream-android/SKILL.mdBuild or integrate Stream Chat/Video/Feeds in Android/Jetpack Compose apps, including AI assistants and agentic chat (stream-chat-android-ai-compose)
skills/stream-flutter/SKILL.mdBuild or integrate Stream Chat, Video, and Feeds in Flutter apps (stream_chat_flutter, stream_chat_flutter_core, stream_video_flutter, stream_feeds)
skills/stream-unity/SKILL.mdBuild or integrate Stream Chat and Stream Video in Unity Engine projects (C#). Chat + Video - no Feeds SDK for Unity
skills/stream-unreal/SKILL.mdBuild or integrate Stream Chat in Unreal Engine 5.7/5.8 projects (C++ and Blueprint). Chat only - no Video or Feeds SDK for Unreal
skills/stream-feeds-migration/SKILL.mdGenerate the v2 -> v3 Activity Feeds sync mapping by sampling the v2 app's live activities and reactions, and by reading the app's v2 integration code when it is available. No CLI and no project required - it emits a config object

For Sendbird data migration, use the shared skills/stream/sendbird-data-migration.md runbook.


Working on this repository

  • Keep skill instructions focused on workflows, observed integration pitfalls, command/docs pointers, and concrete verification. Use plain wording.
  • Use getstream -h, getstream <command> -h, and getstream docs for CLI and SDK reference details. Avoid duplicating that material in skills.
  • Tool permissions belong to the agent harness; avoid adding approval scripts or permission rules to skill prose.
  • In skill instructions, refer to files within the same skill by raw relative path: "Read migration.md".
  • For a file in another skill, name the skill and path: "Read stream skill's migration.md".
  • For another skill's SKILL.md, name only the skill: "Refer to stream skill".
  • getstream skills installs every skill under skills/ into the user's project, next to the skills they keep there. Name a new skill stream-<name> so it never collides with one of theirs.
  • When moving or removing skill files, update their callers, the skills table in README.md, and the contents list in CONTRIBUTING.md, then check local links. Run affected helper scripts when needed to verify behavior and report what was checked.
  • ASCII only: all files in this repo must contain ASCII characters only. No em/en dashes, smart quotes, ellipsis chars, arrows, checkmarks, or other non-ASCII glyphs - use plain ASCII equivalents (-, ', ", ..., ->, OK, etc.).

Installation instructions are in README.md.

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.