berd-orchestrator
Skill1k starsChanged 3 months agoApache-2.0View on GitHub
Coordinate work across Berd sessions while keeping one conversation available to the user. Use for a long-lived orchestration session.
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- could be automatic: a setting could enforce it
- Very specific: line 12
Keep this session available for conversation.
- Distinctive: line 16
Prefer an existing session that owns the relevant context.
- Very specific: line 20
When creating or sending to another session, pass --from '<concise owner or workstream>' so the receiving transcript explains where the …
- Very specific: line 24
Use the berd-monitor skill for external waits associated with delegated work.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Berd Orchestrator
Keep this session available for conversation. Use berdctl session list,
get, create, and send to delegate substantial work to other sessions
instead of doing it here.
Prefer an existing session that owns the relevant context. Create one when work has no owner, and give it a complete task. Do not approve, merge, or archive work without the user's direction.
When creating or sending to another session, pass
--from '<concise owner or workstream>' so the receiving transcript explains
where the message came from.
Use the berd-monitor skill for external waits associated with delegated
work. End the turn after starting a monitor; do not poll in the foreground.
Stay quiet while work is progressing. When attention is needed, either
continue an obvious next step or bring the user one result or decision with a
[session link](berd://session/<id>).
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- bb-cli/AGENTS.mdAGENTS.md
- distro/skills/berd-help/references/agents.mdAGENTS.md
- LAWS/AGENTS.mdAGENTS.md
- src/features/design-system/AGENTS.mdAGENTS.md
- src/shared/ui/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- src/shared/ui/CLAUDE.mdCLAUDE.md
- assistive-uxSkill
- berdctl-new-commandSkill
- code-reviewSkill
- create-prSkill
- experimental-featuresSkill
- agent-builderSkill
- berd-helpSkill
- berd-monitorSkill
- skill-builderSkill
- buzz-handoffSkill
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.

