← Back to Skills Marketplace
97
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install orchestrator-pm
Description
Strategic project manager that reads between the lines, expands scope intelligently, creates job postings, and routes to spawner. Use when starting a session...
Usage Guidance
This skill appears internally coherent for orchestrating and delegating work, but review before enabling: 1) Inspect workspace files (CONTEXT.md, TASKS.md, .learnings/, etc.) for secrets or sensitive data — the skill reads/writes these files and will persist insight tweets and risk register entries. 2) Confirm you trust the downstream skills it will invoke (spawner, recorder, verifier, publisher); those skills will receive workspace context. 3) If you want a human check before delegations, ensure the 'human-escalation' path remains enabled or modify the instructions so gating decisions require explicit human approval. 4) Test in a sandbox workspace first to verify produced JOB_BOARD.md and NEXT_AGENT.md look as expected and do not leak private information.
Capability Assessment
Purpose & Capability
Name/description (strategic PM that creates job postings and routes to a spawner) matches the runtime instructions: read workspace files, infer scope, create JOB_BOARD and NEXT_AGENT artifacts, and invoke the spawner. No unexpected binaries, env vars, or install steps are required.
Instruction Scope
SKILL.md and instructions direct the agent to read and write many workspace files (JOB_BOARD.md, NEXT_AGENT.md, insights.md, RISK_REGISTER.md, etc.) and to always run a local risk-scan and append 'insight tweets' each cycle. This is within the skill's scope but means the skill will aggregate and persist project context; those writes are mandatory by the instructions and could capture sensitive workspace content if present.
Install Mechanism
Instruction-only skill with no install spec and no code files. Lowest-risk install footprint — nothing is written to disk by an installer beyond what the instructions tell the agent to write to the workspace.
Credentials
Requires no environment variables, credentials, or external endpoints. The only required access is to workspace files (read/write) which is appropriate for an orchestrator that produces job postings and handoffs.
Persistence & Privilege
always:false and no requests to modify other skills or global agent config. The skill expects to invoke other skills (spawner, recorder, etc.) which is consistent with its role; autonomous invocation is allowed by platform default but is not an unusual privilege here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install orchestrator-pm - After installation, invoke the skill by name or use
/orchestrator-pm - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
v2: Strategic PM that reads between the lines. Bucket-aware work classification, scope inference, job board planning, wave-based execution with spawner integration.
Metadata
Frequently Asked Questions
What is Orchestrator PM?
Strategic project manager that reads between the lines, expands scope intelligently, creates job postings, and routes to spawner. Use when starting a session... It is an AI Agent Skill for Claude Code / OpenClaw, with 97 downloads so far.
How do I install Orchestrator PM?
Run "/install orchestrator-pm" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Orchestrator PM free?
Yes, Orchestrator PM is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Orchestrator PM support?
Orchestrator PM is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Orchestrator PM?
It is built and maintained by KairoKid (@dodge1218); the current version is v2.0.0.
More Skills