What does the OpenSkills Dev Orchestrator output?

A selected path (skill and/or subagent), the rationale for that path, an ordered execution plan, and explicit success criteria per the Output Contract.

How does it decide which subagent to start with?

It applies the six routing rules (runtime failures, plugin changes, bindings, skill authoring, end-to-end checks, and release prep) to pick the initial skill or subagent, then follows the predefined escalation path if needed.

What happens if a path is unresolved or fails?

Escalation heuristics push the task to deeper subagents or produce a compatibility matrix and migration notes as needed; the orchestrator may continue along the next steps in the plan.

openskills-dev-orchestrator

npx machina-cli add skill Geeksfino/openskills/openskills-dev-orchestrator --openclaw

Files (1)

SKILL.md

2.2 KB

OpenSkills Dev Orchestrator

Use this skill to decide which OpenSkills project skill or subagent to invoke first, and in what order, for the fastest safe outcome.

Routing Rules

1) Runtime failures or sandbox regressions

Start with openskills-runtime-debug.
If issue spans multiple execution paths or platforms, use runtime-sandbox-auditor subagent.
Re-run runtime tests before concluding.

2) Plugin/build feature changes

Start with openskills-plugin-separation.
If dependency topology is unclear, use wasm-plugin-build-specialist subagent.
Validate runtime default-feature behavior and binding impact.

3) Binding breakages (TS/Python)

Start with openskills-bindings-maintainer.
If both bindings are affected or unclear, use bindings-compatibility-agent subagent.
Return a compatibility matrix and migration notes if needed.

4) Skill package authoring or updates

Start with openskills-skill-authoring.
Use skill-spec-conformance-agent subagent when multiple skills or ambiguous triggers are involved.
Validate discovery and activation behavior.

5) End-to-end confidence checks

Start with openskills-e2e-test-runbook.
Use examples-e2e-agent subagent for scenario-heavy or flaky behavior investigations.
Capture scenario-by-scenario pass/fail and tool-call evidence.

6) Release preparation

Start with openskills-release-ops.
Use release-gatekeeper-agent subagent for final GO/NO-GO judgment.
Output blockers, risks, and rollback notes explicitly.

Escalation Heuristics

Use a skill first when the workflow is deterministic and repeatable.
Escalate to a subagent when the task needs deep cross-file reasoning, ambiguity handling, or parallel analysis.
If a task is unresolved after one full skill pass, escalate to the corresponding subagent.

Output Contract

Always return:

Selected path (skill and/or subagent)
Why this path was chosen
Ordered execution plan
Success criteria

Source

git clone https://github.com/Geeksfino/openskills/blob/main/.cursor/skills/openskills-dev-orchestrator/SKILL.mdView on GitHub

Overview

OpenSkills Dev Orchestrator decides which project skill or subagent to invoke first and in what order, delivering the fastest safe outcome. It encodes sequencing rules for debugging, feature work, regression checks, and release readiness to guide cross-skill collaboration and reduce risk.

How This Skill Works

It evaluates the routing rules (runtime failures, plugin changes, bindings, skill authoring, end-to-end checks, and release prep) to select an initial path and subsequent steps. It returns a structured Output Contract: selected path, rationale, ordered execution plan, and success criteria, enabling deterministic handoffs. Escalation heuristics activate subagents when deeper analysis or cross-file reasoning is needed.

When to Use It

Debug runtime failures or sandbox regressions
Plugin/build feature changes
Binding breakages (TS/Python)
Skill package authoring or updates
End-to-end confidence checks
Release preparation

Quick Start

Step 1: Identify the highest-priority routing rule that matches the task
Step 2: Invoke the first skill or subagent as per the rule set, and monitor outcomes
Step 3: If needed, advance to the next subagent in the ordered plan and publish the Output Contract

Best Practices

Follow the predefined routing ladder 1–6 to pick the initial subagent
Escalate to a subagent when cross-file reasoning or ambiguity is required
Capture runtime evidence and compatibility notes during handoffs
Validate discovery and activation behavior after each step
Document blockers, risks, and rollback steps in the output

Example Use Cases

Runtime issue touches multiple paths; orchestrator starts with openskills-runtime-debug, then runtime-sandbox-auditor if needed, and re-runs tests
Plugin feature change: openskills-plugin-separation, with wasm-plugin-build-specialist if topology is unclear
TS binding breakage: openskills-bindings-maintainer, then bindings-compatibility-agent to produce a compatibility matrix
New skill package update: openskills-skill-authoring followed by skill-spec-conformance-agent
End-to-end flaky behavior: openskills-e2e-test-runbook and examples-e2e-agent; capture per-scenario results

Frequently Asked Questions

Add this skill to your agents