$npx -y skills add Geeksfino/openskills --skill openskills-dev-orchestratorRoute OpenSkills development tasks to the right project skill or subagent, including sequencing rules for debugging, feature work, regression checks, and release readiness.
| 1 | # OpenSkills Dev Orchestrator |
| 2 | |
| 3 | Use this skill to decide which OpenSkills project skill or subagent to invoke first, and in what order, for the fastest safe outcome. |
| 4 | |
| 5 | ## Routing Rules |
| 6 | |
| 7 | ### 1) Runtime failures or sandbox regressions |
| 8 | |
| 9 | 1. Start with `openskills-runtime-debug`. |
| 10 | 2. If issue spans multiple execution paths or platforms, use `runtime-sandbox-auditor` subagent. |
| 11 | 3. Re-run runtime tests before concluding. |
| 12 | |
| 13 | ### 2) Plugin/build feature changes |
| 14 | |
| 15 | 1. Start with `openskills-plugin-separation`. |
| 16 | 2. If dependency topology is unclear, use `wasm-plugin-build-specialist` subagent. |
| 17 | 3. Validate runtime default-feature behavior and binding impact. |
| 18 | |
| 19 | ### 3) Binding breakages (TS/Python) |
| 20 | |
| 21 | 1. Start with `openskills-bindings-maintainer`. |
| 22 | 2. If both bindings are affected or unclear, use `bindings-compatibility-agent` subagent. |
| 23 | 3. Return a compatibility matrix and migration notes if needed. |
| 24 | |
| 25 | ### 4) Skill package authoring or updates |
| 26 | |
| 27 | 1. Start with `openskills-skill-authoring`. |
| 28 | 2. Use `skill-spec-conformance-agent` subagent when multiple skills or ambiguous triggers are involved. |
| 29 | 3. Validate discovery and activation behavior. |
| 30 | |
| 31 | ### 5) End-to-end confidence checks |
| 32 | |
| 33 | 1. Start with `openskills-e2e-test-runbook`. |
| 34 | 2. Use `examples-e2e-agent` subagent for scenario-heavy or flaky behavior investigations. |
| 35 | 3. Capture scenario-by-scenario pass/fail and tool-call evidence. |
| 36 | |
| 37 | ### 6) Release preparation |
| 38 | |
| 39 | 1. Start with `openskills-release-ops`. |
| 40 | 2. Use `release-gatekeeper-agent` subagent for final GO/NO-GO judgment. |
| 41 | 3. Output blockers, risks, and rollback notes explicitly. |
| 42 | |
| 43 | ## Escalation Heuristics |
| 44 | |
| 45 | - Use a skill first when the workflow is deterministic and repeatable. |
| 46 | - Escalate to a subagent when the task needs deep cross-file reasoning, ambiguity handling, or parallel analysis. |
| 47 | - If a task is unresolved after one full skill pass, escalate to the corresponding subagent. |
| 48 | |
| 49 | ## Output Contract |
| 50 | |
| 51 | Always return: |
| 52 | |
| 53 | 1. Selected path (skill and/or subagent) |
| 54 | 2. Why this path was chosen |
| 55 | 3. Ordered execution plan |
| 56 | 4. Success criteria |