DanielC000/loom / packages/daemon/assets/skills/orchestrate
orchestrate
VerifiedThe operating doctrine for a Loom lead / orchestrator (manager) session. Load at the start of any orchestrator agent to run the lead-manages-workers loop — plan, decompose, delegate, review, merge, recycle — over the loom-orchestration tools. Your agent prompt supplies the project-specifics; this is the cross-project HOW.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 32.1 KB |
| references/deployed-instance-and-restart.md | markdown | 4.4 KB |
| references/live-verification.md | markdown | 1.8 KB |
| references/merge-and-gate.md | markdown | 14.6 KB |
| references/planning-and-kickoffs.md | markdown | 9.9 KB |
| references/project-memory.md | markdown | 4.5 KB |
| references/requests-inbox.md | markdown | 6.3 KB |
| references/resume-doc-and-memory.md | markdown | 5.0 KB |
| references/resume-doc-rotation.md | markdown | 4.3 KB |
| references/serving-and-capture.md | markdown | 7.6 KB |
| references/verification-discipline.md | markdown | 10.1 KB |
| references/worker-steering-and-recovery.md | markdown | 17.3 KB |
| scripts/dev-server.mjs | script | 37.3 KB |
| scripts/serve-static.mjs | script | 16.2 KB |
references/live-verification.md
View on GitHub# Run-shaped features — the elaborated failure modes
The core doctrine (the loop, step 9) carries the binding rule and both shape names: a feature whose
runtime crosses a boundary a unit test stubs out needs **≥1 real end-to-end smoke run** as a hard DoD
— hermetic green is not live green. This file carries the elaborated failure modes behind each shape
and the hermetic-test cases they imply.
- **Agent-turn runtimes** — agent runs, dispatch, tool-IO, anything where a live model call drives
the behavior: the schema the agent actually sees, how a real model phrases its output, and the
timeout/teardown path only exercise under a real turn. Make **≥1 real-agent smoke run** the DoD.
(This is the classic run/tool-IO miss: every hermetic test was green while a real agent looped
repeatedly because its result was a stringified JSON that the result schema rejected.) Bake that
exact failure into your hermetic-test guidance too: a run/tool-IO feature's tests must cover the
**stringified-result case** — an agent passing a JSON-encoded *string* where an object is expected —
not just the already-well-formed payload, since that's the shape real models actually emit.
- **Subprocess / spawn / hook boundaries** — anything that shells out: spawns a child process, execs
a CLI, or fires an OS hook. Mocking the exec call never exercises the real cross-platform spawn, so
a binary that isn't found, an arg quoted wrong, or an interpreter/file-type mismatch can make the
feature **silently no-op** while every unit test stays green — and it's OS-specific, so a green run
on one platform doesn't cover the others. Make **≥1 real spawn on the target OS** the DoD: exercise
the feature end-to-end across the process boundary and confirm the observable side effect actually
happened, don't just assert the exec was called.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |