rlaope/oh-my-hermes / skills/omh-routing
omh-routing
Verified[omh] Choosing among OMH skills for a request: router guidance for using oh-my-hermes workflow skills inside Hermes Agent.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.4 KB |
| references/catalog-index.md | markdown | 32.9 KB |
| references/coding-handoff-progress-reporting.md | markdown | 4.8 KB |
| references/evidence-boundaries.md | markdown | 2.6 KB |
| references/harness-registry.md | markdown | 21.4 KB |
| references/human-voice.md | markdown | 7.1 KB |
| references/jev-rail.md | markdown | 6.3 KB |
| references/operator-maintenance.md | markdown | 2.1 KB |
| references/skill-common-rail.md | markdown | 15.5 KB |
| references/structural-code-search.md | markdown | 3.8 KB |
| references/workflow-artifacts.md | markdown | 2.6 KB |
| references/workflow-registry.md | markdown | 33.4 KB |
| references/wrapper-routing.md | markdown | 11.3 KB |
references/workflow-artifacts.md
View on GitHub# Workflow Artifact Operator Reference
Agent/operator surface only. Normal users remain chat-first: ask Hermes for the outcome. No command below executes work or implies approval.
```sh
omh runtime workflow-artifact <workflow> <operation> --input <json-file-or->
```
The bounded JSON result is `workflow_artifact_operation_result/v1`; the CLI is metadata-only and never invokes providers, subprocesses, schedulers, CRM mutation, or production promotion.
## Closed registry
- `decision-prototype`: `prepare`, `validate`, `observe`, `receipt`, `handoff`, `persist`
- `lifecycle-growth`: `build`, `prepare`, `validate`, `evaluate`, `readout`, `audience`, `promote`, `graduate`, `configuration`, `metrics`
- `product-discovery-validation`: `build`, `prepare`, `validate`, `audience-gate`, `evaluate`, `handoff`, `append`, `channel-feedback`
- `sales-pipeline-review`: `prepare`, `validate`, `evaluate`, `handoff`
Public contract and synthetic command inputs: [`docs/WORKFLOW-ARTIFACTS.md`](https://github.com/rlaope/oh-my-hermes/blob/main/docs/WORKFLOW-ARTIFACTS.md).
`build` derives schemas, statuses, metadata, and discovery hashes; `validate` is structural, not readiness. `prepare`/`evaluate` apply gates, so lifecycle may return `HOLD` for unknown consent and synthetic discovery remains `inconclusive`. Preparation does not persist; only explicit producer-owned `persist` or `append` writes validated metadata. `handoff` is proposed and executor-neutral and never dispatches, executes, or approves implementation.
Lifecycle launch review (`audience`, `promote`, `graduate`) returns separate `prepared_not_observed` records outside the six closed artifact schemas. Reachability is configuration analysis, not targeted membership or exposure; promotion defaults to `disabled` and requires explicit carry approvals; graduation proposes cleanup only from supplied rollout and rollback evidence. `prepare` and `evaluate` require a separate `lifecycle_growth_exposure_evidence/v1` companion under `exposure_evidence`: bound audience/safety policies, eligibility/exclusion checks, assigned population, actual reach, repeated-contact pressure, overlap, and channel-failure accounting. Unknown evidence holds expansion; first-launch preparation requires observed audience/reachability/contact checks without inventing treatment observations. `readout` accepts the same complete evaluation envelope, or reads a legacy artifact conservatively. Old artifacts still validate but cannot alone produce a new `ship` recommendation. Optional `evaluation_context` adds reference/baseline reasons; independently justified rollback remains rollback.
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: 472k | 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 |