rlaope/oh-my-hermes / skills/omh-docs
omh-docs
Verified[omh] Explaining OMH itself: current-source-first documentation for OMH itself: product identity, public capability catalog, model routing, local state, and long-term memory. Use when the user says: product-docs, OMH documentation, oh-my-hermes documentation, what is OMH, what is oh-my-hermes, how does OMH work, OMH capability catalog, OMH skill catalog.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.2 KB |
| references/capability-map.md | markdown | 2.6 KB |
| references/long-term-memory.md | markdown | 2.3 KB |
| references/model-routing-and-local-state.md | markdown | 3.7 KB |
| references/product-and-sources.md | markdown | 2.6 KB |
references/capability-map.md
View on GitHub# Capability and Public Skill Map
Load this reference for questions about what OMH can do, which skill fits a
task, the public ULW family, or how many skills are installed.
## Retrieve the Current Catalog
- For the public catalog, inspect the generated
`skills/omh-routing/references/catalog-index.md` and
`skills/omh-routing/references/workflow-registry.md` on the disclosed official
ref, or run `omh docs workflows --json` from a version-pinned checkout.
Registry IDs and internal fields are not public display names; derive public
names with `src/skills/catalog_types.py` and
`src/routing/display_names.py`.
- `omh list --json` reports only the current installed manifest. Count those
returned records only when the user asks about `current_local_install`; a
clean or differently profiled home can legitimately report zero skills.
- Use `omh recommend "<intent>" --json --limit 3` for a bounded recommendation;
a recommendation is not a reason to dump or memorize the full catalog.
- Verify the six capability families in `src/capabilities/families.py` at the
disclosed ref.
Never hard-code a mutable public catalog or installed-manifest count in an
answer or in the always-loaded skill body. They answer different questions and
can differ by version and profile.
## Six Capability Families
Use the current projection, whose public families are:
1. Plan and decide.
2. Learn and gather.
3. Retain knowledge.
4. Create materials and visuals.
5. Delegate coding and ship.
6. Operate and observe.
Representative exact public skills across the catalog:
| Area | Public skill examples |
| --- | --- |
| Operations | `omh-support-operations`, `omh-deploy-and-monitor` |
| Design | `omh-design-orchestration`, `omh-design-quality-gate` |
| Frontend | `omh-frontend`, `omh-frontend-refactor` |
| Budget variance, cash and close risk | `omh-finance-analysis` |
| Planning | `ulw-plan`, `ulw-interview`, `ulw-context` |
| Research | `ulw-research`, `omh-web-research`, `omh-source-finder` |
| Inference serving | `omh-inference-serving` |
| Reliability and review | `omh-reliability-review`, `omh-code-review` |
| Materials | `omh-materials-package`, `omh-report-package` |
| Retained knowledge | `omh-memory-new`, `omh-memory-sync`, `omh-decision-recall`, `omh-wiki` |
## Public ULW Names
When examples need an engine name, use only these current public labels:
`ulw-context`, `ulw-interview`, `ulw-research`, `ulw-plan`, `ulw-work`,
`ulw-maestro`, `ulw-loop`, `ulw-qa`, and `ulw-perf`.
Canonical implementation identifiers may differ internally. Do not expose an
internal identifier as the public skill name, and do not derive an installed
name by guessing from the canonical id.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |