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.
OMH Docs
Use this skill to answer questions about OMH itself from current sources. It defaults to passive inspection; it is not a generic documentation writer, workflow picker, or settings workflow.
Default Behavior
- Classify the question as a public-product fact, a current-local-install fact, or both. Keep those claim sets separate in the answer.
- Retrieve only the sources needed for the question. Current public facts must
come from official
rlaope/oh-my-hermessources; current local facts must come from passive CLI output, or narrowly scoped non-secret metadata. If a diagnostic command records state, disclose that side effect before running it. - Disclose the source URL or command/path and the relevant ref, version, or commit. If freshness cannot be established or official sources conflict, name that boundary.
- Answer the one-shot question directly. Do not create a durable artifact unless the user requests one.
For a public catalog count, inspect the generated catalog on the current
official ref. For an installed count, run omh list --json and count only that
installation manifest. Never quote a remembered or embedded count.
Source Route
For public/product questions, start with live GitHub repository metadata and
the current default branch, then read the relevant current source. Load
references/product-and-sources.md for the full official-source hierarchy,
product identity, conflict handling, and disclosure shape.
For current capability and public skill-name questions, load
references/capability-map.md. It covers the six public capability families,
representative exact skill names, catalog retrieval, and the public ULW labels.
For model routing or this machine's installation, load
references/model-routing-and-local-state.md. It separates published routing
behavior from passive local inspection, the state-writing omh doctor --json
diagnostic, and safe inspection of the resolved OMH home (~/.omh by default,
but overridable).
For retained knowledge or memory questions, load
references/long-term-memory.md. It distinguishes reviewed OMH project memory
from Hermes private long-term memory and points to docs/MEMORY.md and
docs/MEMORY_CONTEXT.md.
Public Product vs Local Install
- Public-product facts describe the current official repository at a disclosed branch, tag, version, or commit. A local checkout does not silently replace that source.
- Local-install facts describe only the inspected machine/profile at a disclosed OMH version or commit. Documented paths can be absent because install profiles and enabled features differ.
- When both matter, report them under separate labels before explaining any difference.
Safety and Mutation Boundary
Never read or print credentials, tokens, auth files, .env values, provider
secrets, raw private logs, or unrelated user content. Do not broaden a metadata
question into a home-directory scan.
If the user asks to set up, install, update, repair, change settings, edit
memory, or modify code, name the appropriate specialized public workflow such
as omh-doctor, omh-skill, omh-model-setup, or omh-memory-sync, then stop
before mutation unless that separate action is authorized.
Answer Contract
- Lead with the answer, then the public-product and local-install evidence that supports it.
- When both scopes matter, label the evidence
public_productandcurrent_local_installbefore explaining differences. - Cite the exact official source or disclosed local observation used.
- State version, branch, tag, or commit and the retrieval boundary.
- Name missing or conflicting evidence instead of filling it from recall.
- Mention execution/review status boundaries only when the question actually asks about status; they are not the center of this documentation skill.
Workflow Lane
- Current lane: Research and company ops. Stay read-only and return to the router when the request belongs to another workflow.
- Shared product, routing, compatibility, and evidence rules:
skill_view(name='omh-routing', file_path='references/skill-common-rail.md').
Completion Checklist
- Answer only from disclosed current sources or bounded local observations.
- Treat wrapper metadata-only memory comparisons as advisory local context, not proof of Hermes-memory mutation or raw-entry exposure.
- Record observed delegation results; otherwise return
not_availableornot_observed. - Prepared OMH routing is not execution, review, CI, or merge evidence.
- Preserve workflow intent and stop conditions; verify before claiming completion.
- Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only. When the requested output is delivered, put any open points inside the result and end with no question or offer; only when the person asked to choose or decide and that choice is still theirs, end with one specific question about it, not a list, a generic offer, or a footer; the shared rail's Reply Language And Host Voice and Turn Ending sections hold the full rule.
- Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
Recovery Notes
- If official retrieval fails, disclose the gap and use only versioned fallback evidence.
- If local metadata is absent, report that scoped absence without expanding into private content or mutation.
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: 471k | 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 |