Skip to content

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.

references/long-term-memory.md

View on GitHub
# Long-term Memory

Load this reference for questions about what OMH remembers, how reviewed
project context differs from Hermes memory, and which read-only sources explain
the current design.

## Two Memory Boundaries

- OMH project memory is reviewed, project-scoped context under `.omh/memory/`.
  Candidates remain separate from approved records; recall is bounded and
  source-labeled.
- Hermes long-term memory belongs to Hermes Agent. The bridge in
  `src/plugin_bundle/omh/hermes_memory.py` may read Hermes `MEMORY.md`,
  `USER.md`, memory-limit configuration, and approved OMH records to produce a
  metadata-only comparison. It cannot mutate Hermes memory.

The docs skill must not inspect or print raw Hermes memory merely because the
question mentions memory. Prefer the bridge's metadata-only summary; inspect
raw entries only when the user's narrowly scoped request and authorization make
that necessary.

An installed profile may also expose OMH-owned memory or learning metadata
under its resolved OMH home. Its presence and shape vary by version/profile and
do not prove that Hermes or a coding owner used the content.

## Current Sources

Read `docs/MEMORY.md` for reviewed project-memory lifecycle and
`docs/MEMORY_CONTEXT.md` for context admission, replay, and handoff boundaries.
Use `omh memory --help` and narrowly targeted read-only memory inspection
commands to confirm what the current installed CLI exposes. Disclose the
official ref and the local version or commit separately.

## Public Workflows

- `omh-memory-new` prepares a bounded new-memory candidate.
- `omh-memory-sync` reviews existing retained memory and proposed changes.
- `omh-decision-recall` retrieves reviewed rejected-decision context.
- `omh-wiki` organizes durable project knowledge.

These names identify specialized workflows; this docs skill only explains
them. If the user asks to capture, approve, retire, restore, prune, synchronize,
or otherwise mutate memory, route to the matching public workflow and stop
before mutation unless separately authorized.

## Privacy

Never answer a memory question by printing raw private logs, prompts,
transcripts, credentials, tokens, auth files, `.env` values, provider secrets,
or unrelated user content. Prefer schema, lifecycle, count, status, and
source-reference metadata over raw content.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexUnverifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall