Skip to content
cccskills
FreePublished on GitHub

omh-docs

Answer questions about OMH’s capabilities, model selection, local installation, and long-term memory using current sources. Distinguish official product information from observations on the inspected machine, with sources and version details to explain the findings.

OriginalShow the original description

[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.

See how to install

Good for

  • Understand OMH’s capabilities
  • Check skills in the current installation
  • Understand how OMH selects models
  • Clarify where retained knowledge and memory belong

Files included (5)

  • SKILL.md6.2 KB
  • references/capability-map.md2.7 KB
  • references/long-term-memory.md2.3 KB
  • references/model-routing-and-local-state.md3.2 KB
  • references/product-and-sources.md2.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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

  1. Classify the question as a public-product fact, a current-local-install fact, or both. Keep those claim sets separate in the answer.
  2. Retrieve only the sources needed for the question. Current public facts must come from official rlaope/oh-my-hermes sources; 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.
  3. 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.
  4. 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_product and current_local_install before 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_available or not_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; OMH's record terms (surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in records and tool calls, never in the sentence the user reads unless they ask about one; and when a stop condition or a decision the user owns ends the turn, offer the next action as a question rather than declaring what will not be done.
  • 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.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

dag-ulw

FreeSummary

Coordinate a large job by splitting it into small tasks with explicit dependencies. Run ready tasks in parallel through Hermes, verify the combined result separately, and repair failures within defined limits before reporting completed work and remaining gaps.

  • Delivering a feature across multiple modules
  • Coordinating a migration with ordered steps
  • Managing a broad cleanup across separate work areas
rlaope/oh-my-hermes3.6KUpdated Oct 22, 2026

model-onboarding

FreeSummary

Guide the addition of a new model generation to oh-my-hermes. The workflow checks model recognition, official specifications, routing rules that select models for tasks, documented pricing, and live access, then validates changes with tests and comparative benchmarks.

  • Add a new model generation to oh-my-hermes
  • Check API model IDs and dated snapshot recognition
  • Update model selection chains and related documentation
rlaope/oh-my-hermes3.6KUpdated Oct 22, 2026

Prepare an accessibility audit for an interface using WCAG 2.2 AA, an accessibility standard. Organize evidence for keyboard use, screen readers, contrast, target size, and zoom behavior, then document findings, missing checks, and remediation handoffs.

  • Reviewing checkout accessibility against WCAG 2.2 AA
  • Checking keyboard access and focus order
  • Organizing screen-reader labels and announcement evidence
rlaope/oh-my-hermes3.6KUpdated Oct 22, 2026

omh-achievements

FreeSummary

Summarize earned badges, recent unlocks, achievement tiers, and progress using local files from the hermes-achievements plugin. Prepare a badge list or report section while making missing information and the limits of the recorded snapshot clear.

  • Checking earned badges
  • Reviewing recently unlocked achievements
  • Finding progress toward the next achievement tier
rlaope/oh-my-hermes3.6KUpdated Oct 22, 2026

Examine a technical proposal through independent perspectives, challenge their findings, and resolve objections. The result is a structured set of constraints, decisions, risks, and open questions for a separate planning workflow.

  • Reviewing a technical proposal before planning
  • Challenging assumptions behind a migration
  • Organizing risks and unresolved questions
rlaope/oh-my-hermes3.6KUpdated Oct 22, 2026

omh-agent-board

FreeSummary

Coordinate multiple Hermes agents or profiles through a shared task board. Organize assignments, handoffs, activity updates, blockers, and completion states, while distinguishing planned actions from work supported by observed results.

  • Coordinate agent roles for a launch checklist
  • Track task handoffs and blockers
  • Prepare work for pickup across profiles or after a restart
rlaope/oh-my-hermes3.6KUpdated Oct 22, 2026

See all skills by rlaope

Report a problem with this skill