Omh Skill Health

Skill Health

This is an OMH skill-health workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

Why This Exists

skill-health exists because a skill portfolio drifts in ways no single run shows -- a managed skill changed in place, an authoring finding nobody fixed, an update waiting on its hub -- and use counts measure none of that: it gathers the observed signals into one card with an owner lane and a safe next action for each, and changes nothing itself.

Do Not Use When

• OMH setup, install, or a skill that does not load.
• One run that missed a route or went wrong.
• Finding a new skill to adopt; use omh-skill-scout.

Examples

Good example:

• Prompt: skill-health show the OMH skill portfolio dashboard with stale surfaces, failure patterns, pending amendments, and top improvement actions.
• Expected behavior: Produce prepare_skill_health with required context, wrapper actions, and not-evidence boundaries.
• Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.

Bad example:

• Prompt: skill-health claim every skill is working and patch the failures automatically without observed signals or review.
• Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
• Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.

Completion Checklist

• Dashboard scope, source surfaces, stale/duplicate criteria, and stop condition are explicit.
• Install/setup health, catalog operations, and failure retrospectives stay out of the health card.
• No skill, prompt, doc, memory, or model behavior is claimed changed until a reviewed implementation records evidence.
• Never present use, view, or load counts, .usage.json included, as a health, prune, archive, or retire signal: a rarely used skill is not an unhealthy one, and no health card recommends removing, archiving, or pruning a skill for being used little.
• On Hermes, read the skill audit ledger read-only (that skill's entries in skills/.curator_ledger.jsonl under the active profile's Hermes home, or hermes curator ledger --skill <name> --limit <n>, which lists only the 20 newest entries by default): an entry against an OMH-managed skill means Hermes changed that managed copy outside OMH, so it may no longer match its generated body; report it as drift with the entry's action and actor (agent, user, or curator, which covers Hermes' curator and its background review). An OMH-managed skill is one OMH installed, under a label OMH's catalog renders such as omh-plan or ulw-work; a companion skill the person or an agent created is theirs, whatever its name. An empty ledger is unknown, not clean, because skills.ledger: false turns it off.
• On Hermes, record an authoring finding only from the lint_warnings a skill_manage write returned, which are advisory and never proof a skill works; only some writes return them (an edit never does), so a write without them is not a clean lint. Record an available update for a hub-installed skill only from hermes skills check output that was seen; that hub request is Hermes' own, not OMH's.

Recovery Notes

• If the request is about OMH setup, install, stale package paths, or command availability, it is outside this skill.
• If the request is a missed-route or self-improvement trace, it is outside this skill.

When to Use

Use when operators need portfolio-level skill health without treating it as install repair, live execution success, or automatic skill mutation.

Copy code
Strong routing signals: `skill-health`, `skill health`, `skill portfolio health`, `skill dashboard`, `skill health dashboard`, `skill failure pattern dashboard`, `skill failure patterns`, `pending skill amendments`, `skill amendments`, `스킬 헬스`, `스킬 상태`, `스킬 대시보드`, `스킬 실패 패턴`, `스킬 개선 후보`, `스킬 보류 수정`

Catalog Metadata

Category: operations Phase: skill-health Quality tier: workflow-surface-gated Reasoning demand: light

Quality bar:

• Name the user-facing workflow objective, required context, next action, and stop condition.
• Separate prepared guidance from observed platform, runtime, connector, file, memory, or delivery evidence.
• Expose missing tools, credentials, targets, or observations as user-visible gaps.

Required inputs:

• user request
• target context
• delivery or status expectation
• known missing evidence

Expected outputs:

• catalog, generated, reference, harness, and capability-surface status
• observed failure signals, or an explicit statement that none were supplied
• pending amendment review slots and top safe actions with owner lane and verification path

Artifact expectations:

• skill_health_card/v1 metadata-only wrapper card recording surface status, observed-only failure signals, pending amendments, and the non-mutation boundary

Safety rules:

• A skill health dashboard is not install/setup health, live skill execution success, automatic skill mutation, model training, verification, review, CI, or proof that future routing is fixed.
• Do not claim connector, gateway, runtime, file generation, memory mutation, or host automation evidence from prepared guidance.

Runtime Evidence

Use the current host's own tools and subagent/task mechanism when available; otherwise run the same lanes sequentially or name the unavailable capability. A prepared plan, handoff, checklist, or skill installation is not execution, review, CI, merge-readiness, or merge evidence. Record actual tool results, or not_observed / not_available, in the record; never invent dispatch or host accounting. Treat supplied context as advisory, not proof of hidden memory reads or writes. State scope, constraints, verification, and the stop condition before work. Reply in the user's own words and the host's own voice: the host's 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 real unresolved user decision or a useful briefing discussion remains, offer one specific, content-linked question. Completed work needs no question; omit unrelated non-action footers and generic offers to continue. Supporting paths are relative to this skill directory; sibling skill paths are relative to its parent. Resolve them from the host-provided skill base directory ({baseDir} on hosts that provide it), never a hardcoded install location. A named workflow not installed here is unavailable, not permission to emulate its host-specific capabilities. Verify through the real surface before done.