Skip to content

rlaope/oh-my-hermes / skills/omh-workflow-learning

omh-workflow-learning

Verified

[omh] Missed route or run lessons to record: classify and review self-improvement store routes as an auxiliary review lane before durable writes, then record workflow attempts as metadata-only traces, evals, review queues, patch proposals, regression cases, audits, indexes, and exports. Use when the user says: workflow-learning, workflow learning, route-signal, self-improvement store routing, store route review, memory skill wiki routing, learning trace, learning audit.

Workflow Learning

This is a Hermes-native workflow-learning workflow skill.

Why This Exists

workflow-learning exists because a lesson from a run can land in the wrong store or in none, and Hermes' own background review can write skills and memory after a turn with no OMH review: it routes each lesson to memory, skill, wiki, failure-retrospective, or automation review as metadata-only records, and checks what Hermes wrote on its own against what was reviewed.

Do Not Use When

  • A lasting fact the user wants kept; capture it with omh-memory-new.
  • Lessons seen across runs or projects to score and promote; use omh-instinct-ledger.
  • A run that is stuck or looping right now; use omh-agent-debug.

Examples

Good example:

  • Prompt: workflow-learning route this self-improvement note before deciding whether it is memory, skill, wiki, failure-retrospective, or automation material.
  • Expected behavior: Produce record_workflow_learning_trace 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: workflow-learning silently patch the skill and claim future behavior is fixed.
  • 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

  • Classify a lesson before any write: omh learning route-signal "<one-line lesson>" names the destination (memory, skill, wiki, failure-retrospective, automation review, manual_review_candidate for an ambiguous signal, or discard_transient for private or transient content); add --record only after the user agrees to keep the route. Show the destination and why, list pending routes with omh learning store-routes, and leave omh learning review-route to the person. A fact goes to omh-memory-new and a skill change stays a skill_update_candidate; this skill writes none of those stores.
  • Read Hermes' skill audit ledger read-only (skills/.curator_ledger.jsonl under the active profile's Hermes home, or hermes curator ledger --limit <n>, which lists only the 20 newest entries by default) and report each entry whose actor is agent or curator (Hermes' curator or its background review) that no store-route record (omh learning store-routes) or approved skill_update_candidate accounts for as unreviewed_native_write, which means OMH holds no record of that write, not that nobody reviewed it. An empty ledger is unknown, not clean, because skills.ledger: false turns it off. A trimmed ledger is incomplete too: from Hermes v2026.9.24 the oldest entries are dropped past skills.ledger_max_bytes, so report the window you read (entry count, oldest timestamp) and treat an older write as not_observed, not clean.
  • Mark an approved skill_update_candidate landed only from a skill_manage result for that skill that succeeded without staged: true, or from a ledger entry that is dated after the approval, has actor agent or user and action create, edit, patch, or write_file, and lists the approved target file in its after manifest. An entry by curator, or one that deletes, archives, rolls back, or purges, never marks it landed, and a staged result waits in /skills pending for the person and has not landed.
  • The ledger records skill writes only: a memory write by Hermes' background review is visible only when Hermes staged it under pending/memory/ with origin: background_review, and is not_observed otherwise.
  • Point the user to /journey in the Hermes CLI for Hermes' own view of what it learned; reading the ledger or the journey changes nothing, and undoing an entry (hermes curator rollback <id>) is the person's own step, never OMH's.

Recovery Notes

  • If required context is missing, ask one blocking question or route back to the narrower workflow.
  • If runtime or wrapper evidence is unavailable, keep the status as not_observed and expose the next observable action.
  • Native write policy required stops promotion as unsupported and not_required is not an approval; drift unlinks only the managed SKILL.md and keeps generations and receipts, and an incomplete promotion resumes only via explicit retry --receipt-id.

Workflow Lane

  • Current lane: Automation and status - schedules, status, health, and ops review.
  • If intent belongs to another lane, hand back to omh-routing or name the adjacent workflow.
  • Shared product, routing, compatibility, and evidence rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md').

When to Use

Use after a Hermes/OMH workflow attempt should become inspectable, evaluable, routed to memory/skill/wiki/failure-retrospective/automation review, persisted as a metadata-only store-route decision, queued for review, audited, replayable as a regression, converted to a patch handoff, exported, repaired after index drift, or captured as a missed-route signal without raw prompts. Store-route records are an auxiliary review lane surfaced by learning review and learning store-routes; they are not canonical learning index/export records until a reviewed destination produces its own artifact.

Strong routing signals: `workflow-learning`, `workflow learning`, `route-signal`, `self-improvement store routing`, `store route review`, `memory skill wiki routing`, `learning trace`, `learning audit`, `self improvement store routing`, `store routing`, `where should this learning go`, `audit learning`, `learning review`, `review queue`, `review-route`, `store-routes`, `learning readiness`, `learning export`, `export bundle`, `learning index`, `index rebuild`, `execution trace`, `skill improvement`, `improvement candidate`, `regression corpus`, `GEPA`, `VPRM`, `process supervision`, `why did this route`, `missed route`, `missed workflow`, `did not use OMH`, `OMH was not used`, `learn from this run`, `이번 실행 학습`, `스킬 개선`, `회귀 케이스`, `실행 기록`, `학습 기록`, `학습 점검`, `학습 준비 상태`, `학습 내보내기`, `OMH 안 썼어`, `워크플로 누락`, `라우팅 누락`

Catalog Metadata

Category: optimization Phase: workflow-learning Hermes role: tracker Quality tier: workflow-surface-gated Reasoning demand: heavy

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.

Handoff policy:

Keep this as Hermes-facing orchestration guidance first. Prepare executor, connector, gateway, or host-runtime handoff only when the user accepts that next step and observed evidence can be recorded.

Required inputs:

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

Expected outputs:

  • workflow-learning/v1 card or guidance
  • next action
  • prepared-vs-observed boundary

Artifact expectations:

  • workflow-learning/v1 metadata-only runtime or wrapper card when recorded
  • browser_skill_promotion_approval_receipt/v1 per operation: promotion diff then approve --reviewed-diff-digest --reviewer; source learning promotion --source-id sd-<id> (reviewed draft) or web-qa promotion --trace-id bwt-<id>

Safety rules:

  • A workflow learning trace, self-improvement store route, patch proposal, or export is process evidence for review. It is not automatic model training, memory mutation, skill mutation, wiki write, automation creation, execution, verification, CI, or merge evidence.
  • Do not claim connector, gateway, runtime, file generation, memory mutation, or host automation evidence from prepared guidance.

Runtime Evidence

Preferred harness for this skill: workflow-learning.

omh runtime record --skill workflow-learning --harness workflow-learning --status started

Record observed delegation results; otherwise return not_available or not_observed. Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.

  • Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes. 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.

Shared product, compatibility, topology, memory, harness, and execution rules: skill_view(name='omh-routing', file_path='references/skill-common-rail.md'). Load it when applicable; otherwise name an unavailable capability.

rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall