Workflow Learning
This is a Hermes-native workflow-learning workflow skill.
Why This Exists
workflow-learning exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
Do Not Use When
- The request is already handled by a narrower explicit skill with stronger evidence.
- The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
- The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
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
- Confirm the workflow target, evidence boundary, and stop condition are named.
- Report which outputs are prepared, observed, blocked, or missing.
- Name the smallest next verification or handoff instead of claiming completion from narration.
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 (
achievements, workspace-audit, production-audit, automation-blueprint, github-event-ops, github-issue-intake, buzz, agent-board, +35 more) - schedules, status, health, and ops review.
- If intent belongs to another lane, hand back to
oh-my-hermes or name the adjacent workflow.
- Shared product, routing, compatibility, and evidence rules:
omh-routing/references/skill-common-rail.md.
Use When
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 only through
omh web-qa promotion diff then approve --reviewed-diff-digest --reviewer on an approved, replay-passing omh web-qa trace; every operation needs its own reviewed exact diff
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.
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: omh-routing/references/skill-common-rail.md. Load it when applicable; otherwise name an unavailable capability.
1---2name: omh-workflow-learning3description: [omh] Hermes workflow learning workflow: 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.4---5
6# Workflow Learning
7
8This is a Hermes-native `workflow-learning` workflow skill.
9
10## Why This Exists
11
12`workflow-learning` exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration.
13
14## Do Not Use When
15
16- The request is already handled by a narrower explicit skill with stronger evidence.
17- The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents.
18- The only safe answer is to ask for missing authority, credentials, target, or observed evidence first.
19
20## Examples
21
22Good example:
23
24- Prompt: workflow-learning route this self-improvement note before deciding whether it is memory, skill, wiki, failure-retrospective, or automation material.
25- Expected behavior: Produce `record_workflow_learning_trace` with required context, wrapper actions, and not-evidence boundaries.
26- Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution.
27
28Bad example:
29
30- Prompt: workflow-learning silently patch the skill and claim future behavior is fixed.
31- Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened.
32- Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence.
33
34## Completion Checklist
35
36- Confirm the workflow target, evidence boundary, and stop condition are named.
37- Report which outputs are prepared, observed, blocked, or missing.
38- Name the smallest next verification or handoff instead of claiming completion from narration.
39
40## Recovery Notes
41
42- If required context is missing, ask one blocking question or route back to the narrower workflow.
43- If runtime or wrapper evidence is unavailable, keep the status as not_observed and expose the next observable action.
44- 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`.
45
46## Workflow Lane
47
48- Current lane: **Automation and status** (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `github-issue-intake`, `buzz`, `agent-board`, `+35 more`) - schedules, status, health, and ops review.
49- If intent belongs to another lane, hand back to `oh-my-hermes` or name the adjacent workflow.
50- Shared product, routing, compatibility, and evidence rules: `omh-routing/references/skill-common-rail.md`.
51
52## Use When
53
54Use 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.
55
56 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`
57
58## Catalog Metadata
59
60Category: `optimization`
61Phase: `workflow-learning`
62Hermes role: `tracker`
63Quality tier: `workflow-surface-gated`
64Reasoning demand: `heavy`
65
66Quality bar:
67
68- Name the user-facing workflow objective, required context, next action, and stop condition.
69- Separate prepared guidance from observed platform, runtime, connector, file, memory, or delivery evidence.
70- Expose missing tools, credentials, targets, or observations as user-visible gaps.
71
72Handoff policy:
73
74Keep 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.
75
76Required inputs:
77
78- user request
79- target context
80- delivery or status expectation
81- known missing evidence
82
83Expected outputs:
84
85- workflow-learning/v1 card or guidance
86- next action
87- prepared-vs-observed boundary
88
89Artifact expectations:
90
91- workflow-learning/v1 metadata-only runtime or wrapper card when recorded
92- browser_skill_promotion_approval_receipt/v1 only through `omh web-qa promotion diff` then `approve --reviewed-diff-digest --reviewer` on an approved, replay-passing `omh web-qa trace`; every operation needs its own reviewed exact diff
93
94Safety rules:
95
96- 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.
97- Do not claim connector, gateway, runtime, file generation, memory mutation, or host automation evidence from prepared guidance.
98
99## Runtime Evidence
100
101Preferred harness for this skill: `workflow-learning`.
102
103```sh
104omh runtime record --skill workflow-learning --harness workflow-learning --status started
105```
106
107Record observed delegation results; otherwise return `not_available` or `not_observed`.
108Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.
109- Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes.
110Preserve workflow intent and stop conditions; verify before claiming completion.
111
112Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.
113
114Shared product, compatibility, topology, memory, harness, and execution rules: `omh-routing/references/skill-common-rail.md`. Load it when applicable; otherwise name an unavailable capability.
rlaope