Ops Review
This is an OMH ops-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Why This Exists
ops-review exists to keep operations work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.
Do Not Use When
- The review is over sales stages, forecast categories, deal aging, or seller forecast rather than generic operating status; use
sales-pipeline-review.
- The primary output is durable cadence history, minutes, a decision log, or action history; use
operating-rhythm.
Examples
Good example:
- Prompt: ops-review: summarize this week’s support queue, release blockers, owner status, and next operating risks.
- Expected behavior: Create an operations status review with owners, blockers, evidence gaps, and next actions.
- Why: The request is an operating review rather than a one-off plan or coding handoff.
Bad example:
- Prompt: ops-review: treat casual chat or unaccepted work as if this workflow already produced verified results.
- Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing
ops-review.
- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.
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.
Use When
Use when Hermes should summarize observed status, risks, blockers, priorities, and follow-up actions for recurring operating work.
Strong routing signals: `ops-review`, `ops review`, `weekly ops review`, `status review`, `operating review`, `release risks`, `risks and blockers`, `priorities`, `weekly status`, `운영 리뷰`, `주간 운영`, `상태 리뷰`, `리스크`, `블로커`, `우선순위`, `릴리즈 리스크`
Catalog Metadata
Category: operations
Phase: status-review
Quality tier: status-gated
Reasoning demand: light
Quality bar:
- Tie every status claim to observed evidence or mark it as unknown.
- Separate risks, blockers, priorities, and follow-up owners.
- Keep code fixes as explicit follow-up handoffs, not implicit ops-review output.
Required inputs:
- status evidence
- scope
- time window
- known risks
Expected outputs:
- status summary
- risks
- blockers
- priorities
- follow-up actions
Artifact expectations:
- ops review record or status artifact when a wrapper captures it
Artifact contracts:
This label denotes the machine-enforcement level, not a skill quality score and not an observed evidence state.
- contract_id:
ops-review; enforcement_level: guidance_only; consumer_id: none
Safety rules:
- Do not infer status from missing evidence.
- Separate observed facts, risks, blockers, decisions, and follow-up actions.
- Do not report review, CI, release, or merge readiness from an ops summary alone.
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. Report actual tool results or
not_observed / not_available; 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.
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.
1---2name: omh-ops-review-23description: [omh] Hermes Ops Review workflow: status, risks, blockers, priorities, and follow-ups. Use when the user says: ops-review, ops review, weekly ops review, status review, operating review, release risks, risks and blockers, priorities.4---56# Ops Review78This is an OMH `ops-review` workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).910## Why This Exists1112`ops-review` exists to keep `operations` work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration.1314## Do Not Use When1516- The review is over sales stages, forecast categories, deal aging, or seller forecast rather than generic operating status; use `sales-pipeline-review`.17- The primary output is durable cadence history, minutes, a decision log, or action history; use `operating-rhythm`.1819## Examples2021Good example:2223- Prompt: ops-review: summarize this week’s support queue, release blockers, owner status, and next operating risks.24- Expected behavior: Create an operations status review with owners, blockers, evidence gaps, and next actions.25- Why: The request is an operating review rather than a one-off plan or coding handoff.2627Bad example:2829- Prompt: ops-review: treat casual chat or unaccepted work as if this workflow already produced verified results.30- Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing `ops-review`.31- Why: The request lacks the required inputs or would overclaim work that Hermes did not observe.3233## Completion Checklist3435- Confirm the workflow target, evidence boundary, and stop condition are named.36- Report which outputs are prepared, observed, blocked, or missing.37- Name the smallest next verification or handoff instead of claiming completion from narration.3839## Recovery Notes4041- If required context is missing, ask one blocking question or route back to the narrower workflow.42- If runtime or wrapper evidence is unavailable, keep the status as not_observed and expose the next observable action.43444546## Use When4748Use when Hermes should summarize observed status, risks, blockers, priorities, and follow-up actions for recurring operating work.4950 Strong routing signals: `ops-review`, `ops review`, `weekly ops review`, `status review`, `operating review`, `release risks`, `risks and blockers`, `priorities`, `weekly status`, `운영 리뷰`, `주간 운영`, `상태 리뷰`, `리스크`, `블로커`, `우선순위`, `릴리즈 리스크`5152## Catalog Metadata5354Category: `operations`55Phase: `status-review`56Quality tier: `status-gated`57Reasoning demand: `light`5859Quality bar:6061- Tie every status claim to observed evidence or mark it as unknown.62- Separate risks, blockers, priorities, and follow-up owners.63- Keep code fixes as explicit follow-up handoffs, not implicit ops-review output.6465Required inputs:6667- status evidence68- scope69- time window70- known risks7172Expected outputs:7374- status summary75- risks76- blockers77- priorities78- follow-up actions7980Artifact expectations:8182- ops review record or status artifact when a wrapper captures it8384Artifact contracts:8586This label denotes the machine-enforcement level, not a skill quality score and not an observed evidence state.8788- contract_id: `ops-review`; enforcement_level: `guidance_only`; consumer_id: `none`8990Safety rules:9192- Do not infer status from missing evidence.93- Separate observed facts, risks, blockers, decisions, and follow-up actions.94- Do not report review, CI, release, or merge readiness from an ops summary alone.9596## Runtime Evidence9798Use the current host's own tools and subagent/task mechanism when available;99otherwise run the same lanes sequentially or name the unavailable capability.100A prepared plan, handoff, checklist, or skill installation is not execution,101review, CI, merge-readiness, or merge evidence. Report actual tool results or102`not_observed` / `not_available`; never invent dispatch or host accounting.103Treat supplied context as advisory, not proof of hidden memory reads or writes.104State scope, constraints, verification, and the stop condition before work.105Supporting paths are relative to this skill directory; sibling skill paths are106relative to its parent. Resolve them from the host-provided skill base directory107(`{baseDir}` on hosts that provide it), never a hardcoded install location.108A named workflow not installed here is unavailable, not permission to emulate109its host-specific capabilities. Verify through the real surface before done.