rlaope/oh-my-hermes / skills/omh-jev-review-gate
omh-jev-review-gate
Verified[omh] Wants Jev risk flags on a diff under review: Jev review flags for a diff: auth, tests, migration risk, severity; flags only, never approves a merge. Use when the user says: jev-review-gate, jev review gate, ask jev to review this diff.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.7 KB |
| references/full-contract.md | markdown | 3.5 KB |
| references/preset.md | markdown | 1.1 KB |
references/preset.md
View on GitHub# `review_flags/v1`
OMH owns this question set and its rule ladder (`src/plugin_bundle/omh/jev_presets.py`). The tool
returns Jev's raw answers and, separately, `policy_result` with `computed_by: omh_preset`: the
answers are Jev's and the outcome is OMH's fixed rule. Thresholds: editorial_not_measured.
## What `state` carries, and what leaves the machine
`state` is an object with `file`, `diff`: one file path and that file's source diff. All of it is sent to the route's
host with the question text. OMH adds nothing else.
## Questions
| id | shape |
| --- | --- |
| `touches_auth_or_permissions` | noul |
| `changes_stored_data_shape` | noul |
| `tests_cover_the_change` | noul |
| `introduces_secret_or_key` | noul |
| `senior_would_block` | noul |
| `severity` | score: 4 levels |
## Outcomes
`flags_raised`, `no_flags`, `not_observed`. A non-answer is `not_observed` with `rule: not_answered:<status>`, so it never
reads as Jev's answer. No outcome approves, passes, merges, or declares work done.
The model is pinned to the version the thresholds were written against (`jev-1.13.0`, or
`jev-1.13` on the OpenRouter route).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |