code-review
starsforks
How to install code-review?
rlaope/oh-my-hermes/code-review
$npx -y skills add rlaope/oh-my-hermes --skill code-review[omh] Hermes Code Review workflow: bug-first review with evidence.
SKILL.md
| 1 | # Code Review |
| 2 | |
| 3 | This is a Hermes-native `code-review` workflow skill. |
| 4 | |
| 5 | ## Why This Exists |
| 6 | |
| 7 | `code-review` exists to make review bug-first and evidence-grounded: findings must cite concrete files, diffs, commands, or artifacts before any summary or fix proposal. |
| 8 | |
| 9 | ## Do Not Use When |
| 10 | |
| 11 | - The user asks to implement the fix rather than review existing code or claims. |
| 12 | - There is no diff, file set, claim, artifact, or expected behavior to review. |
| 13 | - The request is broad product critique, strategy, or planning rather than code or evidence review. |
| 14 | |
| 15 | ## Examples |
| 16 | |
| 17 | Good example: |
| 18 | |
| 19 | - Prompt: $code-review review this PR for install/update UX regressions and missing tests. |
| 20 | - Expected behavior: Lead with ranked findings, cite concrete evidence, then list open questions and test gaps. |
| 21 | - Why: The task is explicitly review-shaped and has a behavioral risk surface. |
| 22 | |
| 23 | Bad example: |
| 24 | |
| 25 | - Prompt: $code-review add the missing setup flag and commit it. |
| 26 | - Expected behavior: Route implementation to a selected executor/runtime after review findings are established. |
| 27 | - Why: Review can identify the issue, but code mutation is a separate execution step. |
| 28 | |
| 29 | ## Completion Checklist |
| 30 | |
| 31 | - Findings come first and are ranked by severity before summary or praise. |
| 32 | - Every finding cites file, diff, command output, artifact, or expected behavior evidence. |
| 33 | - No-issue reviews still name residual risk, missing tests, and independent review evidence if unavailable. |
| 34 | - Fix implementation, architecture follow-up, and CI/merge claims stay separate from the review result. |
| 35 | |
| 36 | ## Recovery Notes |
| 37 | |
| 38 | - If no diff, file set, PR, or artifact is available, inspect the requested target or ask one target question before reviewing. |
| 39 | - If tests fail or are missing, cite the exact command gap and do not approve the change as verified. |
| 40 | - If independent review evidence is unavailable, say so directly instead of implying a second reviewer passed it. |
| 41 | |
| 42 | ## OMH Context Rail |
| 43 | |
| 44 | - This skill is part of OMH's Hermes workflow layer, not a standalone executor. |
| 45 | - Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries. |
| 46 | - Current lane: **Coding handoff** (`idea-to-deploy`, `cto-loop`, `deploy-and-monitor`, `code-review`, `build-failure-triage`, `verification-gate`, `security-safety-review`, `ultrawork`, `+7 more`) - coding owners, handoffs, review, CI, and merge evidence. |
| 47 | - If the user intent belongs to another OMH lane, hand back to `oh-my-hermes` or name the adjacent workflow instead of force-fitting this skill. |
| 48 | - Cross-skill context: every OMH skill: match lane; generic tool can render or execute. |
| 49 | - Generic-tool checkpoint: image->img-summary; frontend->frontend/a11y/visual-qa; paper->paper-learning; content->content-operator; media->media-input-operator; file->materials-package; search->web-research; live->live-info-operator; audit->workspace/production/security; failures->build-failure; verify->verification-gate; code->codegraph/onboarding/ultraprocess. |
| 50 | - Coverage: Every generated workflow skill carries this rail. |
| 51 | - Normal users talk to Hermes; OMH CLI is infra. |
| 52 | - Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence. |
| 53 | |
| 54 | ## Use When |
| 55 | |
| 56 | Use for review-shaped requests; findings come first and must cite concrete evidence. |
| 57 | |
| 58 | Strong routing signals: `code-review`, `$code-review`, `review`, `audit`, `find bugs`, `release gate`, `claim audit`, `evidence audit`, `README claim`, `what actually happened`, `code review`, `review gate`, `리뷰`, `코드 리뷰`, `리뷰까지`, `릴리즈 전`, `실제 코드와 맞는가`, `실제로 뭐 했는지`, `검증된 결과` |
| 59 | |
| 60 | ## Catalog Metadata |
| 61 | |
| 62 | Category: `review` |
| 63 | Phase: `critique` |
| 64 | Hermes role: `reviewer` |
| 65 | Quality tier: `finding-evidence-gated` |
| 66 | |
| 67 | Quality bar: |
| 68 | |
| 69 | - Lead with ranked findings grounded in file, diff, command, or artifact evidence. |
| 70 | - Separate review findings from fix implementation; fixes become executor work. |
| 71 | - For Hermes-owned coding work, inspect `hermes_coding_harness/v1` and require review evidence before upgrading the reviewer lane. |
| 72 | - Say clearly when no actionable issue is found and name remaining test gaps. |
| 73 | |
| 74 | Handoff policy: |
| 75 | |
| 76 | Hermes may frame and summarize review evidence; fixes or code mutations found during review should be delegated to the selected coding executor. |
| 77 | |
| 78 | Required inputs: |
| 79 | |
| 80 | - diff or files |
| 81 | - expected behavior |
| 82 | - test evidence |
| 83 | |
| 84 | Expected outputs: |
| 85 | |
| 86 | - ranked findings |
| 87 | - open questions |
| 88 | - test gaps |
| 89 | |
| 90 | Artifact expectations: |
| 91 | |
| 92 | - critic run record when review evidence is captured |
| 93 | |
| 94 | Safety rules: |
| 95 | |
| 96 | - Findings come before summaries. |
| 97 | - Cite concrete evidence for every finding. |
| 98 | - Say clearly when no issue is found. |
| 99 | |
| 100 | ## Harness Discipline |
| 101 | |
| 102 | - Start from the |
People who liked this also viewed
6 picksType
- requesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirementsSkillsJul 2026
- code-reviewSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- receiving-code-reviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performativeSkillsJul 2026
- baoyu-format-markdownFormats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or imprSkillsJul 2026
- code-review-excellenceMaster effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing reSkillsJul 2026
- code-review-and-qualityConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensiSkillsJul 2026
