GitHub Review Iteration
prisma/orm
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
Code and plan review with multi-angle dispatch. An agent skill from KaimingWan/oh-my-kiro.
Install Omk Reviewing
$ npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install KaimingWan/oh-my-kiro omk-reviewing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/omk-reviewing .claude/skills/omk-reviewing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "omk-reviewing" agent skill from https://github.com/KaimingWan/oh-my-kiro/tree/main/skills/omk-reviewing into .claude/skills/omk-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omk-reviewing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/KaimingWan/oh-my-kiro/tree/main/skills/omk-reviewingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install KaimingWan/oh-my-kiro omk-reviewing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/omk-reviewing .agents/skills/omk-reviewing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "omk-reviewing" agent skill from https://github.com/KaimingWan/oh-my-kiro/tree/main/skills/omk-reviewing into .agents/skills/omk-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omk-reviewing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install KaimingWan/oh-my-kiro omk-reviewing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/omk-reviewing .cursor/skills/omk-reviewing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "omk-reviewing" agent skill from https://github.com/KaimingWan/oh-my-kiro/tree/main/skills/omk-reviewing into .cursor/skills/omk-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omk-reviewing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/KaimingWan/oh-my-kiro.git --path skills/omk-reviewing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install KaimingWan/oh-my-kiro omk-reviewing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/omk-reviewing .gemini/skills/omk-reviewing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "omk-reviewing" agent skill from https://github.com/KaimingWan/oh-my-kiro/tree/main/skills/omk-reviewing into .gemini/skills/omk-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omk-reviewing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install KaimingWan/oh-my-kiro omk-reviewingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/omk-reviewing .github/skills/omk-reviewing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "omk-reviewing" agent skill from https://github.com/KaimingWan/oh-my-kiro/tree/main/skills/omk-reviewing into .github/skills/omk-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omk-reviewing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install KaimingWan/oh-my-kiro omk-reviewing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KaimingWan/oh-my-kiro.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/omk-reviewing .opencode/skills/omk-reviewing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "omk-reviewing" agent skill from https://github.com/KaimingWan/oh-my-kiro/tree/main/skills/omk-reviewing into .opencode/skills/omk-reviewing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "omk-reviewing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
omk-reviewing- GitHub stars
- 107
- Token cost
- ~1.9k tokens
- SKILL.md length
- 929 words
- Files
- 6 (incl. references)
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- MIT
At a glance
Code and plan review with multi-angle dispatch. An agent skill from KaimingWan/oh-my-kiro.
- Works in 7 steps: Preflight context → SOLID + architecture check → Security scan → …
- User says review
- SKILL.md covers Trigger Examples, Requesting Review, Iron Principle: Respect the… and Executing Code Review (for…, plus 1 more section
- Calls git
What it does
Omk Reviewing is an agent skill from KaimingWan/oh-my-kiro. Code and plan review with multi-angle dispatch. Trigger when user says 'review', 'code review', 'check my code', 'PR review', '@review', or when completing a plan phase that requires review. Also trigger before merge, after major feature completion, or when user asks for feedback on implementation quality.
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/code-quality-checklist.md`, `references/output-format.md` and `references/removal-plan.md`).
It sits in Development, covering Code review, Pull requests and Subagents. The licence is MIT.
When your agent uses it
- User says review
- Completing a plan phase that requires review
- After major feature completion
- User asks for feedback on implementation quality
Example prompts
- “review”
- “code review”
- “check my code”
- “/omk-reviewing”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit ba228be. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Omk Reviewing loads about 1.9k tokens when it runs, and up to ~5.6k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 929 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from KaimingWan/oh-my-kiro at commit ba228be, republished under its MIT licence (© KaimingWan). 929 words, ~1,896 tokens.
Download SKILL.mdSave it as
.claude/skills/omk-reviewing/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- omk-reviewing
- description
- Code and plan review with multi-angle dispatch. Trigger when user says 'review', 'code review', 'check my code', 'PR review', '@review', or when completing a plan phase that requires review. Also trigger before merge, after major feature completion, or when user asks for feedback on implementation quality.
Trigger Examples
- "@review 看看这个 PR"
- "帮我 review 一下这段代码"
- "check my implementation before I merge"
- "review the plan I just wrote"
- "这个改动有没有问题？"
Reviewing — Request, Execute, Receive
Requesting Review
When (mandatory): after completing major feature, before merge, after each task batch.
Plan Review — 4 angles, 4 parallel subagents
Pre-review Risk Identification
Before dispatching reviewers, the main agent MUST run the Pre-mortem Analysis defined in skills/planning/SKILL.md (Phase 1.5 → Pre-mortem Analysis section). This produces 3 risk questions (Integration / Assumption / Environment) that are injected as "Specific Questions" into each reviewer's dispatch query.
Additionally, craft one canary question per dispatch that requires reading a specific source file.
Dispatch
Dispatch exactly 4 reviewer subagents in parallel (agent_name: "reviewer", dangerously_trust_all_tools: true), one per angle:
| # | Angle | Mission |
|---|---|---|
| 1 | Goal Alignment | Every task maps to goal? Execution order valid? Non-goals respected? |
| 2 | Verify Correctness | Each verify command sound? False positives/negatives? |
| 3 | Completeness | All modified files covered? Edge cases? Conflicts with other plans? |
| 4 | Technical Feasibility | Blockers? Contradictions? Race conditions? Signal safety? |
Each subagent query must include: plan file path + relevant source file paths to read.
Deterministic Pre-check (main agent, before dispatching reviewers)
Before dispatching any reviewer subagent, the main agent runs deterministic checks (reviewer subagent only has read/write/shell — no LSP tools):
- Run
get_diagnosticson all modified files — collect compiler errors/warnings - Run
pattern_searchfor known anti-patterns (bare except, subprocess without timeout, etc.) - Package results as "Pre-check Findings" to include in each reviewer's dispatch query
Pre-check findings are automatically P0/P1 — they don't need LLM judgment. This reduces the reviewer's workload to reasoning-heavy issues only.
Code Review — size-based dispatch
Choose dispatch mode based on diff size:
Small PR (<200 lines diff): Dispatch 1 reviewer subagent (agent_name: "reviewer", dangerously_trust_all_tools: true) with:
- What was implemented
- Plan/requirements reference
- Git diff range (BASE_SHA..HEAD_SHA)
- Pre-check Findings from Deterministic Pre-check
Large PR (≥200 lines diff): Dispatch 2 reviewer subagents in parallel (agent_name: "reviewer", dangerously_trust_all_tools: true):
| Agent | Angle | Focus |
|---|---|---|
| 1 | Correctness + Security | Functional correctness, input validation, auth, injection, race conditions |
| 2 | Quality + Architecture | SOLID, code smells, performance, error handling, boundary conditions |
Each agent receives: diff range, pre-check findings, and relevant source file paths. Findings from both agents are merged and deduplicated by the main agent before presenting to user.
Iron Principle: Respect the Existing Codebase
The existing code is the stable, battle-tested baseline. It may be 85/100 — not perfect — but it works. Your job is to review the new code, not to fix the old code through the PR author.
- Only review new/changed lines. Do not raise findings against unchanged existing code, even if it has style issues, minor inefficiencies, or non-ideal patterns.
- Judge new code by the standards of the existing codebase, not by textbook perfection. If the existing code uses
@Autowiredfield injection, don't flag the new code for not using constructor injection. If the existing code swallows certain exceptions with a warn log, the new code doing the same is consistent, not a bug. - P2/P3 "style improvement" findings on existing patterns are noise. Only raise findings on existing code if it's P0/P1 (security vulnerability, data loss, crash) AND directly touched by the PR.
- "While we're here" refactors are out of scope. If the reviewer wants to suggest improving old code, it goes in a separate follow-up issue, not as a PR comment blocking merge.
Executing Code Review (for reviewer agent)
Show full SKILL.md (383 more words)Show less
1) Preflight context
- Run
git diff --statthengit diffto understand scope - If diff > 500 lines, batch by file/module — review each batch separately
- Note: file renames, new files, deleted files
2) SOLID + architecture check
- Load
references/solid-checklist.mdfor coverage - Check SRP, OCP, LSP, ISP, DIP violations
- Flag common code smells: long methods, feature envy, data clumps, dead code
- Apply refactor heuristics where applicable
3) Security scan
- Load
references/security-checklist.mdfor coverage - Check: input/output safety (XSS, injection, SSRF, path traversal), auth gaps, secrets in code
- Check: race conditions (concurrent access, check-then-act, TOCTOU, missing locks)
- Call out both exploitability and impact
4) Code quality scan
- Load
references/code-quality-checklist.mdfor coverage - Check: error handling (swallowed exceptions, overly broad catch, async errors)
- Check: performance (N+1 queries, CPU-intensive ops in hot paths, missing cache, unbounded memory)
- Check: boundary conditions (null/undefined, empty collections, numeric boundaries, off-by-one)
- Flag issues that may cause silent failures or production incidents
5) Removal candidates
- Load
references/removal-plan.mdfor template - Identify dead code, unused imports, deprecated patterns
- Categorize: safe to remove now vs defer with plan
6) Output
- Load
references/output-format.mdfor structure - Categorize findings: P0 Critical / P1 High / P2 Medium / P3 Low
- Be specific — cite file:line, show code examples
- Never rubber-stamp
7) Next steps confirmation
- Present findings summary with issue counts by priority
- Ask user how to proceed (fix all / P0-P1 only / specific items / no changes)
- Do NOT implement changes until user explicitly confirms
Receiving Review
Core principle: Verify before implementing. Technical correctness over social comfort.
- READ complete feedback without reacting
- UNDERSTAND — restate requirement (or ask)
- VERIFY against codebase reality
- EVALUATE — technically sound for THIS codebase?
- RESPOND — technical acknowledgment or reasoned pushback
- IMPLEMENT one item at a time, test each
YAGNI Check
Before implementing any suggestion, ask: "Does this solve a real problem we have now?" Reject speculative generality, premature abstractions, and features for hypothetical future needs.
Implementation Order
When implementing accepted feedback:
- Blocking issues first — anything that breaks build/tests
- Simple fixes — typos, naming, formatting (quick wins)
- Complex changes — refactors, architecture changes (highest risk, do last)
Push Back
Push back when reviewer is wrong — with technical reasoning and evidence. Show code, show tests, show docs.
Acknowledging Correct Feedback
When feedback is correct, acknowledge briefly and implement: "Agreed, fixing." No flattery.
Never: "You're absolutely right!" / "Great point!" / implement before verifying.
© KaimingWan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in skills/omk-reviewing of KaimingWan/oh-my-kiro.
- SKILL.md
- references/code-quality-checklist.md
- references/output-format.md
- references/removal-plan.md
- references/security-checklist.md
- references/solid-checklist.md
Open the folder on GitHubat commit ba228be
Compare with similar skills
Omk Reviewing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Omk Reviewing this skillKaimingWan/oh-my-kiro | 107 | — | ~1.9k | Automated safety check: Pass | MIT | |
| GitHub Review Iterationprisma/orm | 48k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Cherry Studio PR ReviewCherryHQ/cherry-studio | 53k | — | ~3.9k | Automated safety check: Pass | AGPL-3.0 | |
| PR Reviewjaemk/self_update | 961 | — | ~1.5k | Automated safety check: Notes | MIT | |
| PR Reviewjaemk/cached | 2.1k | — | ~2.5k | Automated safety check: Notes | MIT | |
| Pull Request Code Review Orchestratoropeninterpreter/openinterpreter | 69k | 2 repos | ~163 | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Cherry Studio PR Review
CherryHQ/cherry-studio
Reviews Cherry Studio branches, pull requests, commits, files and docs against the project's own architecture, naming, API-boundary and UI rules, report-only by default.
PR Review
jaemk/self_update
Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/self_update.
PR Review
jaemk/cached
Targeted, read-only review of a PR or checked-out branch. An agent skill from jaemk/cached.
Pull Request Code Review Orchestrator
openinterpreter/openinterpreter
Run a final code review on a pull request
Agentic Review
dxos/dxos
Run the rule-driven agentic code review — discover rule blocks in the repo's .mdl files, prepare per-rule review groups (full project by default; diff-only with --pr-only), spawn one focused Sonnet…
More from KaimingWan/oh-my-kiro
All 15 skills in this repoOmk Research
KaimingWan/oh-my-kiro
Multi-level research: built-in knowledge → web search → Tavily deep research API.
Omk Skill Creation
KaimingWan/oh-my-kiro
Create high-quality, production-ready skills from scratch. An agent skill from KaimingWan/oh-my-kiro.
Omk Youtube
KaimingWan/oh-my-kiro
Extract and summarize YouTube video content via subtitle extraction.
Documentation Lookup
KaimingWan/oh-my-kiro
Fetch current library/framework documentation via Context7. An agent skill from KaimingWan/oh-my-kiro.
Omk Coding
KaimingWan/oh-my-kiro
Enforces coding best practices: deep-read before modify, LSP-first navigation, TDD red-green-refactor, minimal changes, self-review, verification.
Omk Debugging
KaimingWan/oh-my-kiro
Systematic debugging: reproduce → hypothesize → verify → fix.
Related
Categories
Questions about Omk Reviewing
What does Omk Reviewing do?
Code and plan review with multi-angle dispatch. An agent skill from KaimingWan/oh-my-kiro. Omk Reviewing is an agent skill from KaimingWan/oh-my-kiro. Code and plan review with multi-angle dispatch.
When should I use Omk Reviewing?
Omk Reviewing fits situations like: user says review; completing a plan phase that requires review; after major feature completion; user asks for feedback on implementation quality.
How do I install Omk Reviewing in Claude Code?
Run `npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a claude-code`. Or copy the skill folder (skills/omk-reviewing in KaimingWan/oh-my-kiro) into .claude/skills/omk-reviewing in your project. Claude Code loads it when a task matches its description.
How do I install Omk Reviewing in Codex?
Run `npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a codex`. Or copy the skill folder (skills/omk-reviewing in KaimingWan/oh-my-kiro) into .agents/skills/omk-reviewing in your project. Codex loads it when a task matches its description.
Can I use Omk Reviewing in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add KaimingWan/oh-my-kiro --skill omk-reviewing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omk-reviewing, .gemini/skills/omk-reviewing, .github/skills/omk-reviewing and .opencode/skills/omk-reviewing in your project.
What does Omk Reviewing need to run?
Going by SKILL.md and its folder, Omk Reviewing needs the command-line tools its instructions call (git).
Does Omk Reviewing access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Omk Reviewing safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Omk Reviewing use?
Omk Reviewing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Omk Reviewing use?
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.
What are the alternatives to Omk Reviewing?
Skills that share tags, products or a category with Omk Reviewing: GitHub Review Iteration (prisma/orm, 48k stars), Cherry Studio PR Review (CherryHQ/cherry-studio, 53k stars), PR Review (jaemk/self_update, 961 stars) and PR Review (jaemk/cached, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Omk Reviewing?
KaimingWan (a GitHub user) maintains it in KaimingWan/oh-my-kiro, which has 107 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on April 2, 2026.
Source: KaimingWan/oh-my-kiro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.