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.
Runs an independent, multi-dimension review of a PR, diff or branch with separate reviewers and adversarial verification, in a light or a deep multi-agent mode.
Install Deep Code Review
$ npx skills add lobehub/lobehub --skill deep-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lobehub/lobehub deep-review --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/lobehub/lobehub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deep-review .claude/skills/deep-review && 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 "deep-review" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/deep-review into .claude/skills/deep-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-review", 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/lobehub/lobehub/tree/canary/.agents/skills/deep-reviewType 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 lobehub/lobehub --skill deep-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lobehub/lobehub deep-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/deep-review .agents/skills/deep-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "deep-review" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/deep-review into .agents/skills/deep-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-review", 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 lobehub/lobehub --skill deep-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lobehub/lobehub deep-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/deep-review .cursor/skills/deep-review && 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 "deep-review" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/deep-review into .cursor/skills/deep-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-review", 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/lobehub/lobehub.git --path .agents/skills/deep-review--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 lobehub/lobehub --skill deep-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lobehub/lobehub deep-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/deep-review .gemini/skills/deep-review && 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 "deep-review" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/deep-review into .gemini/skills/deep-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-review", 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 lobehub/lobehub deep-reviewInstalls 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 lobehub/lobehub --skill deep-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/deep-review .github/skills/deep-review && 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 "deep-review" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/deep-review into .github/skills/deep-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-review", 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 lobehub/lobehub --skill deep-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lobehub/lobehub deep-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/deep-review .opencode/skills/deep-review && 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 "deep-review" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/deep-review into .opencode/skills/deep-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deep-review", 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
deep-review- GitHub stars
- 83k
- Token cost
- ~5.3k tokens
- SKILL.md length
- 1,836 words
- Files
- 34 (incl. scripts, references)
- Skills in repo
- 50
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Runs an independent, multi-dimension review of a PR, diff or branch with separate reviewers and adversarial verification, in a light or a deep multi-agent mode.
- Works in 5 steps: Anti-hallucination — reviewers need… → Anti self-approval — an agent that just… → Rules over model — review quality comes… → …
- Getting an independent review of a pull request, diff or branch
- SKILL.md covers Core principles, Two entry modes, Dimensions and Extension packs, plus 3 more sections
- Reviewing a change that touches security, performance or release risk
What it does
The skill builds a code review from independent reviewers rather than a single pass by the agent that wrote the code. Breadth comes from running dimension reviewers in parallel, with reference files for dimensions such as business logic, security, performance, observability, compatibility, code style, reuse and architecture, release risk, UX, new features and skill freshness. Precision comes from verification: in deep mode independent agents mark each candidate finding as confirmed, false positive or need more context, and duplicates are consolidated globally before the report.
Its principles are anti-hallucination, by giving reviewers surrounding context and not only diff fragments; anti self-approval, by always using a reviewer other than the main agent; rules over model; calibrating to the codebase's existing standard and the code's declared lifespan, with security exempt; and speed, through one parallel wave. There are two entry modes, light and deep, and the full multi-agent review runs only when explicitly requested. Separate reference folders cover Claude Code and Codex environments.
When your agent uses it
- Getting an independent review of a pull request, diff or branch
- Reviewing a change that touches security, performance or release risk
- Filtering out false positives before posting review findings
Example prompts
- “Run a deep review of this branch against main.”
- “Do a light independent review of the current diff and list only confirmed findings.”
- “Review the open pull request across security and compatibility and consolidate duplicate findings.”
Requirements
- An agent environment that can run independent subagents for deep mode
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Anti-hallucination — reviewers need surrounding context, not only diff fragments. Deep mode verifies candidate findings through…
- Anti self-approval — an agent that just wrote the code is grading its own homework and will pass it. Both modes use an independent…
- Rules over model — review quality comes from fine-grained, executable dimension rules, not from a smarter model. Subagents run on…
- Calibrate to codebase and lifespan — hold the diff to the standard the codebase already meets, not an idealized one. If a pattern is…
- Speed is a feature — one wave of parallel reviewers, verification pipelined per dimension (never a global barrier), irrelevant dimensions…
What it can do on your machine
Read from SKILL.md and the folder at commit 35d442e. 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
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Deep Code Review loads about 5.3k tokens when it runs, and up to ~39k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 1,836 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); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,836 words (~5,324 tokens).
“Multi-dimensional code review built on independent reviewers. Review breadth comes from parallel dimension coverage; precision comes from adversarial verification and global duplicate consolidation before findings reach the report.”
- name
- deep-review
Files
SKILL.md and 33 other files (scripts, references) in .agents/skills/deep-review of lobehub/lobehub.
- SKILL.md
- references/claude-code/main.md
- references/codex/main.md
- references/consolidate-prompt.md
- references/dimensions/ai-coding-bad-habits.md
- references/dimensions/business-logic.md
- references/dimensions/code-style.md
- references/dimensions/compatibility.md
- references/dimensions/logic.md
- references/dimensions/new-feature.md
- references/dimensions/observability.md
- references/dimensions/performance.md
- references/dimensions/release-risk.md
- references/dimensions/reuse-architecture.md
- references/dimensions/security.md
- references/dimensions/skill-freshness.md
- references/dimensions/ux.md
- … and 17 more
Open the folder on GitHubat commit 35d442e
Compare with similar skills
Deep Code Review 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 |
|---|---|---|---|---|---|---|
| Deep Code Review this skilllobehub/lobehub | 83k | — | ~5.3k | Automated safety check: Pass | Custom licence | |
| GitHub Review Iterationprisma/orm | 48k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Cherry Studio PR ReviewCherryHQ/cherry-studio | 52k | — | ~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 lobehub/lobehub
All 50 skills in this repoLobeHub Interactive Prototype
lobehub/lobehub
Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.
Acceptance Evidence for Deliveries
lobehub/lobehub
Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
LobeHub Alint Rule Set Maintenance
lobehub/lobehub
Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.
LobeHub Builtin Tool Authoring
lobehub/lobehub
Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.
LobeHub Data Fetching Layers
lobehub/lobehub
Explains how LobeHub client code fetches data through services, SWR store hooks and cache keys, and when to avoid useEffect fetching or duplicated state.
Related
Categories
Questions about Deep Code Review
What does Deep Code Review do?
Runs an independent, multi-dimension review of a PR, diff or branch with separate reviewers and adversarial verification, in a light or a deep multi-agent mode. The skill builds a code review from independent reviewers rather than a single pass by the agent that wrote the code. Breadth comes from running dimension reviewers in parallel, with reference files for dimensions such as business logic, security, performance, observability, compatibility, code style, reuse and architecture, release risk, UX, new features and skill freshness.
When should I use Deep Code Review?
Deep Code Review fits situations like: getting an independent review of a pull request, diff or branch; reviewing a change that touches security, performance or release risk; filtering out false positives before posting review findings.
How do I install Deep Code Review in Claude Code?
Run `npx skills add lobehub/lobehub --skill deep-review -a claude-code`. Or copy the skill folder (.agents/skills/deep-review in lobehub/lobehub) into .claude/skills/deep-review in your project. Claude Code loads it when a task matches its description.
How do I install Deep Code Review in Codex?
Run `npx skills add lobehub/lobehub --skill deep-review -a codex`. Or copy the skill folder (.agents/skills/deep-review in lobehub/lobehub) into .agents/skills/deep-review in your project. Codex loads it when a task matches its description.
Can I use Deep Code Review 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 lobehub/lobehub --skill deep-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-review, .gemini/skills/deep-review, .github/skills/deep-review and .opencode/skills/deep-review in your project.
What does Deep Code Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Deep Code Review is instructions for the agent only. Our summary lists: An agent environment that can run independent subagents for deep mode.
Does Deep Code Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Deep Code Review 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Deep Code Review use?
Deep Code Review has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Deep Code Review use?
About 5.3k tokens (SKILL.md is roughly 21k 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 34k tokens, read only when the agent opens those files.
What are the alternatives to Deep Code Review?
Skills that share tags, products or a category with Deep Code Review: GitHub Review Iteration (prisma/orm, 48k stars), Cherry Studio PR Review (CherryHQ/cherry-studio, 52k 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 Deep Code Review?
lobehub (a GitHub organization) maintains it in lobehub/lobehub, which has 83,074 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 9, 2026.
Source: lobehub/lobehub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.