deep-review
A code-review skill kept in the LobeHub repository for independent review of a pull request, diff or branch by reviewers other than the agent that wrote the code.
What the skill teaches
A code-review skill kept in the LobeHub repository for independent review of a pull request, diff or branch by reviewers other than the agent that wrote the code. By default it runs a light review: one independent reviewer with a quick checklist and at most one round of follow-up checks. A deep review, run only on explicit request, sends parallel reviewers across up to fourteen areas such as logic, security, performance, user experience and release risk, verifies their candidate findings, removes duplicates and writes a structured report. The agent should suggest deep review for changes to billing, authentication, database schemas or shared contracts, or very large diffs, and findings are judged against the codebase's existing standards.
Capabilities
- Run a light independent review of a diff
- Run a multi-reviewer deep review on request
- Verify and deduplicate review findings
About
- Publisher
- LobeHub
- Tool
- Code review
Install
The project doesn't document install steps that we could confirm. See the project's own instructions
What's inside
- 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
- references/dimensions/workflow.md
- references/light-review-prompt.md
- references/release-risk/persisted-state.md
- references/release-risk/prompt-surface.md
- references/release-risk/rollout-surface.md
- references/report-template.md
- references/review-prompt.md
- references/scoping.md
- references/verification/release-risk.md
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
This skill includes scripts that your agent may run.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Code review | |
| Publisher | LobeHub | source |
| Official status | Not stated in its documentation | |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | Not stated in its documentation | |
| Licence | NOASSERTION | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 11, 202684,974 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository Website |
More from LobeHub
33 skills
- pr (Skill)
- acceptance (Skill)
- add-model-provider (Skill)
- add-setting-env (Skill)
- agent-signal (Skill)
- agent-testing-bot (Skill)
Also listed under: Code review
Sources
- Skill file (SKILL.md)github.com/lobehub/lobehubNov 15, 2026
- GitHub repositorygithub.com/lobehub/lobehub · Backs: Publisher, ActivityNov 11, 2026
- Skill file (SKILL.md)github.com/lobehub/lobehub · Backs: LicenceNov 10, 2026
- Folder in the repository (deep-review)github.com/lobehub/lobehub · Backs: Includes scriptsNov 10, 2026