Agent skill · software engineering · lobehub
deep-review
Use for independent PR, diff or branch review; not explanations. Full multi-agent review requires an explicit deep-review request.
Why this skill is useful
Adds executable workflows for multi-dimensional code review with independent verification and structured reporting that the AI cannot generate on its own.
What it needs
Requires git installed locally. About 8k tokens when loaded. Last updated 2026-08-07. 81,352 stars on the source repository.
What this skill does
Deep Review 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. Core principles Every design choice below serves one of these. When unsure how to execute a step, come back here. 1. Anti-hallucination — reviewers need surrounding context, not only diff fragments. Deep mode verifies candidate findings through independent agents returning confirmed / falsepositive / needmorecontext. Light mode uses the bounded follow-up procedure below; it does not add a separate per-finding verification pipeline. 2. Anti self-approval — an agent that just wrote the code is grading its own homework and will pass it. Both modes use an independent reviewer with a third-party stance. Light: one reviewer that is not the main agent. Deep: independent subagents per the environment manual. Never silently degrade either mode to "the main agent reviews the diff itself". 3. Rules over model — review quality comes from fine-grained, executable dimension rules, not from a smarter model. Subagents run on balanced/fast model tiers; each dimension file tells them exactly how to check, what counts, and what does not. 4. Calibrate to codebase and lifespan — hold the diff to the standard the codebase already meets, not an idealized one. If a pattern is widespread in the existing code and this diff does not make it worse, it is not a finding. Declared-temporary code (time-boxed campaign, experiment, one-off script) is judged against its lifespan: hardcoding and low-extensibility shortcuts are the intended trade-off for shipping fast, and "delete the code at expiry" is a valid plan — do not demand configurability from code built to be deleted. (Security is exempt from all calibration — see the dimension file.) 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills lobehub/deep-review