Agent skill · software engineering · pedronauck
deep-review
Review branch diffs, working trees, or PRs in depth with defect, polish and cross-contract coverage. Includes incremental and spec-conformance reviews; excludes fixes, spec-document reviews and quick single-file feedback.
Why this skill is useful
Adds a comprehensive set of executable scripts for deep review processes that automate complex code review workflows and artifact management.
What it needs
Requires gh installed locally. About 4k tokens when loaded. Last updated 2026-08-01. 564 stars on the source repository.
What this skill does
Deep Review Find actionable defects and improvements with complete selected-hunk and project-rule accounting. Scripts handle discovery, partitions, artifact assembly and validation; the model supplies applicability decisions and evidence-based review. Keep source read-only; write review artifacts under <out> (default .deep-review/<target>/). Resolve <skill-dir> from this file and run bundled commands from the reviewed repository root. Contract No total file or line cap on the PR. Every selected hunk has exactly one defect owner and one polish owner. Both default to broad cohorts of 200 files / 15,000 changed lines per job, adjustable with --max-cohort-files, --max-cohort-lines, --max-polish-files and --max-polish-lines. Oversized files are sliced without losing hunks. An optional --max-context-lines N preparation budget accounts for whole-file reading while preserving selection. Every defect has causal evidence; every advisory has an observed premise, concrete improvement and bounded fix. Investigated rejections stay in the suppression ledger. No quota; advisories never block SHIP. Every applied rule comes from material actually read, with verbatim text, source, scope and explicit assessment. Root/nested instructions retain scope and precedence. Metadata is a triage queue, not an instruction to load every skill. Relevant linters run first or reuse evidence for the same frozen inputs. Record unavailable lanes; suppress overlapping findings. Never install tools to fill a lane. The checkout, rule evidence and job contracts are pinned. Valid outputs are reused only for their unchanged contracts. Missing coverage, stale evidence and malformed results prevent completion. Publish only with --publish or explicit session authorization. Product fixes are outside this skill. 1. Prepare The helper creates the manifest, knowledge.md and decisions.template.json. Inspect the manifest summary for correct base/head and file selection, especially after a rebase. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills pedronauck/deep-review