
Review PR
SkillReviews a branch's changes against its base as a pull request for defects and gaps
- Open source
- 8.2K GitHub stars
- Developer tools

Reviews a branch's changes against its base as a pull request for defects and gaps

Runs a code review by dispatching naming and leftover-marker auditor agents and merging

Generates a sandboxed devcontainer with Claude Code and language tooling for a project

Guides an agent through a security-focused review of PR, commit or diff changes

Guides an agent through inspecting, verifying and parsing DWARF debug info in binaries

Steers the agent to use authenticated gh CLI commands instead of raw GitHub fetches

Triage a repo's open issues and PRs with gh, gated by your approval

Drafts copy-paste-ready /goal completion conditions for long-running agent tasks

Guides C++ code toward C++20/23/26 idioms that reduce memory and type-safety bugs

Sets up Python projects and scripts with uv, ruff, ty and modern tooling

Guides an agent through preparing a repository for a safe public release

Guides an agent to fix a confirmed bug at the invariant level with tests and one commit

Guides an agent to fix one known local bug with a patch commit and proof report

Independently reproduces a named runtime or compiler bug in a local repository

Validates security patches with baseline-versus-patched evidence and adversarial checks

Finds candidate regressions in a pinned code change by tracing its callers

Pins before and after source states and gathers PR or commit context for regressions

Coordinates multi-agent hunts for regressions in PRs and commits with staged verification

Assembles an evidence-linked regression report from saved campaign decisions

Builds an interactive HTML walkthrough of branch changes with review findings

Runs independent code reviews of changes through Codex or Antigravity CLIs

Guides the agent to write and test custom Semgrep rules for security and code patterns

Ports an existing Semgrep rule to other languages with tests for each variant

Teaches your agent to read, filter, deduplicate and convert SARIF scan results

Sets up and runs cargo-fuzz harnesses to fuzz Rust crates and triage crashes

Measures which code a fuzzing campaign reaches and turns gaps into harness or seed work

Guides an agent through building, running and triaging libFuzzer harnesses for C/C++ code

Overlays SARIF, weAudit and binary graph findings onto Trailmark code graphs

Generates Mermaid diagrams of call graphs, class hierarchies and attack surface flows

Triages mutation testing and necessist results into false positives, test gaps and fuzz