Loading...
Loading...
Found 94 Skills
Analyzes git diff and commit history to write PR title and description based on the project's PR template.
Use when the user asks to perform a code review, review code changes, analyze a diff, or audit code quality. Runs a structured review of git diff output covering security, correctness, performance, maintainability, and style. Produces a markdown report saved as a .md file named after the current branch.
Force a skeptical second pass on your own work. Because 'it should work' has never once been true.
Adopt the Three Provinces and Six Ministries style code review, output structured review conclusions in five stages: Zhongshu Sheng, Shangshu Sheng, Six Ministries, Menxia Sheng, and Jinyiwei
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
Simplify and refine code for clarity, consistency, and maintainability
Remove AI-style code slop from a branch by reviewing diffs, deleting inconsistent defensive noise, and preserving behavior and local style.
Split a large PR diff into reviewable sub-patches for easier code review.
Technical solution evaluation and code review in the style of Linus Torvalds. Only use this when the user explicitly requests a Linus-style review or explicitly asks for a rigorous evaluation of code changes/technical solutions (e.g., "review changes/code", "evaluate if the solution is appropriate", "check submission standards", "linus-tech-review").
Validates code changes against DeepRead's mandatory patterns and standards defined in AGENTS.md. Use this after writing or modifying code to catch violations before committing.
Design and generate property-based tests (PBT) for changed files in the current git branch. Extracts specifications, designs properties (invariants, round-trip, idempotence, metamorphic, monotonicity, reference model), builds generator strategies, implements tests, and self-scores against a rubric (24/30+ required). Supports fast-check (TS/JS), hypothesis (Python), and proptest (Rust). Use when: (1) "write property tests for my changes", (2) "add PBT", (3) "property-based test", (4) after implementing pure functions, validators, parsers, or formatters to verify invariants.
프로젝트 컨텍스트를 파악한 뒤 전문가 관점으로 코드 리뷰하고, 사용자 승인 후 Agent Team SPAWN으로 병렬 개선 작업을 수행합니다. 트리거: 코드리뷰, 코드 리뷰, code review, 리뷰해줘, 리팩토링, 코드검토, PR 리뷰, 변경사항 검토.