Loading...
Loading...
Found 66 Skills
Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing, and architecture. Triggers on "review code", "code review", "审查代码", "代码审查".
PR review with parallel specialized agents. Use when reviewing pull requests or code.
Perform general code reviews for PRs and code changes. Evaluate code quality, security, and design based on common standards to make approve/reject decisions. Use this for requests like "Review this PR", "Do a code review", "Pre-merge check", or when executing the gh pr view command.
Grill the diff. Specialists evaluate every finding internally — only high-value findings reach the user for discussion until reaching shared understanding.
Follow this sub-process when fixing bugs—turn the verbal description of "discovered a problem" into a closed loop of verification and repair, leaving three documents in the middle: issue report, root cause analysis, and repair record. This process adds a buffer between "seeing the problem" and "starting to modify code", avoiding several common pitfalls: the problem description in your mind disappears after modification, fixing only the surface without analyzing the root cause, uncontrollable expansion of repair scope that cannot be traced, and not knowing if the fix is correct without verification after modification. This skill only acts as a router, deciding which of report / analyze / fix to proceed with based on existing outputs. For simple problems that can be identified at a glance, a fast track will be taken, skipping the two middle steps and only keeping the fix-note.
Watch for the 11 known AI-coding-agent failure modes (fabrication, scope_creep, security_vulnerability, etc.) — consult this skill before edits, dependency adds, completion claims, or anything that could trip a known supervision concern. Quote the snake_case failure-mode ids verbatim when flagging risks.
Comprehensive pre-merge validation checklist for Python/React pull requests. Use before approving or merging any PR. Covers code quality checks (linting, formatting, type checking), test coverage requirements, documentation updates, migration safety, API contract compatibility, accessibility compliance, bundle size impact, and deployment readiness. Provides a systematic checklist that ensures nothing is missed before merge. Does NOT cover security review depth (use code-review-security).
Automated code review with security, performance, and best practices analysis. Use when reviewing pull requests or analyzing code for vulnerabilities, performance issues, or maintainability concerns.
Meta-skill for validating the integrity and quality of other skills. automatically checks for SKILL.md existence, script syntax errors (via Godot CLI), and metadata completeness. Use this skill to verify the entire skill library. Trigger keywords: validation, continuous_integration, quality_assurance, syntax_check, metadata_check.
Deep Python code review of changed files using git diff analysis. Focuses on production quality, security vulnerabilities, performance bottlenecks, architectural issues, and subtle bugs in code changes. Analyzes correctness, efficiency, scalability, and production readiness of modifications. Use for pull request reviews, commit reviews, security audits of changes, and pre-deployment validation. Supports Django, Flask, FastAPI, pandas, and ML frameworks.
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.
Open source contribution best practices. Creating quality pull requests, writing good issues, following project conventions, and collaborating effectively with maintainers.