স্কিল খুঁজুন
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
review-git-changes
Analyzes and refactors code changes in the current git working tree (staged, unstaged, or recent commits). Ensures changes follow best practices, coding standards, and maintain code quality. Use when the user asks to "review my git changes", "check what I changed", "refactor my changes", "ensure my changes are clean", or "review before commit".
git-commit-helper
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.
repo-indexer
Build and maintain a fast navigation index of the repo.
git-gh-sandbox
Use when executing git or gh commands that require network access. Explains sandbox restrictions for git push, pull, fetch, clone, and all gh commands.
github-api
Access plain text versions of GitHub content (diffs, patches, raw files) using GitHub's URL transformations. Use when users share GitHub URLs for PRs, commits, files, or gists and you need to analyze the actual content. Works for pull requests, commits, file blobs, comparisons, and gists.
flutter-reviewer
Use this agent when you need to review code changes in a pull request or after writing/modifying code. The agent performs comprehensive code review following established team standards, categorizing findings as Critical Issues, Suggestions, or Praise. It's particularly suited for reviewing backend (Golang/Protobuf/Postgres) and frontend (Flutter/Riverpod/GetX) code. Examples: <example> Context: After implementing a new API endpoint user: "I've added a new user profile update endpoint" assistant: "I'll review the code changes for the new endpoint" <commentary> Since new code was written, use the flutter-reviewer agent to ensure it meets quality standards. </commentary> assistant: "Let me use the flutter-reviewer agent to review this implementation" </example> <example> Context: After modifying database schema user: "I've updated the schema to add a new column to the users table" assistant: "I'll review these database changes" <commentary> Database schema changes require careful review for backward compatibil
create-project-docs
Creates comprehensive GitHub project documentation including README, CONTRIBUTING, CODE_OF_CONDUCT, CHANGELOG, architecture docs, and API documentation. Analyzes codebase to generate accurate, well-styled documentation with modern GitHub aesthetics. Use when setting up a new project, improving existing documentation, or generating missing docs.
code-review
Review code changes for quality, security, performance, and maintainability. Use when reviewing PRs, diffs, or code files. Provides structured feedback with severity levels.
code-review
Comprehensive code review with best practices, security, and maintainability checks. Use when reviewing pull requests, pre-commit code checks, learning code review techniques, improving code quality, or performing security audits. Triggers include "code review", "review code", "PR review", "pull request review", "security review", "code quality", or when evaluating code for issues and improvements.
codex-review
Delegates code review to OpenAI Codex CLI. Use when user says "코드 리뷰해줘", "Codex한테 리뷰 맡겨", "PR 검토해줘", "코드 품질 체크", "리팩토링 제안해줘", "second opinion", or asks for code review, refactoring suggestions.
commit-writer
Expert at crafting clear, meaningful git commit messages following conventional commit standards and repository conventions. Use when user asks to create commit messages, write commits, or needs help with git commit text. Analyzes git diffs and repository history to generate contextual, well-structured commit messages.
code-reviewer
Use this skill after code changes are made, when reviewing implementations, checking code quality, or ensuring constitutional compliance. Apply when user mentions reviewing, analyzing, or checking code quality. Also use proactively after significant code implementations to verify they follow mini_agent framework principles.
self-reviewing-code
Self-review checklist before marking PR ready - catch clarity, correctness, and maintainability issues with fresh eyes
pr-code-review-fixer
Systematically fetch, analyze, and fix code review issues from GitHub Pull Requests. Use when the user asks to review and fix code issues from AI code reviewers (like Gemini Code Assist, GitHub Copilot, CodeRabbit) or any PR review comments. Fetches all review comments using gh CLI, attempts to fix all reported issues, commits changes to the PR branch, and generates a comprehensive fix report. Triggers on requests like "fix PR review issues", "address code review feedback", "apply review suggestions", or when given a GitHub PR URL with review comments to address.
create-worktree
Create git worktrees for new features or bug fixes. Use when the user wants to start a new feature, fix a bug in a separate worktree, create a worktree, or work on something in isolation.
multi-model-review
マルチモデルコードレビュー。LLMがコードレビューを行った後、GitHub Copilot CLIに精査させて双方の視点を統合した最終レビューを提供。Use when user wants multi-model code review, second opinion, or wants to cross-check review findings with another AI. Triggers: "/multi-model-review", "マルチモデルレビュー", "複数モデルでレビュー", "セカンドオピニオン"
verify-skill
Use before claiming work is complete - runs tests, checks git status, verifies changelog
