আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Write production-ready Go backends, CLIs, and APIs following modern best practices from top tier tech companies. Use this skill when creating or reviewing Go code for (1) backend services and APIs, (2) command-line tools, (3) code requiring proper error handling, concurrency, or testing patterns, (4) any Go development requiring adherence to established style guidelines. Includes comprehensive linting configuration and detailed style guide.
Follow trunk-based development practices with short-lived branches, frequent integration to main, feature flags, and continuous integration. Use when managing git workflow and releases.
Remove AI-generated code slop from current branch. Identifies and removes inconsistent comments, over-defensive code patterns, and style mismatches introduced by AI. Use when: cleaning up AI-generated code, before committing AI changes, after code generation session.
Create well-structured git commits. Use when committing code changes.
Create or update root and nested AGENTS.md files that document scoped conventions, monorepo module maps, cross-domain workflows, and (optionally) per-module feature maps (feature -> paths, entrypoints, tests, docs). Use when the user asks for AGENTS.md, nested agent instructions, or a module/feature map.
Use when working with stacked branches, managing dependent PRs/CRs, or uncertain about git-spice commands (stack vs upstack vs downstack) - provides command reference, workflow patterns, and common pitfalls for the git-spice CLI tool.
Systematic code review workflow to evaluate changes against Java and Spring standards. Use when reviewing Pull Requests, commits, or diffs. Ensures robustness, maintainability, and adherence to best practices.
This skill teaches how to access GitHub's REST and GraphQL APIs via gh api for inline PR comments, review threads, and data not available through standard gh commands. Use this when you need PR review comments, thread status, or other GitHub data that gh pr view doesn't provide.
Generates properly formatted commit messages following project conventions. Use when creating commits or when users need help writing commit messages. Inspects staged changes and creates messages with component tags, concise summaries, and detailed descriptions.
Extract and review GitHub Pull Requests with comprehensive analysis
Create pull request from current branch with AI-generated title and description. Use when user wants to create a PR for their current branch. Triggers include: - Korean: "PR 만들어줘", "PR 생성해줘", "풀 리퀘스트 만들어줘" - English: "create PR", "open PR", "make pull request" - Context: User has commits on current branch and wants to open PR
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Destructive Command Guard (DCG) safety hook for all AI coding agents. Rust-based PreToolUse hook that blocks dangerous git and filesystem commands. Use when agent attempts destructive operations, safety verification is needed, or when checking protection status across VMs. Keywords: safety, git reset, rm -rf, destructive, guard, hooks, protection
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
This skill should be used when performing exhaustive code reviews using multi-agent analysis, ultra-thinking, and Git worktrees for deep local inspection. It applies to PR reviews, branch comparisons, and comprehensive code quality assessments.
Complete development branches with structured options for merge, PR, keep, or discard. WHEN: MUST use when implementation complete and tests pass. Invoke with "/finishing-a-development-branch" or "finish this branch", "ready to merge", "what to do with this branch". WHEN NOT: Tests still failing, implementation incomplete, still debugging.
