Loading...
Loading...
Found 3,994 Skills
Implement a feature from issue, specs, and docs, then propose a PR
Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)
Edit prose to sound more natural, direct, and engaging. Works top-down through four levels (Document → Paragraph → Sentence → Word) with human checkpoints at each stage. Fixes LLM patterns, writerly bad habits, and style deficits. Works for academic papers, reports, memos, essays, blog posts, proposals, and other nonfiction. Use when prose sounds robotic, dull, or inaccessible.
Orchestration mode for implementation tasks. Manages the plan → code → review loop. Use /orchestrate <requirements> or let /implement invoke it.
Use when you need to request a code review for a PR/MR and want a consistent review brief (context, scope, risk areas, test instructions, acceptance criteria) before merge.
Commit recent changes that haven't yet been commited.
Orchestrates the release process - Testing, Documentation, and Tagging. Use when preparing a new version release.
This skill should be used when the user asks to "wrap up session", "end session", "session wrap", "/wrap", "document learnings", "what should I commit", or wants to analyze completed work before ending a coding session.
分析代码审查反馈或开发中发现的问题，提取通用规则并更新 CLAUDE.md 和详细规则文档。当用户说"更新规则"、"添加编码规则"、"update claude md"或发现需要记录的编码模式时使用。
Create or update .groove/index.md config interactively. Run before groove install.
Resolve human PR review comments on current PR. Fetches unanswered human comments, evaluates each piece of feedback, applies fixes, and replies to every comment with the outcome.
Review the current Pull Request that has been checked out locally with structured feedback on code quality, issues, testing, and suggestions. Use when you need a comprehensive code review of a PR branch.