Loading...
Loading...
Found 3,895 Skills
Commit and push ALL changes (staged + unstaged + untracked) to the remote repository
Optimize command outputs with RTK (Rust Token Killer) for 70% token reduction
Sync ag-shared subrepo changes across ag-charts, ag-grid, and ag-studio repos
合并 - Complete PR lifecycle: worktree → implement → commits → PR → verify → merge. 触发条件/Triggers: 需要实现功能并提交 PR、修复 Issue、或完成代码审查后的合并工作。 工作流/Workflow: - 阶段 0/Phase 0: 创建工作树/Create worktree - 阶段 1/Phase 1: 实现功能/Implement feature - 阶段 2/Phase 2: 创建 PR/Create PR - 阶段 3/Phase 3: 验证循环/Verification loop (CI + Review + Approval) - 阶段 4/Phase 4: 合并清理/Merge & cleanup 命令/Commands: - /合并 <任务> - 启动完整 PR 工作流 - /合并 create <任务> - 创建 PR - /合并 check - 检查验证状态 - /合并 status - 查看 PR 状态 - /pr <task> - English command 能力/Capabilities: 工作树管理、功能实现、原子提交、PR 创建、验证循环、合并清理。
Create a high-quality pull request: branch, focused changes, lint/build, conventional commit, and a clear PR description with validation steps. Use when the user asks to open or prepare a PR.
Review recent repository changes and decide whether AGENTS.md or other project-level documentation needs a high-level update. Use when finishing a feature, fix, refactor, or architectural change and you need to preserve repo-shaping guidance such as new patterns, constraints, workflows, validation rules, or onboarding-relevant gotchas without adding low-level implementation detail.
Prepare a structured, scannable review checklist for a branch or diff, grouped by feature change and applying the four-pass review order (Types, Data Flow, Business Logic, Edge Cases) within each feature. Use when the user asks to "prep a review", "review order", or wants a checklist to manually walk through changes.
Self-directed iterative improvement system for Codex that cycles through modify, verify, retain/discard indefinitely
Review local code changes organized into logical chapters with Stage CLI, a code review tool that works with any AI agent
Analyze Chromium-based browser artifacts using Hindsight to extract browsing history, downloads, cookies, cached content, autofill data, saved passwords, and browser extensions from Chrome, Edge, Brave, and Opera for forensic investigation.
Use when an issue needs deeper analysis than triage — confirming root cause by reading code, verifying file/line references in body are still valid, checking blast radius across the codebase, or proposing a concrete fix direction. One issue per invocation.
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