Loading...
Loading...
Found 10,550 Skills
Use when starting any conversation, receiving a new task, or when uncertain which skill applies - establishes how to find and use all 64 toolkit skills, requiring Skill tool invocation before ANY response including clarifying questions
WeChat automation operations. Implement functions including sending messages, fetching chat records, listening to messages, and friend management via the wxautox4 RESTful API. Use when: (1) Send WeChat messages to friends or group chats, (2) Read WeChat chat records, (3) Listen to new messages, (4) Fetch friend list or group chat list, (5) Accept friend requests, (6) Switch chat windows and other WeChat operations.
This skill should be used when the user asks to "improve my setup", "learn from this session", "fix my config", "stop asking for permissions", or reports friction with skills, agents, hooks, or permissions. Analyzes conversation history and proposes configuration improvements.
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure
Split uncommitted changes into focused, logical commits using git-hunk. Use when asked to "split changes", "split commits", "organize commits", "commit by hunk", or "separate changes into commits".
Run an interactive naming session for a project. Use when the user wants to name a project, app, package, tool, or repo. Presents names in rounds, tracks preferences, and refines suggestions based on selections.
Use when iterative review-fix cycles are needed on a plan or implementation — bounded loop with severity gating, automatic fixes, and finding disposition.
Finish a code review session by fetching comments from the running diffx server, applying requested changes, and marking comments as resolved. Use when the user invokes /diffx-finish-review.
Triggers only when the user wants to do spec coding.
Switch model profile for GSD agents (quality balanced budget)
Orchestrates multi-day execution of complex tasks through milestones. Each milestone goes through plan-crafting, run-plan (worker-validator), and review-work phases with checkpoint/recovery. Triggers when the user says "long run", "start long run", "execute milestones", or "run all milestones".
Use before any implementation start — auto-detects and fixes git state issues (branch, dirty files, remote sync) with one confirmation per fix. Trigger on "start implementation", "implement this plan", "start coding", "execute plan", "開始實作", "執行計劃", or any signal that coding is about to begin.