kun-agent-system/skill-toolkit-public
Public standalone Skill lifecycle toolkit for creating, adopting, overlaying, repairing, and evolving Agent Skills across Codex and Claude Code.
Public standalone Skill lifecycle toolkit for creating, adopting, overlaying, repairing, and evolving Agent Skills across Codex and Claude Code.
npx skills add kun-agent-system/skill-toolkit-publicPublic standalone Skill lifecycle toolkit for creating, adopting, overlaying, repairing, and evolving Agent Skills across Codex and Claude Code.
Use this skill when working with coordinates, vectors, matrices, shapes, hit testing, or layout rectangles in PixiJS v8. Covers Point/ObservablePoint, Matrix (2D affine, decompose, apply, applyInverse), shapes (Rectangle, Circle, Ellipse, Polygon, RoundedRectangle, Triangle), Rectangle layout helpers (pad, fit, enlarge, ceil, scale, getBounds), strokeContains hit tests, Polygon isClockwise/containsPolygon, toGlobal/toLocal, PointData/PointLike/Size types, DEG_TO_RAD, and pixi.js/math-extras vector and intersection helpers. Triggers on: Point, ObservablePoint, Matrix, Rectangle, Circle, Polygon, Triangle, RoundedRectangle, toGlobal, toLocal, hitArea, strokeContains, pad, fit, enlarge, ceil, getBounds, containsRect, intersects, isClockwise, math-extras, lineIntersection, segmentIntersection, DEG_TO_RAD, PointData.
Track OpenClaw session costs daily and automatically remove stale sessions to control usage and prevent overspending.
A specialized AI Agent skill to bridge the gap between Markdown and WeChat Official Account publishing.
Manage NuGet packages using Central Package Management (CPM) and dotnet CLI commands. Never edit XML directly - use dotnet add/remove/list commands. Use shared version variables for related packages.
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.