Explore skills

Synchronizes the agent environments. Looks at the inventory (plugin-sources.json) and reinstalls all skills and plugins from the sources indicated. Also cleans up any orphaned artifacts from removed plugins. Trigger when the user asks to "sync plugins", "update all plugins", "refresh environment", or "run the sync script".

Interactively select and uninstall agent plugins and skills from the local .agents/ environment.

A deliberately broken skill that should trigger multiple anti-pattern detections during analysis.

This AI game actual video prompt pack factory generates complete sets of keyframe image prompts, Seedance video prompts, and shot sequence timelines from a reference image or character/IP name. It supports both demo-oriented and story-driven video creation, including subtitle and TTS scripts for narrative content.

A fitness and diet tracking tool. It analyzes food photos for calories, logs workouts, calculates metabolism (BMR/TDEE), provides daily calorie summaries, and generates training/diet plans.

Identifies and eliminates typical AI writing patterns in Chinese text, such as clichés and formulaic structures, to make it sound natural and human-like. Applicable across all Chinese writing scenarios, from social media to academic abstracts.

Quantify "do they like you?" by importing WeChat/QQ chat logs, Moments screenshots, photos, and your subjective description. It outputs a 1-10 favorability score and detailed relationship progress advice.

Distills wiki source files into the RLM summary layer (summary.md, bullets.md, deep.md) using the cheapest available LLM CLI. Routes to Copilot gpt-5-mini first, then Claude Haiku, then Gemini Flash. Never uses Ollama. Use when wiki nodes need RLM summaries generated or refreshed.

计算机科学学术大佬——盲审评审专家与博士生导师。用于论文盲审评审、博士生研究指导、选题评估、写作改进和模拟答辩。当用户提到论文审稿、盲审、学术评审、论文review、博士指导、研究方向建议、开题报告、论文写作、选题评估、模拟答辩、学术问题讨论时触发此技能。即使用户没有明确说"审稿"，只要涉及对论文或研究方案的学术评价，都应使用此技能。

Dìtīng is a fictional character distillation skill. It extracts character settings from literature, film, and anime works to generate activatable character skills.

Haskell language extension and language edition (GHC2024/GHC2021) selection policy. Use when configuring or reviewing Haskell language extensions, cabal default-extensions, or default-language.

Opinionated constrained optimization skill using Augmented Lagrangian Methods (ALM), ADMM, and KKT verification. Enforces step ordering, solver routing, feasibility checks, and adversarial guards that agents skip unprompted. Trigger on: constrained optimization, KKT conditions, Lagrange multipliers, ALM, ADMM, shadow prices, infeasibility diagnosis, safe RL constraints, multi-objective Pareto, Bay