AI Agent Skills

Reverse-engineer and clone one or more websites in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in…

Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, he

Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line

Add a complete Sim integration from API docs, covering tools, block, icon, optional triggers, registrations, resolved-secret/model-input safety, and integration conventi…

Add or update a Sim dynamic selector using the shared manifest, server attachment, and selectors.execute path. Use for provider-backed, internal, or local option lists r…

Drive a PR to a clean review (Greptile 5/5, zero open threads) — ships if needed, keeps it mergeable against staging, re-triggers both Greptile and cubic, fixes real fin…

Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Dist…

Set up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Use when building a tracking…

Get structured design feedback on usability, hierarchy, and consistency. Trigger with "review this design", "critique this mockup", "what do you think of this screen?",…

Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a cha…

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code a

Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "…

Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop…

Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use…

当用户困在无法改变的处境（坏关系/讨厌的同事/不如意的事）里反复内耗、问「该忍还是该走」时调用。 核心理念: 面对任何情境只有三选项——改变它/接受它/离开它; 三者都不做是痛苦之源; 接受=快速适应, 用「积极方面是什么」重释训练。 不适用于: 可以改变的处境(应先改变), 以及涉及违法/人身安全的场景。 Triggers: 接受/忍…

当用户在重大选择上纠结（换工作/买房/搬城/合伙/结婚）、列了利弊表还是拿不定主意时调用。 核心理念: 无法决定就答否; 三个重大决定(住哪/和谁/做什么)值得花一两年; 两个均等选择选短期更痛苦的路。 不适用于: 日常琐碎选择（晚饭吃什么）、信息查询。 Triggers: 纠结/拿不定主意/要不要/该不该/利弊/decision/he…