Explorar skills

Provides base R programming guidance covering data structures, data wrangling, statistical modeling, visualization, and I/O — using only packages included in a standard R installation. Use when the user writes or debugs R scripts, works with vectors, matrices, lists, data frames, or factors, applies the apply family (sapply, lapply, vapply, tapply), fits models with lm/glm/aov/nls, creates base gr

End-to-end Malaysian accounting engagement workflow. Takes a client folder and produces accrual-basis financial statements (Excel working papers + PDF) compliant with MPERS / MFRS / ITA 1967. Covers Sole Proprietor, Partnership, Sdn Bhd, Berhad, and NGO. USE THIS SKILL when the user wants to: - Start or continue an accounting engagement: "start the accounting", "process this client", "do the full

Two-pass code audit: adversarial Opus deep review + standard Codex second opinion. Use after implementing features, fixing multi-file bugs, or when the user says 'audit this'. Checks types, API contracts, data consistency, auth, pagination, dead code, edge cases, and anything else that looks off.

Use when user asks to humanise text, remove AI writing patterns, make text sound human, de-slop writing, or strip AI tells. Also triggers on "humanize", "make this sound natural", "remove AI", "de-AI", "rewrite like a human". Works on any text input regardless of origin.

Build production-ready MCP servers using FastMCP framework with proven patterns for tools, resources, prompts, OAuth authentication, and comprehensive testing. Use this when creating FastMCP-based MCP servers with features like Google OAuth, multiple resource types, testing with FastMCP Client, or complex tool implementations.

a2a (Agent-to-Agent) — 跨模型对抗式 code review。Claude 写的代码让 Codex 审，Codex 写的让 Claude 审，互相找茬不留死角。

Marketing team as slash commands. Current Kai inventory: 46 skill directories, 44 canonical kai-* skill docs, 40 public /kai router commands, 52 playbook docs, 35 checklists, 27 framework docs, 17 channel guides, and 8 audience persona profiles. Full marketing ops from brief to gate.

ProductionOS — dual-target AI engineering operating system for repo-wide audits, upgrade plans, code reviews, strategic product reviews, security sweeps, UX audits, and recursive quality improvement.

Persistent memory MCP server for Claude Code — self-hosted, n8n + PostgreSQL + pgvector. No cloud required.

Agent-agnostic long-term project memory through `.memory-bank/` + RULES (TDD/SOLID/Clean Architecture/FSD/Mobile) + dev-toolkit commands. Use when working in a project with a `.memory-bank/` directory or when the user explicitly asks for memory-bank workflow, code rules, or dev-toolkit commands.

Fetches and summarizes the latest AI news from across the internet — including tech blogs, research outlets, newsletters, and news sites — then renders a polished interactive digest as a React artifact in chat. Trigger this skill whenever the user asks about recent or latest AI news, developments, breakthroughs, releases, or anything like \"what's new in AI\", \"AI news this week\", \"catch me up

Generate beautiful themed HTML data displays. Six visual idioms with matched voices, rendered as self-contained HTML files. Use when the user asks for charts, dashboards, reports, tearsheets, briefings, data visualizations, or any data-driven document.