Writing & Editing

Shadow — on-device AI council and audit chain for regulated banking workflows. One engine, 4 device clients, 5 persona packs.

Compile natural language specs into local neural functions for text classification, extraction, and fuzzy matching tasks in your AI coding agent.

Generate aesthetically beautiful draw.io diagrams with a mandatory visual QA loop — your agent builds diagrams that actually look right.

Pi package for on-demand Verse / UEFN docs lookup via verse-mcp.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Publish HTML frontend games to the AI Game MCP platform.

AI Skill 执行可靠性审查工具。评估 Skill 被 AI 执行时的可复现性、可信度与业务适配性。Halu = Hallucination, Catch = 捕获。

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local project files.

帮助用户从零写出高质量 PRD，或评估/改进/增量更新已有需求文档。本技能按三视角（用户 / 商业 / 技术）完成诊断，分 **概念版** 与 **落地版** 写入工作区，并系统补全交互状态、数据规范、文案与关键页线框等细节，使文档可直接用于研发实现或 AI 生成代码。

A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is a diff in your repo. MCP + CLI.

Codex skill for checking usage limit reset windows and reset-credit expiries

Codex skill pack for rewriting rough prompts and learning prompt style from local evidence

Bilingual Codex skill for batch-matching resumes to internship HCs and preparing confirmed NetEase Mail Master applications.

Codex skill for rigorous scientific and document translation

10 copy-paste superprompts + 100 agent-ready goals for ChatGPT connectors (Gmail, Drive, Calendar), Claude Code, Codex, and MCP agents. Authored with Claude Fable 5, executed by GPT-5.5 xhigh or cheaper models. Includes LOOPS.md-inspired agent-loop templates.

A portable AI-agent skill for finding project blind spots, unknown unknowns, hidden risks, and missing decisions, with a durable ledger for repeat audits across Claude Code, Codex, and OpenCode.

正式技術報告 docx 交付技能(Claude Code / Codex Skill)——繁中政府/招標交付:全流程方法庫 + 台灣語料實證寫作標準 + 大陸用語 linter + 英文去 AI 味 linter

Claude Code / Codex / Antigravity 用の Agent Skills 集

Shareable skills and tools for AI agents

Agent Skill for saving raw repo-local knowledge captures.

Agent-agnostic self-improvement skill: reads your Claude Code, Codex & Cursor threads and turns recurring corrections into rules in CLAUDE.md / AGENTS.md / .cursor/rules. The write half of /insights.

My agent skills

Progressive docs-as-code template for AI agent skills, AGENTS.md, playbooks, work traces, and just test policies

Portable AI-agent skills (SKILL.md) for accommodation search, availability, pricing, cross-OTA comparison & reviews via ScoutingAPI. Works with Claude, MCP and more. MIT-0.