Writing & Editing

Audit SKILL.md drift against repo docs, scripts, examples, and release notes

Web search skill that runs entirely on the user machine — no Z.AI / cloud SDK dependency. DuckDuckGo / Bing / Google HTML scraping with automatic engine fallback.

Turn an email into an enriched, cited public profile: a zero-dependency agent skill with a free-to-premium enrichment waterfall (GitHub, Tabstack, Hunter, SixtyFour).

深层结构驱动的长篇小说完整写作 Codex Skill，支持复调人物、旁观者主角、象征系统、阶层全景、卷纲细纲、正文追踪与防偏航修订。

My Claude Code skills. wong turns your work day into a study guide you can actually read. dormammu breaks your code until it works. agamotto summons a ruthless AI critic to tear your plans apart.

Accept any Token-2022 mint in your Solana program without getting drained. A tested Anchor guard that refuses hostile mints on-chain, plus a scanner. Anchor 1.0 + LiteSVM. Built for the Solana AI Kit.

A command-line client for Huly built on huly-mcp, featuring project and issue management, search, direct MCP tool calls, and Agent Skill support.

Codex Skill and runbook for querying banked Codex reset credits / Codex 重置机会过期时间查询Skill，可以安装后查询，也支持不安装一次性查询

Claude skill to proofread & semantically reconstruct error-dense medical ASR transcripts — multi-transcript diff, never fabricates, powered by a self-growing Notion glossary that learns confusing terms automatically. ｜ 醫學語音逐字稿校稿與語意重建的 Claude skill：多稿交叉比對、絕不捏造，搭配「會自動記錄易混淆字詞、自我成長」的 Notion 詞庫。

An agent skill (SKILL.md) for writing minimal reproducible examples maintainers can paste and run.

Codex skill for translating academic literature into polished Chinese LaTeX

Production-grade AI agent skills for content marketing, SEO & growth — works with Codex, Claude Code, Copilot, Cursor & more

Codex skill for structured academic research project management, experiment tracking, evidence mapping, and paper writing.

Codex skill for Wadiz-style Korean ecommerce detail pages using OpenCrab ontology packs

中/英自然语言找+装+改 agent skill (Claude Code / Codex) | Cross-agent skill discovery in CN/EN. 三维评分 R/U/T + OpenSSF Scorecard + OSV 漏洞库安全审 + agent-as-LLM 架构 + 三槽位版本快照.

Lightweight security scanner for vibecoded apps — run it from your AI agent (Cursor/Claude Code) or the CLI. Black-box + white-box, OWASP-mapped, SARIF-ready. Authorized testing only.

A CLI tool and library that executes Cypher graph queries against an in-memory graph built on Graphology

Project structure analysis and development logging for AI agents — project-onboard + project-docs

把内心戏私稿折射成可对外发布的客观分析 · 一个 water-shaped 的 Claude 技能

An Value Representation Architecture for LLM-based agents.

Audit LLM agents for hallucination using interrogation-science techniques. Ground, cite, abstain. An open agent skill.

Personal AI agent skills I use in development workflows.

Claude Code skill to set up loop engineering: an autonomous, self-running AI coding agent that discovers work, verifies it with a separate checker agent, and repeats until a verifiable goal is met.

An installable skill and field guide for removing AI slop from writing.