Writing & Editing

Catch the database migration that locks your table before it ships. A Claude Agent Skill that reviews migrations for downtime risks and rewrites them into safe, zero-downtime steps. Postgres & MySQL, any framework.

Cursor Agent Skill for writing conventional commit messages

Open-source Agent Skill for standards-based professional document creation (ISO/IEEE/APA/PDF-A, i18n/RTL).

Spec-driven multi-agent teamwork for any skills-capable agent (Claude Code, Codex, and more) — plan, dispatch, monitor, QA. No framework lock-in.

这是一个面向 SCI 论文审稿的 Codex Skill，适用于对用户上传的学术论文进行分领域、分章节、证据导向的系统评审。该 Skill 会首先判断论文所属研究领域，再结合全文内容、关键实验结果和必要的前沿文献检索，对 Introduction、Results and Discussion、Conclusion 等部分进行严谨审阅，重点识别逻辑结构、实验设计、数据解释、机理推断、结论外推和语言表述中的问题。它强调所有审稿意见都必须回到原文逐条核验，避免凭空编造，并可根据问题严重性和修改难度对意见进行筛选、排序和中英文输出，适合用于辅助生成高质量、可直接用于期刊审稿报告的 Review Comments。

高善文风格宏观研究与财经分析 SKILL — 完整版,跨平台 Agent 兼容,致敬高善文先生(1971-2026)

name: ethics-audit

OpenAlex Explorer — an agent skill, LLM-powered automated literature review pipeline: search papers via OpenAlex, screen for relevance & quality, extract summaries, and write structured reviews.

Codex skill for summarizing completed projects into reusable handoff documents and resume prompts.

一个用于将技术视频或技术文章整理为可发布技术博客的 Codex Skill，支持自动生成中英文 Markdown，并配套截图、图示和其他视觉素材

HCS Agent Ecosystem v2.0 - Complete OpenCode Agent & Skill System with 36 Autonomous Agents, Admin Dashboard, Customer Management, Content Rephraser Pipeline, Multi-Platform Support, Auto-Trigger System, and Localhost-First Pipeline

Codex skill for repairing malformed PDF extraction and auditing silent content loss.

Codex skill for paragraph-level academic paper logic

A collection of Claude skills to aid in grant writing and submission

Codex skill for writing accurate GitHub project READMEs

Carefully crafted, token-efficient Agent Skills for reliable agentic workflows.

Read-only readiness audits for agent skill repositories

Index a whole repo (code + docs) into a navigable, AI-analyzed encyclopedia — map + per-module entries + typed link-graph — so an AI works in huge codebases without filling its context. One auto-routing skills.sh skill with grounded, citation-checked analysis and optional local (Ollama) semantic search.

Short-lived text/plain URLs for long prompts and agent instructions

Scene-specific AI workers for Codex and Claude.

Strip AI flavor from writing, across agents — a de-AI-flavor skill + one-command installer. 去除文字里的 AI 味,一条命令装到你所有 agent。

Evaluate a skill or codebase with a multi-agent workflow, ground every finding in a real file:line, and generate an AI-exploitable TDD fix backlog. A skills.sh agent skill.

A marketplace of plugins for claude.ai

Evidence-backed release candidate notes for local agent work