Writing & Editing

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)

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。

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.

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 paragraph-level academic paper logic

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

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

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

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

Codex skill for writing accurate GitHub project READMEs

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。

Read-only readiness audits for agent skill repositories

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

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.

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.

Scene-specific AI workers for Codex and Claude.

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

A marketplace of plugins for claude.ai

Evidence-backed release candidate notes for local agent work

Living docs protocol and Codex skill for keeping AI-assisted code changes, requirements, status, guardrails, tests, and change records in sync.

Agent skill and reference runtime for maintaining a git-backed business ontology: source intake, review gates, evals, and MCP/GBrain boundaries.

📖 A Claude Code / Codex skill that deep-reads an academic paper and explains it thoroughly in Chinese — grounded in an anchored knowledge graph so it never fabricates content not in the source.

An interactive Codex skill for reading research papers stage by stage and maintaining evidence-aware Markdown notes.

Minimalistic, project-agnostic skills and rules for AI coding agents