Writing & Editing

Speaker is a Codex skill project for academic presentations: read real.pptx, combine text extraction, PPTX structure parsing, page-by-page rendering, OCR, and visual review to generate page-by-page speaker notes, and write a clean version of the lecture into the PowerPoint comment area.

A Claude Code skill that generates and maintains AI-agent-oriented documentation for any repository.

Lean agentic dev loop for Claude Code: prime → lean-doc → orchestrate → repeat. Eleven standalone skills + an opt-in /flow conductor + a /council decision aid. No hooks, agent-free core — drop in and adapt.

Write, optimize, and test prompts through automatic, measured iteration — a model-agnostic skill for Claude Code, Codex, and Cursor.

Rust runtime with TS/Python bindings for Claude Skills with progressive disclosure of skill metadata, full content and scripts/resources. Any agent can now own skills. Currently support Seatbelt and experimentally, WASM, sandboxing

Official Monte Carlo toolkit for AI coding agents. Skills and plugins that bring data and agent observability — monitoring, triaging, troubleshooting, health checks — into Claude Code, Cursor, and more.

Claude Code and Codex SKILLs for PDF, Excel, Word, and PowerPoint manipulation — extraction, forms, formulas, tracked changes, adapted from Anthropic skills.

A lightweight desktop app to manage, doctor, and organize AI agent skills across 15+ coding tools — Cursor, Claude Code, Codex, Copilot, and more.

Autonomous novel writing AI Agent — agents write, audit, and revise novels with human review gates

Convert handwritten notes and scanned PDFs into clean, Overleaf-ready LaTeX files with full math and step-by-step detail

Automate code reviews for general code projects with modular parallel checks, config-driven scope, and clear reports.

Explore OpenClaw with an Obsidian knowledge base of 282 notes, 2397+ links, and deep research on its core docs and use cases

Explore a LangChain document pipeline for RAG, from ingestion and embeddings to retrieval and LLM response generation

Document Claude Code CLI v2.1.84 logic, modules, and config for reverse engineering and rewrite work

Scan project dependencies and Dockerfiles for known vulnerabilities across 8 ecosystems with free public sources and AI analysis

Document Claude Code source leak analysis, code breakdowns, and docs for Anthropic’s npm sourcemap exposure

Capture and organize notes in cc-notebook with a clean, simple interface for fast writing and easy review

Documentation and project-story skills (ADR, story, queue-audit, session-wrap) for Claude Code and Cursor, layered on OpenSpec.

Pause your AI agent. Ask a human. Resume with their answer. Open source human-in-the-loop (HITL) library for production LLM agents: Slack, email, and web dashboard. Typed Pydantic and Zod responses. Durable Temporal and LangGraph adapters. AI verifier. Audit trail. Self-hosted, Apache 2.0. Python and TypeScript.

Bilingual SkillOpt-inspired Codex skill writer for SKILL.md creation, validation gates, bounded edits, and agent skill optimization

Every agent leaves a paper trail. Tamper-evident JSONL audit logs for agentic workflows.

深知写作助手：基于深知搜索的公文与政务材料写作 Agent Skill

Privacy-first agent skill for curated Obsidian memory closeouts, retrieval, Codex, and Claude

LLM-ready web documentation resolver: Python cascade skill + web + Rust CLI (wdr) with semantic cache, multi-provider routing, and quality synthesis