Writing & Editing

Claude Code skill: turn a work summary/project writeup into editable PowerPoint architecture/link-chain/process diagrams

An agent skill that removes signs of AI-generated writing from text

面向 Journal 与 Grant 两类场景的中文医学写作 Codex Skill

Claude Code skill: turn a thesis/proposal/paper into editable PowerPoint framework/roadmap/conceptual-model figures

Cyber Aware Creations — CISO Toolkit: composable, NIST-aligned Claude skills for security leaders (risk register + board translation).

Improved fork of affaan-m/ECC: react-testing skill for Claude Code. Credit to @affaan-m.

Turn everyday photos into tactile editorial study cards with a reusable Codex skill.

将照片转成复古编辑印刷插画的 Codex Skill，支持美食、饮品、风景、建筑、人像和产品

Codex skill for translating complete English academic papers into fluent Chinese

Evidence-driven Codex skill for industrial Chinese long-form web fiction workflows

Extensible Codex skill for mainland Chinese lure-fishing translation, naturalization, fidelity checks, and quality gates.

Yifan's personal Claude Code skills: dev-workflow, work-tools, writing

D∞ — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has, made mechanical: an agent embodied in a directory, three operators, and a gate that catches a missing closure at the syntax level.

Delivery conveyor for Claude Code and the OpenAI Codex CLI (investigate → decompose → deliver), plus the reproducible container it runs in — mechanical gates, worktree-per-ticket, PRs driven to green.

Typed step contracts for Gherkin, so a scenario can be told wrong before it runs. The vocabulary is machine-readable for agents, and every execution leaves a receipt the tool measured rather than the agent reported.

Scan AI agent skills and SKILL.md files for prompt injection, dangerous commands, exposed secrets, and install-time supply-chain risks.

Pine Script v6 skills and MCP tooling for coding agents — backed by a real validator, not prose.

Capture and co-develop important ideas into traceable Markdown without auto-starting implementation.

Repository-native planning guardrail against AI process slop.

Public, grab-and-go agent skills for rigorous software engineering workflows.

Codex skill for closing conversations into traceable process assets

Feastalytics CLI + agent skill — drive campaigns, automations, offers, funnels, and members-program rewards from the terminal. Works with Claude Code, Codex, Cursor.

An unofficial, provider-agnostic Agent Skill for querying the Rankscale AI brand-visibility REST API — works with Claude Code, Cursor, Codex, and other agentic tools.

Self-hosted infrastructure for selling Agent Skills. Storefront, checkout, licensed delivery, updates, and leak tracing.