Writing & Editing

Evidence-based JD–resume analysis powered by Python and a Codex Skill

Submission source for the BenchFlow Agent Skill Lift hackathon: four static skills, one meta-skill, and the tooling to verify every number in the writeups.

Codex skill for restrained, visual Chinese sad copywriting and viral titles

Multi-agent hypothesis lab: run any number of hypotheses with agents/subagents in isolated git worktrees; mandatory JSON + Markdown findings. Python/Rust hybrid safety cage. Never auto-merges.

先教你怎么用，再把 AI 味中文改回自然表达的 Agent Skill

Agent Skill for writing, validating, and model-checking Event-B formal models with rossi and ProB.

Approve what an agent reads by content, not by name. A verifying MCP gateway that makes tool-description and Agent Skills rug-pulls unexpressible.

Cursor Skill：开题或做计划前的全网类似技术调研（GitHub 开源为主），结果在对话里交付

Route any request to the right agent skills. One package, every AI client.

飞书 OKR 草稿｜按严格 OKR 标准写出有结果、有指标、有承接、有主责的高质量 OKR，并支持写入飞书、真实 @ 与保存核验

A skill that builds skills: create, audit and ship Agent Skills and Claude Code plugins — conformance to the open standard, a validator that can fail, every distribution channel, and the MCP/A2A boundary.

中文技术博客与工程文章写作 Agent Skill，支持多轮共创、结构重构、润色、事实核查、发布检查与独立审稿。

中文老师｜Chinese Teacher — 让中文工作文档有判断力、有人味、能推动决策的 AI skill，自动插入飞书画板做视觉摘要

Agent skill that edits drafts into sharper, more human writing without flattening the writer's voice. Also detects AI-slop patterns without guessing authorship.

Fast Windows file discovery for Codex, Claude Code, and compatible AI agents using Voidtools Everything CLI.

Agent skill that turns a URL, file, or topic into a publish-ready editorial package: article draft, social metadata, and production-ready figure specs.

Write like a person. Or like you. Drop-in agent skill for Claude, Codex, Cursor, Hermes, OpenClaw.

Several coding agents, one repository, no collisions — leases with a TTL, race-free id reservation, a run journal and a generated board over a pluggable knowledge cloud. Ships in the sshlg-skills bundle.

Evidence-first website audit for search AND answer engines. Ten tracks from crawl access to AI citation mechanics; every finding carries an observation, every recommendation an evidence tier. Output is a prioritized change plan plus a link-building brief with keyword CSV — not a score.

LNURL-auth (LUD-04) signer for LLM coding agents — Sign in with Lightning, no wallet required

职业资产：通过读材料和深度访谈沉淀长期职业资产，并针对岗位生成可迭代简历的 Agent skill

Full-cycle delivery orchestrator for AI coding agents: a mandatory intake grill that front-loads every decision, then ten gated stages — docs, brainstorm, decompose, spec, plan, build, tests, deploy, post-deploy, acceptance — with a loop guard that breaks churn.

The stupid coordination tool - tasks and architecture decisions in your repo, behind one CLI any coding agent can call

Self-hostable Digital Twins of Different APIs For E2E & Agent Simulation Testing