Writing & Editing

A simple and crude Claude skill that allows people to perform Excel tests just by writing what the test is supposed to do in a table.

Codex skill for bilingual Obsidian paper cards from Markdown or Zotero, with verified translation and stable assets.

Reconnaissance on a Git repository before you trust it: secrets, vulnerable deps (OSV.dev), malicious-code heuristics, author due-diligence, privacy posture, and AI-agent-targeting content, in one graded report. Ships a Claude skill for verified, pre-deploy scanning.

Evidence-grounded Agent Skill for turning podcasts, papers, and long reads into traceable reconstructions and publishable content packs.

AI agent skill for localizing Ren'Py games (PC + Android): enforced terminology consistency, two-pass LLM translation, dynamic/persistent text audits, CJK bootstrap, APK overlay signing and verification

Composable Skills written for agents, by agents.

A Codex skill that distills field-specific academic writing patterns from published research papers.

x-algorithm-boost — Claude skill for X strategy and writing, derived from the open-sourced For You algorithm: real ranking weights, filter stack and credibility model. Audits an account for its binding constraint before it scores a post.

Two Claude Code skills for ADHD developers (mirror, librarian), copied unedited from the author's daily ~/.claude/skills. MIT. No installer, no dependencies.

通过持续对话共同研究、搭建结构并完成解释型视频内容的 Codex Skill

15 principles and 17 operational guides for .NET Aspire services on Fly.io and Azure, extracted from systems already in production, readable as documentation, installable as agent plugins for Claude Code, GitHub Copilot and VS Code.

Claude Code skills that turn papers and conversations into a cross-linked Obsidian knowledge base — ten-section paper notes with inline figures, filed under topic hubs.

Free x402 buyer-discovery audits, installable agent skills, and signed provider launch profiles over MCP.

Agent skill: run a project from one manager session — GitHub issues as the board, one builder tab per issue, self-review and auto-merge

换电脑、换网络，不再反复登录公众号后台修改IP白名单。一个只负责对接OpenLX长期在线网关的独立Agent Skill。

Open-source layer that lets your own AI agent (Claude Code, Codex, Cursor, Gemini CLI) read your notes first, then find, order and PAY for goods on real shops under a signed purchase mandate. Allegro.pl verified: first live autonomous purchase 2026-09-05. PSD2-aware, honest anti-bot, self-install by any AI agent.

A text-grounded Agent Skill for tracing aesthetic lineages from criticism into films, books, and other works.

Agent skill and local supervisor for off-session LLM jobs

Read-only Modbus engineering skills and workflows for Codex, Claude Code, Cursor, and other Agent Plugins clients.

EveryNumber phone-number activation and rental skill for Codex and Claude Code. REST catalog discovery, bounded code polling and explicit order settlement rules.

Estimate Astra task cost before execution. Compare Standard and Fast with an evidence-based range — an open Agent Skill.

EveryMail transactional email skill for Codex and Claude Code. REST sender-readiness checks, message preparation and approved single or batch delivery.

Agent skill + standalone CLIs to audit, minimize, and heal bloated Vitest/Jest test suites — per-test coverage metrics, greedy minimization, AI-slop detection, mutation-score verification

Route Codex tasks between GPT-6 Astra and GPT-5.6 Sol by expected rework cost, then delegate bounded repetitive work to GPT-5.6 Luna.