Claude
Tools

Preservation-first architectural intelligence for Codex: rendering, plan-to-3D, materials, reviews, documentation, and portfolios.

Augmentation-only Claude Agent Skills for fiction writers — editors, critique simulators, character work, and craft drills. Reads and critiques your manuscript; never ghostwrites.

Human-in-the-loop context compaction for Claude Code — you pick which conversation turns survive, a SessionStart hook re-injects them after every compact/resume.

Self-deploying cross-tool AI harness — one canonical source deployed to Claude Code, Codex, Cursor, Devin, Antigravity & 9 more. Loop engineering, three-layer memory, worker personas, hooks, MCP, vault.

Automatic model router for Claude Code — a UserPromptSubmit hook that scores each prompt's complexity and recommends the right model (Haiku/Sonnet/Opus). Bilingual, configurable, 100% local.

Claude Code, powered by your ChatGPT subscription. Keep your CLI workflow, skills, hooks, and MCP tools while using the Codex backend.

A Claude skill: land your first internship with no connections — concise resume, application system, founder cold emails.

Diagnose Chrome Manifest V3 extension pitfalls — and teach AI coding agents to avoid them.

AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.

Source-backed skills that turn official Claude and Codex training into reliable daily workflows.

AI skill: 把一张截图或一段文字，自动生成一整套可直接发布的小红书/公众号教程图与信息图。晚秋简约风，纯排版离线渲染，支持 Claude Code / Codex / WorkBuddy

AI 教练带你走精益画布→揪关键假设→设计最低成本验证，可反复重跑 · Coach a founder through a Lean Canvas, pin the riskiest assumption, design the cheapest validation. Re-runnable.

macOS notification hook for Claude Code that focuses your terminal (Ghostty/Cursor) when you click it

«Скилл грамматики для юриста»: проверка формы юридического текста (синтаксическая неоднозначность, пунктуация, область действия «и/или», границы сроков, анафора, деонтическая модальность) на праве РФ. Третий элемент тривиума грамматика·логика·риторика, парный к pravo-logika и pravo-ritorika. Показывает оба прочтения, выбор оставляет автору. MIT.

Port Hermes Agent's self-improving skill loop to Cursor & Claude Code via native Hooks + Skills.

Portable marketing second brain for Codex, Claude Code, and Agent Skills with 502 sources for strategy, SMM, content, growth, CRO, and buyer psychology.

幫任何網站加上聚光燈導覽的 Claude skill：分析版面、訪談開發者、產生步驟並用 Playwright 逐步驗證。Claude skill that adds a verified spotlight onboarding tour to any website.

Claude in Chrome, powered by your local claude CLI. Drive your real logged-in Chrome from Claude Code, or chat in a side panel while you browse. No claude.ai login, no intermediary server, and it never steals focus.

DNA de design de 20 sites premium — Lenis + GSAP/ScrollTrigger destilados em leis, calibres e 22 efeitos com codigo. Skill do Claude Code.

Research-grounded Agent Skill for writing professional LLM prompts — matches technique to model class, separates evidence from folklore.

Claude Skill: country / major-world-events news briefing from Wikipedia Current Events + GDELT (stdlib only, offline fixture mode)

Claude Skill: extract cryptographic protocol message flow from code, RFCs, ProVerif or Tamarin models into Mermaid + ASCII sequence diagrams

A catalogue of AI writing tells, each with a plain rewrite, shared by Fireside. Drop it into a system prompt to stop LLM output reading like LLM output.

発言が詭弁かどうかを4行で即答する Claude Code スキル。詭弁の特徴のガイドライン19条＋論理学の誤謬で判定し、本来の論点と論点に戻す一言まで返す