majiayu000/spellbook

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

This repository also configures its own agents. See what spellbook tells them →

278Stars on the repository
120Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

server-security

73

majiayu000/spellbook

Skill Claude Code

Use this skill for server security audits and reversible hardening plans across SSH, firewall, users, services, file permissions, and update posture.

not rated 278 +6 yesterday A SkillSpector: pass 55 tokens original MIT

skill-audit

74

majiayu000/spellbook

Skill Claude CodeCodex

Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building Claude Code: How we use skills. Use when reviewing an existing skill, deciding whether a workflow deserves a skill, planning a skill library, turning team knowledge into skills, choosing skill…

not rated 278 +6 yesterday A SkillSpector: pass 79 tokens original MIT

skill-creator

75

majiayu000/spellbook

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 278 +6 yesterday A 63 tokens copy · 84% MIT

majiayu000/spellbook

Skill Codex

Audit and safely repair cross-runtime Skill governance: canonical-source ownership, divergent or duplicate projections, exposure scopes and budgets, lifecycle drift, quarantine, and retirement. Use when the user explicitly requests cross-runtime or cross-scope Skill governance; ignore project-local Skill inventory…

not rated 278 +6 yesterday A SkillSpector: warn 75 tokens original MIT

skill-lifeguard

77

majiayu000/spellbook

Skill Claude CodeCodex needs its repo

Use when a skill is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract. Trigger for phrases like skill lifeguard, reliable skill, self-maintaining skill, negative examples, verification checkpoints, drift signals, replay hooks, or failure log to skill patch. Audits or patches skills so…

not rated 278 +6 yesterday A SkillSpector: pass 92 tokens original MIT

skill-usage-stats

78

majiayu000/spellbook

Skill Claude CodeCodex

A read-only reporting tool for checking how Claude and Codex skills are being used and whether related agent settings appear healthy.

not rated 278 +6 yesterday A SkillSpector: pass 103 tokens original MIT

slides

79

majiayu000/spellbook

Skill Claude Code

A slide generator that creates PNG images for presentation decks, including simple backgrounds for spoken-video scripts and fuller layouts for standalone presentations.

not rated 278 +6 yesterday A SkillSpector: pass 41 tokens original MIT

sol-luna-router

80

majiayu000/spellbook

Skill Codex

Route substantial coding or repository-review work through a two-stage Sol commander/verifier and separate Luna Max CLI worker. Use when the user explicitly asks Sol to direct or supervise Luna, explicitly requests this router, needs an isolated auditable Luna-owned implementation with a Sol review loop, or asks to…

not rated 278 +6 yesterday A SkillSpector: warn 123 tokens original MIT

majiayu000/spellbook

Skill Claude CodeCodex

Design, audit, or implement application structured logging architecture from repository evidence. Use when a user asks whether or where to add logs, how to choose or migrate a logger, how to standardize events/fields/levels/redaction, how to add HTTP access or panic logs, or why production logs cannot answer an…

not rated 278 +6 yesterday A SkillSpector: pass 95 tokens original MIT

system-doctor

82

majiayu000/spellbook

Skill Claude Code

A system performance diagnosis guide for finding why a computer is slow, overloaded, or short on memory. It checks running processes, CPU, memory, swap, and related system details.

not rated 278 +6 yesterday A SkillSpector: pass 35 tokens original MIT

majiayu000/spellbook

Skill Claude CodeCodex

Four-phase debugging framework for any technical issue. Use when encountering bugs, errors, or unexpected behavior. Prevents random fix attempts.

not rated 278 +6 yesterday A SkillSpector: pass 31 tokens original MIT

technical-spec

84

majiayu000/spellbook

Skill Claude CodeCodex

Technical specification and design document expert. Use when writing design docs, RFCs, ADRs, or evaluating technology choices. Covers C4 model, system design, and architecture documentation.

not rated 278 +6 yesterday A SkillSpector: warn 39 tokens original MIT

majiayu000/spellbook

Skill Claude CodeCodex

Enforces TDD discipline with RED-GREEN-REFACTOR cycle. Use when writing new features, fixing bugs, or refactoring code. Ensures tests genuinely verify behavior.

not rated 278 +6 yesterday A 40 tokens original MIT

threads

86

majiayu000/spellbook

Skill Codex

A workflow guide for coordinating several coding agents on a broad task. It defines separate work lanes, file ownership, review gates, and checks that the work is complete.

not rated 278 +6 yesterday A SkillSpector: pass 75 tokens original MIT

trip-planner

87

majiayu000/spellbook

Skill Claude CodeCodex

Use when the user wants detailed travel itineraries with activities, logistics, day-by-day schedules, vacation planning, trip organization, or travel documentation.

not rated 278 +6 yesterday A SkillSpector: warn 33 tokens original MIT

typescript-project

88

majiayu000/spellbook

Skill Claude CodeCodex needs its repo

Modern TypeScript project architecture guide for 2025. Use when creating new TS projects, setting up configurations, or designing project structure. Covers tech stack selection, layered architecture, and best practices.

not rated 278 +6 yesterday A SkillSpector: warn 42 tokens original MIT

ui-designer

89

majiayu000/spellbook

Skill Claude CodeCodex

Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.

not rated 278 +6 yesterday A 47 tokens copy · 100% MIT

ui-ux-pro-max

90

majiayu000/spellbook

Skill Claude CodeCodex

Use when planning, building, designing, code review, refactor, fixing, improving, optimizing, enhancing, or checking UI/UX work. Covers product patterns, landing pages, chart choices, visual styles, palettes, typography, UX rules, and 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind…

not rated 278 +6 yesterday A SkillSpector: pass 166 tokens original MIT

vibeguard

91

majiayu000/spellbook

Skill Claude CodeCodex

Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives. Use when the user asks for guardrails, task contracts, risk scoring, or review templates.

not rated 278 +6 yesterday A SkillSpector: pass 45 tokens original MIT

vscode-doctor

92

majiayu000/spellbook

Skill Claude Code

Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use when the user reports editor lag, typing delay, UI freezes, extension host stalls, file watcher noise, high editor CPU/RSS, uses VS Code/Cursor as a file browser over a large folder, or wants a safe editor…

not rated 278 +6 yesterday A SkillSpector: warn 75 tokens original MIT

majiayu000/spellbook

Skill Claude CodeCodex

Use when creating elaborate, multi-component claude.ai HTML artifacts with React, Tailwind CSS, shadcn/ui, state management, routing, or complex frontend structure; not for simple single-file HTML/JSX artifacts.

not rated 278 +6 yesterday A 50 tokens copy · 94% MIT

weekly

94

majiayu000/spellbook

Skill Claude CodeCodex

A weekly-report workflow that combines Git history with records from Claude Code and Codex sessions. It turns work from a selected date range into a report for two related software repositories.

not rated 278 +6 yesterday A 41 tokens original MIT

majiayu000/spellbook

Skill Claude CodeCodex

A Chinese-language editing workflow that makes Xiaohongshu, public-account, and video-script writing sound more natural and culturally local. It focuses on removing stiff phrasing that reads like a literal translation from English.

not rated 278 +6 yesterday A SkillSpector: pass 189 tokens original MIT

xiaohongshu

96

majiayu000/spellbook

Skill Claude Code

A Chinese-language content workflow for Xiaohongshu, a Chinese social-media platform focused on lifestyle and recommendation posts. It helps create posts, images, tags, and publishing files for that platform.

not rated 278 +6 yesterday A SkillSpector: pass 35 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: