majiayu000

majiayu000/spellbook

Skill Claude CodeCodex

An idea-development role that extends a proposal through comparisons with other industries, historical periods, nature, or art. It is one participant in the idea-team discussion.

majiayu000/spellbook

Skill Claude CodeCodex

A critical-thinking role that examines an idea by finding weak assumptions, counterexamples, unreliable evidence, and awkward user situations.

majiayu000/spellbook

Skill Claude CodeCodex

A research role for an idea discussion that searches for current facts, competitors, examples, and sources. Competitors are other products or services solving a similar problem.

majiayu000/spellbook

Skill Claude CodeCodex

A structured group discussion for exploring a product idea through three roles: researcher, critic, and analogy finder. The roles look for evidence, weaknesses, and useful comparisons.

majiayu000/spellbook

Skill Claude CodeCodex

A guided process for turning a product idea into a product brief and a clickable HTML prototype. It includes steps for checking feasibility, reducing the first version, mapping the user journey, and checking ease of use.

majiayu000/spellbook

Plugin Claude Code

Rust development toolkit with best practices, code review, performance optimization, and async Rust patterns.

majiayu000/spellbook

Skill Claude CodeCodex

Audit AND optimize a CLAUDE.md / AGENTS.md instruction file — score it against the five high-leverage patterns, flag anti-patterns, then apply approved fixes in place. Use when the user says 优化 CLAUDE.md / 优化 AGENTS.md / optimize my agent doc / 帮我改 claudemd, or after an audit when they want the fixes applied (not just…

majiayu000/spellbook

Skill Claude CodeCodex

Generate or update repository-specific AGENTS.md instruction files from real repo evidence. Use when asked to create, design, scaffold, split, or improve root or scoped AGENTS.md files for Codex/Claude/agent workflows, especially when a repo needs directory-specific rules, validation commands, generated-file…

majiayu000/spellbook

Skill Claude CodeCodex

REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.

majiayu000/spellbook

Skill Claude CodeCodex

Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform guidelines. Covers Material Design 3, Human Interface Guidelines, color theory, typography, and 2025 trends.

majiayu000/spellbook

Skill Claude CodeCodex

End-to-end app feature inventory and user-story testing workflow with a canonical tracker. Use when the user asks to audit every feature, derive expected behavior from code, test user journeys, or explicitly fix and retest documented UX or logistical defects.

majiayu000/spellbook

Skill Claude CodeCodex

Design architecture foundations before implementation. Use when asked to design or refactor architecture, choose Rust/Go crate, package, module, runtime, workflow, or service boundaries, compare mature project architecture, prevent stacked one-off PRs, audit migration debt in existing repos, or produce a spec before…

majiayu000/spellbook

Skill Claude CodeCodex

Ask Grok or Gemini via opencli (browser-session based, no API cost). Use when the user says "问 grok", "问 gemini", "ask grok", "ask gemini", "用 grok 查", "grok 怎么看", "让 gemini 分析", or wants a second opinion from Grok/Gemini without paying API tokens. Routes to opencli which drives the already-logged-in Chrome session.

majiayu000/spellbook

Skill Claude CodeCodex

OAuth 2.1 + JWT authentication security best practices. Use when implementing auth, API authorization, token management. Follows RFC 9700 (2025).

majiayu000/spellbook

Skill Claude CodeCodex

A workflow for extracting specific decision rules from approved expert-model interviews or real task records and packaging them for skill review.

majiayu000/spellbook

Skill Claude CodeCodex

A diagnostic and configuration skill for Clash Verge and Mihomo, tools that manage network proxy profiles and routing rules. It focuses on inspecting profiles, checking connectivity, switching profiles, and routing AI tools such as Claude, Codex, Cursor, or Warp.

majiayu000/spellbook

Skill Claude CodeCodex

A command-line tool that shows which proxy route a selected computer process is using. Mihomo is the proxy engine behind some Clash clients.

majiayu000/spellbook

Skill Claude CodeCodex

A read-only method for inspecting authorized local executable files and release binaries, including Mach-O, ELF, PE, WebAssembly, and packaged applications. Static analysis examines a file without running it.

majiayu000/spellbook

Skill Claude CodeCodex

A deployment guide for adding NewAPI, a billing and usage-control layer, in front of an already running CLIProxyAPI service. CLIProxyAPI provides an OpenAI-compatible interface to several AI account providers.

majiayu000/spellbook

Skill Claude CodeCodex

A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.

majiayu000/spellbook

Skill Claude CodeCodex

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

majiayu000/spellbook

Skill Claude CodeCodex

Use when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and handoff discipline to keep daily Codex usage responsive and low-friction. Always pairs with comprehensive handoffs before archiving active work.

majiayu000/spellbook

Skill Claude CodeCodex

Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs2.sqlite, logs2.sqlite-wal, blockloginserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.

majiayu000/spellbook

Skill Claude CodeCodex

Use when you want Codex to review its own recent history (last N days or specific period) and improve its behavior. Produces minimal, high-signal updates to AGENTS.md and tiny reusable skills. The goal is long-term fluency — Codex gradually becomes better at your specific style, constraints, and workflows.