majiayu000/spellbook

1

fixflow Use when executing coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run…

majiayu000/spellbook

50

2

optflow Use when the user asks to discover and deliver repository optimization work end to end: identify performance/reliabil…

majiayu000/spellbook

48

3

plan-flow Use when deep architecture review or convergence planning requires analyzing repository-level duplicate/redundant des…

majiayu000/spellbook

47

4

threads Use when the user explicitly asks for $threads, Codex-native subagents, 开几个子 agent, or a GitHub issue/PR queue ne…

majiayu000/spellbook

28

5

optimize-network Safely diagnose and improve local network speed, latency, jitter, DNS, Wi-Fi, Ethernet, macOS network services, and b…

majiayu000/spellbook

24

6

cliproxy-newapi-stack 在已经过独立验证的 CLIProxyAPI upstream 之上部署 NewAPI 计费层，把 Codex/Claude/Gemini/Qwen 等订?

majiayu000/spellbook

19

7

codex-retrospective Use when you want Codex to review its own recent history (last N days or specific period) and improve its behavior.

majiayu000/spellbook

18

8

codex-fluent Use when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and ha…

majiayu000/spellbook

17

9

figma-to-react Use when the user wants to extract Figma designs into production-ready React or Next.js components with TypeScript, T…

majiayu000/spellbook

15

10

figma-to-code Extract Figma designs and generate production-ready React/Next.js components with TypeScript, Tailwind CSS, and pixel…

majiayu000/spellbook

14

11

ui-designer Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users p…

majiayu000/spellbook

14

12

agentsmd-optimize Audit and organize AI coding-agent instructions, including AGENTS.md, CLAUDE.md, skills, and agent definitions.

majiayu000/spellbook

13

13

cliproxy-deploy 在 Linux VPS 上部署 CLIProxyAPI（router-for-me/CLIProxyAPI）并暴露 OpenAI 兼容 API。覆盖 Go 环境、源码拉取、最小配置…

majiayu000/spellbook

13

14

comprehensive-testing Complete testing strategy covering TDD workflow, test pyramid, unit/integration/E2E/property testing, framework best …

majiayu000/spellbook

13

15

react-hooks-best-practices Provides React patterns for hooks, effects, refs, and component design. Covers escape hatches, anti-patterns, and cor…

majiayu000/spellbook

13

16

structured-logging-lite Design, audit, or implement application structured logging architecture from repository evidence. Use when a user ask…

majiayu000/spellbook

13

17

systematic-debugging Four-phase debugging framework for any technical issue. Use when encountering bugs, errors, or unexpected behavior. P…

majiayu000/spellbook

13

18

architecture-foundation Design architecture foundations before implementation. Use when asked to design or refactor architecture, choose Rust…

majiayu000/spellbook

12

19

playwright-automation Browser automation and testing with Playwright. Use when testing web applications, automating browser tasks, taking s…

majiayu000/spellbook

12

20

contribution-architect Use when a contributor wants to move beyond simple bug fixes into architectural improvements, technical debt discover…

majiayu000/spellbook

11

21

elegant-architecture Guides clean architecture design with strict 200-line file limits. Use when starting new features, refactoring large …

majiayu000/spellbook

11

22

gemma4-local-deploy 在本机 Mac 或 Apple Silicon 上部署 Gemma 4 12B。本地安装/升级 llama.cpp，下载 GGUF 量化模型，用 llama-server 暴露 Ope…

majiayu000/spellbook

11

23

git-commit-smart Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to …

majiayu000/spellbook

11

24

project-health-auditor Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking depende…

majiayu000/spellbook

11

25

release-engineering Plan and verify software releases with versioning, changelogs, release branches, feature flags, canaries, migration g…

majiayu000/spellbook

11

26

skill-audit Audit, design, categorize, distribute, and measure agent skills using lessons from Anthropic's Lessons from building …

majiayu000/spellbook

11

27

vscode-doctor Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use whe…

majiayu000/spellbook

11

28

xiaohongshu-netfeel-guardian 当用户用 Claude 写小红书、? ? - “Claude写小红书翻译? - “帮我把这个笔记改成纯中文网感”“去除Claude翻译? - “? - “强制Cla…

majiayu000/spellbook

11

29

flowguard Guard long, ambiguous, or stateful AI-agent work from drift. Use when the user asks to run or continue a multi-step t…

majiayu000/spellbook

10

30

config-secrets-environments Design, audit, and verify configuration, environment separation, secrets, BYOK flows, key rotation, config schema val…

majiayu000/spellbook

9

31

data-contract-migrations Design and verify data contracts, schema changes, migrations, rollbacks, backfills, compatibility windows, tenant iso…

majiayu000/spellbook

9

32

dev-architecture-playbook Route full software-development architecture work from product intent through design, implementation, testing, releas…

majiayu000/spellbook

9

33

multi-model-orchestrator Use when coordinating complex tasks across multiple AI agents with a centralized handoff document for planning, execu…

majiayu000/spellbook

9

34

performance-capacity Plan, diagnose, and verify performance budgets, latency targets, load tests, capacity estimates, bottleneck analysis,…

majiayu000/spellbook

9

35

repo-agent-context-audit Audit and recommend improvements for a repository's agent-readable context, including AGENTS.md, CLAUDE.md, WARP.md, …

majiayu000/spellbook

9

36

review-gate Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when…

majiayu000/spellbook

9

37

security-threat-model Threat-model product features, APIs, data flows, secrets, permissions, supply-chain changes, auth boundaries, and ris…

majiayu000/spellbook

9

38

agentsmd-scaffold Generate or update repository-specific AGENTS.md instruction files from real repo evidence.

majiayu000/spellbook

8

39

app-user-story-qa End-to-end app feature inventory and user-story testing workflow with a canonical tracker. Use when the user asks to …

majiayu000/spellbook

8

40

codex-log-guard Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user menti…

majiayu000/spellbook

8

41

incident-slo-runbook Create or audit SLOs, SLIs, alert rules, incident response steps, escalation paths, postmortems, operational runbooks…

majiayu000/spellbook

8

42

repo-scaffold Scaffold or standardize a production-ready repository structure with specs, source layout, tests, CI, agent context, …

majiayu000/spellbook

8

43

skill-usage-stats 只读统计 Claude/Codex 的 Skill 使用证据并检查 agent 配置健康。仅用于明确的健康检查、配置诊断、使用排行或低使用候选请…

majiayu000/spellbook

8

44

claude-mem Orchestrator-driven planning and execution workflow. Use when coordinating Claude memory-backed planning, make-plan/d…

majiayu000/spellbook

7

45

recap

majiayu000/spellbook

7

46

skill-lifeguard Use when a skill is brittle, drifting, repeatedly failing, or needs a Reliable Skill Contract.

majiayu000/spellbook

7

47

capability-distill 能力蒸馏工作流——从用户批准的强模型访谈或真实任务轨迹中提取非显然的判断规则，形成可审计的 judgment packet，再交给 skil…

majiayu000/spellbook

6

48

ip-check 检测一个 IP 或住? IP"、"为什么被判定在 X 国"、"check ip"、给出 socks5 代理凭证问归属或解锁时使用。

majiayu000/spellbook

6

49

skill-ecosystem-doctor Audit and safely repair cross-runtime Skill governance: canonical-source ownership, divergent or duplicate projection…

majiayu000/spellbook

6

50

structured-logging Comprehensive logging system design guide. Use when designing log architecture, establishing logging standards, addin…

majiayu000/spellbook

6