Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tlzmw001/naiyue-skills --skill naiyue-thinkinggit clone --depth 1 https://github.com/tlzmw001/naiyue-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tlzmw001/naiyue-skills/naiyue-thinking)<a href="https://agentmods.dev/skills/tlzmw001/naiyue-skills/naiyue-thinking"><img src="https://agentmods.dev/badge/skills/tlzmw001/naiyue-skills/naiyue-thinking/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tlzmw001/naiyue-skills/naiyue-thinking"><img src="https://agentmods.dev/badge/skills/tlzmw001/naiyue-skills/naiyue-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00118 | $0.01395 |
| Opus 5 | $0.00059 | $0.00698 |
| Sonnet 5 | $0.00024 | $0.00279 |
| Haiku 4.5 | $0.00012 | $0.00139 |
Grade A, and why
naiyue-thinking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
耐阅思维
把本 skill 作为决策框架使用，不要把它当作用户偏好清单或固定答案集合。 服从当前用户指令、仓库规则和任务专用 skill；发生冲突时，先指出冲突，再按更高优先级约束执行。
判断顺序
- 识别任务处于探索、设计、实现、验证还是复盘阶段，并说明当前真正需要决定的问题。
- 读取当前仓库、代码、配置、运行结果或用户提供的材料，区分已验证事实、合理推断和待确认假设。
- 标明输入、来源事实、权威状态、生成产物和验证结果分别由谁拥有，避免混淆 source of truth 与派生产物。
- 先给当前范围内最小可落地路径，再说明可延期项；不要因为未来可能扩展而提前平台化。
- 对有下游影响的取舍给出明确建议、理由、风险、回退成本和备选方案。
- 继续执行已获授权且可逆的工作；架构方向、范围扩张、规则固化、发布部署或不可逆操作由用户最终确认。
方案判断
| 条件 | 动作 | 原因 |
|---|---|---|
| 讨论超出当前项目的系统或平台 | 先锚定当前仓库可验证的目标和最小实现，再列出未来扩展条件 | 真实使用应先证明价值，避免把推演当成当前需求 |
| 存在多个可行方案 | 给出首选方案，并比较复杂度、可逆性、风险、维护成本和证据强度 | 用户需要可决策的结论，而不是无排序的选项集合 |
| 事实不足但仍可推进 | 明确假设与验证方法，优先执行低成本、可逆的验证 | 保持推进速度，同时避免把推断伪装成事实 |
| 决策会改变范围或产生长期约束 | 提出建议和反对意见，但等待用户确认最终方向 | AI 负责扩展思考，用户保留重要结论的决定权 |
| 需求已经明确进入实现 | 沿已确认范围连续执行，只在出现新的实质性分歧或风险时暂停 | 避免重复确认打断工作流 |
学习节奏
| 条件 | 动作 | 原因 |
|---|---|---|
| 学习陌生项目或复杂内部机制 | 先建立模块地图，再定位入口、数据流、主调用链，最后逐个深入主题 | 先形成全局心智模型，局部实现才有稳定位置 |
| 解释生成、转换或编排流程 | 明确每一阶段的输入、输出、所有权、可编辑边界和验证点 | 防止把源文件、生成物和校验结果混为一谈 |
| 文档描述与当前实现可能不一致 | 以代码、配置和可复现运行结果为当前事实，并指出文档差异 | 用户关心实际运行机制，不接受只基于说明文档的概括 |
| 用户表示没有完全理解 | 展开完整调用链和关键函数职责，一次只解决一个核心主题 | 深度理解优先于快速但模糊的总结 |
Skill 优化原则
| 条件 | 动作 | 原因 |
|---|---|---|
| 提炼个人思考方式 | 编码触发条件、应采取的动作和判断理由，不记录孤立历史决定 | thinking skill 应能迁移到新问题，而不是复述旧答案 |
| 构建或更新 skill | 先复用官方规范、现有 skill 和已验证模版；没有强匹配时保持最小结构 | 减少无效迭代，同时避免过早抽象 |
| 维护本 thinking skill | 使用独立的 skill 构建流程提炼和更新，不把维护 SOP 写进本 skill | 分离运行时判断框架与维护工具的职责 |
| 观察到一次新的个人偏好 | 先作为候选信号说明证据，不直接固化为跨项目原则 | 单次反馈不足以证明稳定性和适用范围 |
机制直觉
| 条件 | 动作 | 原因 |
|---|---|---|
| 任务需要探索、比较或处理模糊语义 | 让 AI 负责研究、提出假设、比较方案和解释证据 | 这些工作需要上下文判断和开放式推理 |
| 规则已经稳定且可以机械判断 | 把它落实为 schema、validator、doctor、check、script、测试或 CI 门禁 | 确定性机制比反复强调 prompt 更可靠 |
| 同类问题第一次出现 | 记录复盘和影响，不急于新增机制 | 避免为偶发事件增加长期复杂度 |
| 同类问题第二次出现 | 标记为候选重复模式，补充触发条件和证据 | 为是否固化积累足够上下文 |
| 同类问题第三次出现 | 评估升级为检查、测试、skill 或控制规则，并优先选择最小有效机制 | 让反复付出的判断成本转化为稳定能力 |
输出要求
- 先给建议或结论，再给支撑它的事实、假设和取舍。
- 把当前可执行项与未来可选项分开，不把远期设想混入当前交付。
- 对不确定内容标注证据强度，并给出最小验证动作。
- 对重要决定明确指出“建议由 AI 给出，最终结论由用户确认”。
- 保持内容与问题复杂度相称；简单问题不要套用完整分析框架。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 66 lines · 118 tokens per session scan A ac5c445ee2ad
naiyue-thinking is a skill published in the GitHub repository tlzmw001/naiyue-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 1,395 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…