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 PANGKAIFENG/ai-product-manager-skills --skill complex-explorationgit clone --depth 1 https://github.com/PANGKAIFENG/ai-product-manager-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/pangkaifeng/ai-product-manager-skills/complex-exploration)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/complex-exploration"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/complex-exploration/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/pangkaifeng/ai-product-manager-skills/complex-exploration"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/complex-exploration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00160 | $0.02698 |
| Opus 5 | $0.00080 | $0.01349 |
| Sonnet 5 | $0.00032 | $0.00540 |
| Haiku 4.5 | $0.00016 | $0.00270 |
Grade A, and why
complex-exploration 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
复杂探索资产化（complex-exploration）
中文速查
- 中文名：复杂探索资产化 / 复杂探索协作
- 英文稳定名：
complex-exploration - 分类：认知与协作
- 状态：
active - 你可以这样叫我：
先不要直接写方案，帮我做复杂探索、这个 Roadmap 问题是不是问窄了、这次探索反复很多，帮我复盘沉淀、把这次复杂任务沉淀成可复用资产、进入 Complex Exploration - 适合：复杂、不确定、多轮迭代的产品策略、商业化、Roadmap、竞品定位、复杂 PRD 前置探索、项目复盘和方法论沉淀
- 不适合：简单执行、润色、翻译、摘要；单点问题定义校准用
ai-collaboration-calibration；已有方案压力测试用grill-me；系统专题研究用research-topic-compiler
核心原则：不要在问题层级、隐含假设和探索框架未稳定前直接输出完整方案。复杂探索的目标不是一次答完，而是让探索过程留下可复用的判断能力。
Boundary
先判断用户当前阶段，再选择是否使用本 Skill：
| 用户状态 | 处理 |
|---|---|
| 只是模糊地说不清问题，尚无复杂探索任务 | 转 ai-collaboration-calibration，先校准问题定义 |
| 已经有复杂任务，需要定义任务类型、重构问题、规划探索路径 | 使用 complex-exploration |
| 问题基本成立，只需要比较 2-3 个落地方案 | 转 brainstorming |
| 需要系统收集资料、建立证据矩阵或候选池 | 转 research-topic-compiler，本 Skill 可提供研究 brief |
| 已有具体方案，要连续追问失败模式 | 转 grill-me |
| 已有重复 AI 工作，要判断资产层级 | 转 ai-work-assetization-diagnoser |
如果用户明确说“直接做，不要校准”，可以执行用户请求，但要用一句话标注你跳过了复杂探索门。
Operating Modes
按用户输入选择一个主模式，不要机械跑满所有模板。
模式选择不清时先读取 references/mode-selection.md。
| Mode | Use When | Primary Output |
|---|---|---|
| Quick Mode | 用户刚提出复杂请求，需要快速判断是否应直接执行 | 快速判断：任务类型、是否过窄、真正问题、下一步 |
| Deep Mode | 正式启动复杂策略、Roadmap、定价、定位或复杂 PRD 前置探索 | 复杂探索任务定义：类型、假设、问题重构、框架、调研和中间产物 |
| Review Mode | 已经有多轮讨论、多个版本或项目过程，需要复盘探索质量 | 过程复盘：问题升级路径、关键转折、有价值反复、低价值返工 |
| Asset Mode | 最终成果已完成，希望沉淀方法论、模板或下次协作规则 | 五类资产沉淀：认知、结构、方法论、工具、影响力资产 |
详细方法论依据和失败模式见 references/exploration-method.md。需要格式化输出时读取 references/output-templates.md。
Task Type Taxonomy
复杂请求启动时先判断任务类型。一个任务可以有主类型、辅类型和隐含类型。
| 类型 | 定义 | Skill 行为 |
|---|---|---|
| 执行型 | 目标明确，只需要完成具体产出 | 可以直接执行，确认输出格式即可 |
| 方案型 | 存在多个路径，需要比较取舍 | 输出 2-3 个路径和取舍，不直接写完整执行清单 |
| 定位型 | 需要定义对象边界、差异和心智 | 先输出核心判断、边界、反例和待验证假设 |
| 系统型 | 涉及多个对象、模块、角色、流程关系 | 先画对象关系、分层、闭环和关键取舍 |
| 策略型 | 涉及阶段目标、资源投入、商业化、竞争优势 | 先明确真正管理对象，再输出路径和节奏 |
| 方法论型 | 需要从过程沉淀可复用规律 | 输出复盘框架、抽象方法、模板和资产清单 |
| 认知校准型 | 需要判断原问题是否问错、假设是否成立 | 直接挑战假设，指出盲区，不急于产出方案 |
启动输出必须包含：
## 任务类型判断
- 主类型：
- 辅类型：
- 隐含类型：
- 是否建议直接执行：
- 不建议直接做什么：
- 下一步建议：
What ships with it
5 files 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 · 186 lines · 160 tokens per session scan A 71a386f7ae9b
complex-exploration is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 160 tokens to every session and 2,698 once invoked, about $0.0008 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
sequential-think
Multi-step reasoning engine for complex analysis and systematic problem solving. Use when: (1) Complex debugging scenarios with multiple layers, (2) Architectural analysis and system design, (3) Problems requiring hypothesis testing and validation, (4) Multi-component failure investigation, (5) Performance bottleneck…