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 decision-researchgit 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/decision-research)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/decision-research"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/decision-research/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/decision-research"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/decision-research.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 | $0.00335 | $0.02927 |
| Opus 5 | $0.00168 | $0.01463 |
| Sonnet 5 | $0.00067 | $0.00585 |
| Haiku 4.5 | $0.00034 | $0.00293 |
Grade A, and why
decision-research 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
决策调研 Skill（decision-research）
中文速查
- 中文名：决策调研 / 决策驱动调研
- 英文稳定名：
decision-research - 分类：研究学习 / 认知与协作
- 你可以这样叫我：
帮我调研、有没有现成方案、这个怎么接、技术上可行吗、帮我选一个、业界怎么做、这个方向对不对、应该怎么定位 - 适合：面对一个具体决策需要找信息——单次、即时、调研完直接进入下一步；也可消费 research-topic-compiler 产出的 Candidate Backlog / Cross-Session Handoff 来给最终推荐
- 不适合：问题还没想清楚（先用 ai-calibration L4-fuzzy 脑暴）；需要系统学习或沉淀知识库（用 research-topic-compiler）
- 与 research-topic-compiler 的一句话区别：调研是为了做一个决定（decision-research）vs 调研是为了建立对某个领域的认知（research-topic-compiler）
核心原则
调研是服务于决策的，不是服务于信息完整性的。
本 Skill 拥有最终推荐、排除理由、置信度和颠覆条件，也拥有当前 decision_question 内为选择服务的有界取证与反证搜索；不拥有开放式知识工程，不执行已经通过 Research Return Request 明确交给 Research 的证据 gap，也不拥有方案设计、Critic clearance 或 readiness 审批。
去掉所有图表和术语，剩下的结论能不能让用户敢于立刻做决定？如果不能，问题出在信息太浅，或者决策问题本身还没定义清楚。
调研的骨架：
研究框定 → 决策锚定 → 假设显式化 → 竞争假设枚举 → 反对证据搜索 → 三角收敛 → 有立场结论
Startup Gate
搜索前先完成四件事。详细规则按需读取 references/research-framing-gate.md、references/research-map-template.md 和 references/mode-routing.md。
- 判断输入是问题、现象还是解法，并把它提升成一句
decision_question。 - 判断研究层级和类型：技术选型、平台接入、可行性、产品策略、商业模型、竞品判断或行业格局。
- 显式列出当前假设、已知事实、暗知识缺口和停止条件。
- 输出 Research Map；如果来自
research-topic-compiler的 Candidate Backlog，先纳入候选、权重和已排除项。
推荐确认句：
你的问题属于 [类型]，层级在 [X]。我理解核心决策是 [Y]。调研结束时需要能判断 [停止条件]。这个理解对吗？
如果问题还没定义清楚，先转 ai-collaboration-calibration。如果目标是长期知识沉淀或候选池，转 research-topic-compiler。
Mode Routing
按问题类型只加载必要资产：
| Mode | Use When | Read |
|---|---|---|
technical-selection |
选库、框架、模型、服务或实现路径 | references/modes/technical-selection.md |
platform-integration |
接 API、Bot、平台、SDK、开放能力 | references/modes/platform-integration.md |
product-strategy |
产品定位、用户群、差异化、方向判断 | references/modes/product-strategy.md |
business-model |
定价、版本分层、商业包装、升级触发 | references/modes/business-model.md |
competitive-decision |
竞品证据已经收集完，需要做最终判断 | references/channel-guide.md + references/conclusion-template.md |
当用户明确需要“持续推进一个决策”“保存状态”“下一轮继续”或“更新结论”时读取 references/decision-loop-contract.md。Loop 只围绕同一个 decision_question 迭代；如果目标变成研究知识库，转 research-topic-compiler。
What ships with it
17 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.
- evals/evals.json 13 KB
- references/assumption-ledger.md 2.1 KB
- references/channel-guide.md 4.5 KB
- references/conclusion-template.md 2.8 KB
- references/core-loop-decision-handoff.md 3.7 KB
- references/decision-loop-contract.md 5.1 KB
- references/mode-routing.md 2.0 KB
- references/modes/business-model.md 906 B
- references/modes/platform-integration.md 1.1 KB
- references/modes/product-strategy.md 1.0 KB
- references/modes/technical-selection.md 1004 B
- references/research-framing-gate.md 3.4 KB
- references/research-map-template.md 2.3 KB
- references/research-rules.md 4.7 KB
- references/scope-drift-checkpoint.md 2.0 KB
- references/top-down-product-mode.md 3.1 KB
- scripts/check_decision_report.py 1.4 KB runs code
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 · 175 lines · 335 tokens per session scan A cb78ee912ee4
decision-research is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 12d ago), licensed MIT. It adds 335 tokens to every session and 2,927 once invoked, about $0.0017 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…