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 grill-megit 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/grill-me)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/grill-me"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/grill-me/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/grill-me"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/grill-me.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 | $0.00173 | $0.01466 |
| Opus 5 | $0.00086 | $0.00733 |
| Sonnet 5 | $0.00035 | $0.00293 |
| Haiku 4.5 | $0.00017 | $0.00147 |
Grade A, and why
grill-me 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
方案拷问（grill-me）
中文速查
- 中文名：方案拷问 / 压力测试
- 英文稳定名：
grill-me - 你可以这样叫我：
拷问我的方案、压力测试这个设计、帮我问 hard questions、这个方案哪里会翻车、grill me - 适合：已有方案、架构、计划或决策，且问题目标基本确认，需要按依赖、假设、分支和失败模式逐个追问
- 不适合：直接写最终方案、泛泛总结文档、没有互动空间的一次性输出；问题还没定义清楚时改用
ai-collaboration-calibration；标准 PRD readiness 评审改用prd-review
Overview
使用这个 Skill 对方案或设计做聚焦访谈式压力测试。目标是达成共同理解，而不是抛出一长串互不相干的问题。
本 Skill 是 Critic：拥有 challenge、严重度、推荐答案/假设、关闭标准、唯一 return owner 和复查；不拥有完整研究、最终选择、方案重写或 readiness/发布审批。
Boundary
先判断被拷问对象是否已经成形：
- 问题、目标或成功标准还不清楚：转交
ai-collaboration-calibration，先校准问题定义。 - 已有具体方案、架构、计划、产品决策或 PRD 背后的解法：留在
grill-me做压力测试。 - 用户要判断“这份 PRD 是否可开发、可测试、可交付”：转交
prd-review。 - 用户要判断“这份 PRD 背后的方案是否会失败”：留在
grill-me。
grill-me 不输出 Implementation-Plan Readiness 结论；这个 readiness verdict 由 prd-review 负责。
Workflow
- 用一句话复述正在被拷问的方案或设计。
- 找出主要决策分支、依赖、隐含假设和可能失败模式。
- 一次只问一个问题；除非答案能从本地代码或文档中直接发现，否则等待用户回答后再继续。
- 每个问题都要给出你的推荐答案或当前假设，让用户可以接受、否定或修正。
- 如果问题可以通过读取代码库、PRD、ADR 或本地文档回答，先去查证，不要把可查问题丢给用户。
- 按依赖顺序解决分支；上游约束还不稳定时，不要跳到下游细节。
- 当拷问暂停或结束时，汇总结论、被否掉的选项、仍未解决的问题和计划变化。
Critic Handoff
需要跨 Skill 返回 blocker 或复查 delta 时，读取 references/critic-handoff-contract.md。
- 必须引用版本化 artifact，一次只输出一个 Challenge 和一个 primary return owner；finding 涉及多节点时选择最早因果缺口。
- 证据 gap 返回
research-topic-compiler，选择标准/排除逻辑返回decision-research，scope/flow/state/recovery 返回brainstorming，本地权限、预算或不可逆取舍进入 Human Gate。 - 只输出 Challenge/Critic Handoff，不替目标节点生成完整 Evidence、Decision、Design Spec、PRD 或实现计划。
- delta 返回后只复查原 challenge；无 blocker/high 时可输出
clear-for-owner-confirmation，但这不是任何 readiness verdict。 - 同一 challenge 完成两轮回流后仍未关闭或缩小时，停止自动回流并进入 Human Gate。
Context Intake
优先使用已有材料：PRD、issue、代码、文档、ADR、图、日志和之前的对话。只问那些会改变真实决策的缺失信息。
开始前先确认或推断三件事：
- 被压测的方案是什么。
- 这个方案针对的问题是否已经被确认。
- 用户想压测的是方案可行性、取舍、失败模式，还是 PRD artifact 质量。
如果第 2 点为“否 / 不清楚”，先建议进入 ai-collaboration-calibration。如果第 3 点是 PRD artifact 质量，转 prd-review。
Output
过程输出是一问一答，并且每个问题都附带推荐答案。结束输出是一份简洁决策记录：
- 已确认决策
- 被否掉的选项及原因
- 仍未解决的问题
- 推荐下一步
Definition of Done
What ships with it
4 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 · 107 lines · 173 tokens per session scan A 8182b132f5ab
grill-me is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 12d ago), licensed MIT. It adds 173 tokens to every session and 1,466 once invoked, about $0.0009 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…