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 agentmods add skills/konglong87/superpm/pm-interviewnpx skills add konglong87/superPM --skill pm-interviewgit clone --depth 1 https://github.com/konglong87/superPMWrote 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/konglong87/superpm/pm-interview)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-interview"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-interview.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.01881 |
| Opus 5 | $0.00037 | $0.00941 |
| Sonnet 5 | $0.00015 | $0.00376 |
| Haiku 4.5 | $0.00007 | $0.00188 |
Grade A, and why
pm-interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
# 创建需求调研目录
mkdir -p docs/01-需求调研
if [ -f "docs/01-需求调研/需求调研报告.md" ]; then
echo "✅ 需求调研报告 - 已找到(可复用假设与目标用户)"
else
echo "⏳ 需求调研报告 - 未找到(可选,缺失时由本技能快速采集)"
fi
跨 Agent 交互规则
当流程要求与用户交互时:
- 如果当前环境支持 AskUserQuestion,使用 AskUserQuestion(最佳体验)。
- 如果当前环境不支持 AskUserQuestion,必须用普通聊天消息提出同样问题。
- 一次只问一个问题。
- 提问后必须停止当前回合,等待用户回答(STOP and WAIT)。
- 不得在用户回答前生成文档、写入 docs。
- 已有 docs 文件不能替代本轮用户回答。
适用场景
- 用户说"用户访谈""访谈提纲""用户调研方案""想找用户聊聊""定性研究"
- 与
pm-demand区分:pm-demand 偏案头/二手调研;本技能偏一手定性研究(访谈设计与执行)。
执行流程
步骤 1: 明确访谈目标与假设(主 agent - 用户交互)
使用 AskUserQuestion 询问:
🎯 访谈目标
这次访谈主要想搞清楚什么?
A) 验证需求假设(功能是否真被需要) B) 探索用户痛点与场景(开放式发现) C) 评估产品体验(可用性/满意度) D) 理解决策与付费(选型/付费动机)
你想验证/探索的核心假设是?(一句话)
记录到变量 INTERVIEW_GOAL 与 HYPOTHESIS。
步骤 2: 确定访谈对象与样本(主 agent)
结合需求调研报告(如有)提取目标用户画像,使用 AskUserQuestion 确认:
👥 访谈对象
A) 沿用需求调研报告的目标用户分层 B) 我手动指定人群 C) 聚焦某一极端/核心用户群
样本量:建议 5-8 人/每细分(饱和即止);周期:{周}
记录 SEGMENTS 与 SAMPLE_PLAN。
步骤 3: 设计访谈提纲(主 agent + 可选 subagent)
按阶段生成提纲,默认结构:
- 暖场(建立信任,背景了解)
- 行为与场景(真实使用/替代方案)
- 痛点与动机(当前如何解决问题、痛点强度)
- 需求与期望(对解决方案的期望、付费意愿)
- 收尾(开放补充、是否愿意后续回访)
使用 Agent 工具(可选,针对复杂主题)派发 subagent 生成分群提纲:
Tool: Task
Parameters:
subagent_type: "general-purpose"
description: "访谈提纲生成"
prompt: |
你是用户研究专家。请基于以下信息设计一份用户访谈提纲。
目标:{INTERVIEW_GOAL}
核心假设:{HYPOTHESIS}
对象分层:{SEGMENTS}
要求:开放式问题为主、避免引导性提问、每阶段 3-5 题、标注追问点。
输出 Markdown 提纲。
主 agent 整合并定稿。
步骤 4: 招募与执行指引(主 agent)
生成:
- 招募话术 / 筛选问卷(含准入/排除标准)
- 执行指引:提问技巧(追问"为什么""能举个例子吗")、避免 Leading、录音与知情同意、时间控制(45-60 分钟)
- 记录模板:逐场要点 + 引用原话
步骤 5: 分析与产出(主 agent)
使用 Write 工具生成 docs/01-需求调研/用户访谈方案.md:
# {产品名称} 用户访谈方案
## 一、访谈目标与假设
- 目标: {INTERVIEW_GOAL}
- 核心假设: {HYPOTHESIS}
- 待回答的关键问题: {列表}
## 二、对象与样本
| 分层 | 特征 | 样本量 | 招募渠道 |
|------|------|-------|---------|
| {层1} | {特征} | {n} | {渠道} |
## 三、访谈提纲(按阶段)
### 阶段1 暖场
1. {问题}
### 阶段2 行为与场景
1. {问题}(追问:...)
...
## 四、招募与执行
- 招募话术: {话术}
- 执行指引: {要点}
- 记录模板: {模板}
## 五、分析方法
- 归纳编码(开放→主题)
- 假设验证矩阵(支持/反驳/需补充)
- 输出物: 洞察报告 + 用户原话引用
## 六、下一步建议
1. /pm-demand - 整合访谈洞察进入需求调研
2. /pm-clarify - 细化高价值需求
3. /pm-priority - 将洞察转优先级
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.
- 4d ago First seen · 219 lines · 75 tokens per session scan A 22f39bcedb61
pm-interview is a skill published in the GitHub repository konglong87/superPM (60 stars, last pushed 21d ago), licensed MIT. It adds 75 tokens to every session and 1,881 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
deepsafe-scan
Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced…
douyin-upload-mcp-skill
通过抖音创作者平台(creator.douyin.com)发布视频和图文内容。首选调用 MCP 工具完成操作,MCP 无法满足时可运行 Skill 脚本兜底。禁止自行启动外部浏览器访问抖音。.
team-tasks
Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via…
multi-search
智能多引擎搜索,自动检测网络环境并按优先级切换:DuckDuckGo -> Tavily -> Bing API -> Bing爬虫。支持自动配额管理和网络缓存。Invoke when user needs web search with automatic engine selection and network adaptation.
meeting-note-summarizer
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
daily-standup-journal
Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.