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 Gingiris-1031/gingiris-skills --skill gingiris-user-interviewgit clone --depth 1 https://github.com/Gingiris-1031/gingiris-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/gingiris-1031/gingiris-skills/gingiris-user-interview)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gingiris-user-interview"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gingiris-user-interview/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/gingiris-1031/gingiris-skills/gingiris-user-interview"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gingiris-user-interview.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 | $0.00369 | $0.04629 |
| Opus 5.5 | $0.00148 | $0.01852 |
| Sonnet 5.5 | $0.00074 | $0.00926 |
| Haiku 4.5 | $0.00037 | $0.00463 |
Grade A, and why
gingiris-user-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 6d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 2C 产品的渠道调整
本 skill 默认 dev / B2B 渠道。2C 消费品 / 教育 / 应用：获客主战场是 垂类社区 + 短视频 + 垂直 KOL，按地区公开数据选第一平台（如印尼/泰国短视频已反超 Facebook）。KOL 优先 nano / micro 垂类——粉丝越多互动率越低，micro > mega 性价比更高。完整 2C 渠道数据库 + 公开来源见 → gingiris-seo-geo/references/2c-adaptation.md。
用户访谈与冷启动运营实战手册
播客一手案例与引用边界：references/podcast-evidence.md。
🌍 Language / 语言: 中文 | Interview Guide | Cold-Start Ops
核心原则
"产品的 founder，在刚开始的前半年都会密集的做大量的用户访谈。像 HeyGen 就是半年，founder 自己做了 937 场；Wisperflow 和 Higgsfield 都做了 500 场以上——就是不断做访谈，不断改。" —— 生姜iris
关键洞察：用户访谈不是调研工具，是 PMF 发现引擎。访谈频率与产品成功率正相关。
Token Top10 访谈法（2026 招牌方法）
把访谈从"调研动作"变成"日常运营循环"的最短路径，已在多个 AI Agent 项目全线复用：
- 后台按 token 消耗 / 用量拉 Top10 用户 list（每周刷新）
- 约共享屏幕访谈，必须录屏——看真实操作 > 听口述
- Transcript 喂 AI，自动提取 feature request / bug 直接进 Linear（或任意 issue 工具）
- 次日回访：告知"你提的 X 已修/已排期"——反馈闭环本身就是留存杠杆
- 节奏：每天至少 2 场；访谈后截 5-10 分钟关键片段直接给产研
配套动作：
- 新访谈员先 mock interview + 全程录屏 + 复盘 highlight，再上真实用户
- KOL 访谈二合一：合作 YouTuber 顺便做用户访谈 + 可用性测试，一次合作拿两份价值；视频访谈 20-30 分钟 ROI 最高
- 访谈资产化：一场付费用户访谈可同时产出功能需求 + SEO 素材 + reseller 线索三件套
邀约触达节奏（2026 更新）
- 1/3/7/14 天四次触达：Day 1 首发 → Day 3 → Day 7 → Day 14 各跟进一次
- 双通道：邮件模板 + 邮箱反查 LinkedIn 私信；邮件无回复转 LinkedIn 补一轮
- 话术用宽泛理由（"团队早期想做用户访谈"），不暴露真实筛选原因，避免用户带着预设表演
标杆锚点
Wisprflow：launch 前人工 onboard 前 500 名用户、逐个视频访谈，用积累的势能带 launch；HuggingFace：scale up 前 8 个月调研 + 500 场用户访谈。
2026-07 增补（播客一手提炼）：
- 据转述（AFFiNE 前 COO 口径）：Gamma / Notion / HeyGen 均在半年内做了约 1,000 场用户访谈，"用户提到的不好的点就真的去解"。
- Gamma / HeyGen / Lovable 等成功产品的共同路径：半年 500-1,000 场访谈打磨产品细节，才有资格谈增长——"大量的人忽视了前面这半年到一年脏活累活的过程"。
- 反例（匿名项目，reported）：跳过访谈打磨直接烧钱投放，单个注册成本高达几十美金、单个付费用户成本几百美金——"没有逻辑，但有钱"。
用户访谈执行框架（5步）
Step 1：确定目标与筛选用户
用户优先级：
| 优先级 | 用户类型 | 价值 |
|---|---|---|
| P0 | 付费用户 | 已验证付费意愿，最高价值 |
| P0 | 高频活跃用户 | 深度了解产品，反馈最有效 |
| P1 | 竞品用户 | 提供竞争视角 |
| P1 | 流失用户 | 暴露产品真实问题 |
| P2 | 注册未付费用户 | 转化障碍洞察 |
Step 2：邀约与排期
跟进节奏：Day 1 → Day 3 → Day 7 → Day 10（全渠道：LinkedIn/Email/Telegram/Discord）
What ships with it
9 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.
- 6d ago Changed · +14 lines 8105cf0d2a17
- 1mo ago Changed · +2 lines 2837d7f9f84a
- 1mo ago First seen · 311 lines · 369 tokens per session scan A b425e60651c4
gingiris-user-interview is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (86 stars, last pushed 6d ago), licensed MIT. It adds 369 tokens to every session and 4,629 once invoked, about $0.0015 per session on Opus 5.5. 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
pmf-advisor
You are a product-market fit advisor with a mandate to challenge, not validate. Your default posture is skepticism. You have seen founders mistake good marketing for PMF, mistake a vocal minority for the market, and mistake retention of the wrong customers for product success. You apply rigorous frameworks and refuse…
user-research
User personas, customer journey maps, interview guides, usability testing, and card sorting. Use when building user understanding, mapping customer experiences, planning user research sessions, or defining Jobs-to-Be-Done.
first-customer-finder
Find evidence-backed potential first customers, beta users, or design partners from public demand signals. Use for product-specific prospect research, qualified shortlists, source-grounded outreach drafts, and follow-up searches refined by the user's feedback and local prospect history. Does not send outreach…
jtbd-extractor
Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish. Use when: extract jobs, jtbd analysis, jobs to be done, what job is the user hiring, underlying user needs.
apply-product-market-fit-test
Use when deciding whether a startup has found product-market fit before investing in growth, sales, or scaling — survey active users with Sean Ellis's "how would you feel if you could no longer use this product" question and treat 40%+ answering "very disappointed" as the threshold, rather than relying on founder…
assumption-mapper
Surfaces the assumptions a product or strategy depends on, classifies them by criticality and evidence quality, and produces a prioritized test plan. Use when: assumption mapping, identify assumptions, what could go wrong, leap-of-faith assumptions, riskiest assumption test, RAT, assumption inventory, validate before…