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 Lambenthan/mixed-methods-instrument-design --skill interview-guide-designgit clone --depth 1 https://github.com/Lambenthan/mixed-methods-instrument-designWrote 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/lambenthan/mixed-methods-instrument-design/interview-guide-design)<a href="https://agentmods.dev/skills/lambenthan/mixed-methods-instrument-design/interview-guide-design"><img src="https://agentmods.dev/badge/skills/lambenthan/mixed-methods-instrument-design/interview-guide-design/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/lambenthan/mixed-methods-instrument-design/interview-guide-design"><img src="https://agentmods.dev/badge/skills/lambenthan/mixed-methods-instrument-design/interview-guide-design.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 | $0.00451 | $0.06449 |
| Opus 5 | $0.00226 | $0.03224 |
| Sonnet 5 | $0.00090 | $0.01290 |
| Haiku 4.5 | $0.00045 | $0.00645 |
Grade A, and why
interview-guide-design 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 8d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
质性访谈提纲设计 / Research-Grade Interview Guide Design
这个 skill 把"研究思路"变成"经得起方法论审稿的质性访谈提纲"。它的立场不是"快速生成一串看起来像访谈题的问题"，而是每一道访谈问题都能回答"它服务哪个研究问题、能不能挖到深度、会不会诱导受访者、依据是什么"。
它是 questionnaire-design（量化问卷）的质性姊妹 skill。两者方法论不同、不可互换：
questionnaire-design（量化） |
本 skill（质性） | |
|---|---|---|
| 出发点 | 构念 → 量表题项 | 研究问题 → 访谈问题 |
| 挂靠什么 | 成熟量表 | 成熟访谈框架（IPR / Yin 协议）+ 同主题已发表提纲 |
| 质量标准 | 信度、效度（α、AVE…） | 可信度四准则（credibility/transferability/dependability/confirmability） |
| 出题红线 | 11 条量表红线 | 质性提问红线（诱导/双重负载/封闭化/术语/"为什么"质问/抽象/社会赞许） |
| 效度/偏差控制 | 注意力检测、CMB 程序控制 | 三角验证、成员核验、反身性与立场性、搜寻负向案例 |
| 预试 | 认知访谈 + 小试点 | IPR 专家 close reading + pilot + 饱和评估 |
适用：中英双语、质性访谈提纲（半结构化 / 结构化 / 关键知情人 / 精英 / 案例研究访谈）。不做量化问卷、量表（走 questionnaire-design）。
启动时先做的两件事
第一，亮明边界声明（每份产出开头都要有）。 访谈提纲设计只管数据收集工具这一侧——它能让提纲问对问题、挖到深度、降低诱导与偏差、为后续编码与三角验证铺好路；但它不替你抽样、不替你做编码/主题分析、不保证结论可推广到其他案例或总体。在质性里"可推广"叫 transferability，靠的是厚描述、目的性抽样与跨案例分析，不是靠一份提纲（详见 references/trustworthiness-and-sampling.md）。还要讲清：这份提纲是案例的数据收集工具，不是案例研究本身——案例的可信度还要靠多源证据三角验证（Yin）。本 skill 设计的是工具，不替代伦理审查程序与个人信息合规（见 references/trustworthiness-and-sampling.md §4）。不写这条，用户会误以为"好提纲=好研究"。
第二，确认五个关键参数（用户没说就用默认值并在产出里点明）：
- 语言：中文 / 英文 / 中英双语（默认问什么语言答什么）
- 研究问题（RQ）与理论视角：要回答哪几个研究问题？有没有理论命题（proposition）？——这是出题的起点，等价于量化里的构念，没有它无法开工。
- 案例 / 研究取向：是案例研究吗？走 Yin（实证、命题驱动、结构）还是 Stake/Merriam（解释、涌现、灵活）？案例的边界（一个县/一家机构/一个项目）是什么？（见
references/case-study-traditions.md） - 访谈对象 + 进入路径：关键知情人 / 精英（领导、管理者、专家）还是普通参与者？是否涉及脆弱/权力不对等人群？怎么进得去（引荐人 / 组织授权）？这决定敬语、提问姿态、能问什么、伦理强度（精英访谈与 access 规范见
references/trustworthiness-and-sampling.md§3.0、§3、§4） - 结构化程度 + 后续分析：结构化 / 半结构化（默认半结构化，质性最常用）；后续要做主题分析、案例分析还是扎根理论？——分析目的会反过来影响出题（带着分析目的设计工具）
- 访谈方式：线下 / 视频 / 电话（默认线下）——影响录音同意话术与非言语探测，见
references/modality-considerations.md
如果用户只给了一句模糊的"帮我做个关于 XX 的访谈提纲"，先把研究问题和访谈对象问清楚再动手——研究问题不清，后面全是返工。
核心工作流：从研究问题到访谈提纲
整个流程整合 Castillo-Montoya（2016）的访谈提纲精炼框架（IPR 四阶段）与 Yin 的案例研究协议。本 skill 做第 1–7 步（对齐→检索锚定→出题→组装→自检→可信度与三角验证设计→产出），交付含研究者版 + 后续验证清单；其后真正落地的专家近读、pilot、饱和、抽样与编码（IPR Phase 3/4）由用户执行，本 skill 只写成后续清单——不要假装替用户跑了访谈或编码。
What ships with it
11 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.
- assets/interview-guide-docx-template.js 6.5 KB runs code
- LICENSE 1.0 KB
- references/analysis-readiness.md 3.8 KB
- references/case-study-traditions.md 5.7 KB
- references/chinese-conventions.md 7.4 KB
- references/modality-considerations.md 2.3 KB
- references/protocol-structure-and-refinement.md 4.8 KB
- references/question-writing-and-probes.md 5.9 KB
- references/sources.md 7.2 KB
- references/trustworthiness-and-sampling.md 12 KB
- references/word-output.md 3.8 KB
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.
- 8d ago First seen · 179 lines · 451 tokens per session scan A 2ec54ed0ec9c
interview-guide-design is a skill published in the GitHub repository Lambenthan/mixed-methods-instrument-design (4 stars, last pushed 26d ago), licensed MIT. It adds 451 tokens to every session and 6,449 once invoked, about $0.0023 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.