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 questionnaire-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/questionnaire-design)<a href="https://agentmods.dev/skills/lambenthan/mixed-methods-instrument-design/questionnaire-design"><img src="https://agentmods.dev/badge/skills/lambenthan/mixed-methods-instrument-design/questionnaire-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/questionnaire-design"><img src="https://agentmods.dev/badge/skills/lambenthan/mixed-methods-instrument-design/questionnaire-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 | $0.00192 | $0.03052 |
| Opus 5 | $0.00096 | $0.01526 |
| Sonnet 5 | $0.00038 | $0.00610 |
| Haiku 4.5 | $0.00019 | $0.00305 |
Grade A, and why
questionnaire-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 9d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
研究级问卷设计 / Research-Grade Questionnaire Design
把研究问题转成可理解、可回答、可执行、可追溯并为分析做好准备的调查工具。问卷质量同时受测量与代表性影响;写出顺口的题面只解决其中一部分。
边界与分类
每份产出先声明:本管线设计问卷、变量字典、测试与验证计划,不替代抽样实施、伦理审批、正式预测试、现场质量控制、量表验证或统计推断。
先给工具分类,后续规则不得混用:
- 事实/行为调查:关注定义、回忆期、报告误差、覆盖与无应答。
- 态度/感知题组:可包含多个项目,但不因项目相似就自动构成量表。
- 潜变量量表:需要明确构念、内容覆盖、内部结构、可靠性及与其他变量的关系证据。
- 知识测验/能力测验:涉及难度、区分、猜测、公平性和可能的题目安全;必要时采用测试学专门规范。
- 筛查/诊断或决策工具:阈值会产生实际后果,必须使用领域监管与决策准确性规范;本通用管线不能自行设定临界值。
- 登记表/服务评价表:可服务运营描述,不自动支持总体推断或潜变量解释。
“问卷”“量表”“测验”“指数”不得互称。工具的用途、目标总体、分析单位和预期推论决定证据要求。
启动参数
开始写题前确认并记录:
- 研究目的、RQ、预期使用结果的决定或推论。
- 目标总体、抽样框、纳入/排除、回答者、观察单位和分析单位。
- 构念/变量的操作性定义、边界、回忆期和参照对象。
- 事实题、题组、潜变量量表、测验或筛查工具的类型。
- 调查模式、设备、语言、场景、访问渠道和预计负担。
- 计划分析、比较组、纵向/横向设计和所需精度。
- 敏感性、伦理审批、知情同意、隐私、许可和版权条件。
- 既有工具是否存在、是否允许复制/翻译/改编及版本状态。
信息缺失但不改变工具类型时可采用标注为“暂定”的值;会改变总体、构念、模式、伦理或推论时,先确认。
出题前硬闸
进入题项起草前建立可见待办并完成:
- 用途判定:说明为何问卷适合该 RQ,哪些 RQ 仍需访谈、记录或观察。
- 总调查误差草图:标出构念/测量、覆盖、抽样、无应答、处理与调整风险;见
references/foundations-and-sources.md。 - RQ—变量—构念映射:每个拟收集字段有分析用途,无孤儿题。
- 来源检索:Web 检索原始量表论文、官方工具、目标人群/语言验证研究和许可;完整执行
references/foundations-and-sources.md。 - 证据核验:核对原题、选项、回忆期、计分、适用人群、版本与许可;二手文章只用于发现来源。
- 状态标记:逐题标为
validated、adapted、official或new;改动后的工具不得继承原效度声明。 - 分析预演:说明每题形成什么变量、如何进入计划分析,无法使用的题删除。
任何原工具全文不可得、许可不明、计分规则不明或版本冲突,都要标“待核”,不能补写看似合理的内容。
核心工作流
1. 定义测量对象和证据链
完整读取 references/foundations-and-sources.md。建立构念表:定义、包含/排除、目标人群、观察单位、候选指标、来源、分析用途与误差风险。区分要测的概念、实际提问、观察到的回答和最终统计量。
2. 生成并审查题项
完整读取 references/question-writing-and-response-process.md。按“理解—检索—判断—作答”检查每道题。题面、回忆期、参照对象、信息来源和受访者知识边界必须匹配。事实、行为、态度、知识、敏感和开放题分别处理。
3. 设计响应格式与整卷流程
完整读取 references/response-options-scales-and-flow.md。设计互斥/穷尽的选项、量尺标签、缺失类回答、题序、随机化和敏感题位置。不要默认五点同意量尺;量尺点数、中点、反向项目、矩阵和总分都需任务依据。
4. 按模式实现工具
完整读取 references/mode-usability-and-programming.md。为 Web、移动端、纸面、电话、面访或混合模式建立显示、导航、跳题、校验、帮助文本和输出测试。追求含义与回答任务等价,不强求跨模式逐字相同。
5. 处理翻译与跨群体比较
涉及多语言、跨文化、跨地区或跨群体比较时,完整读取 references/translation-and-cross-cultural-equivalence.md。采用团队翻译、审定、目标语言预测试和版本记录。语言等价不等于测量等值;比较组均值前先评估相关等值证据。
What ships with it
15 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/questionnaire-docx-template.js 28 KB runs code
- assets/questionnaire-spec.template.json 4.7 KB
- references/ethics-privacy-and-chinese-context.md 4.3 KB
- references/foundations-and-sources.md 3.9 KB
- references/measurement-validation-and-analysis-readiness.md 4.3 KB
- references/mode-usability-and-programming.md 3.1 KB
- references/output.md 3.8 KB
- references/pretesting-and-cognitive-interviewing.md 3.4 KB
- references/question-writing-and-response-process.md 3.9 KB
- references/response-options-scales-and-flow.md 3.7 KB
- references/sampling-nonresponse-and-data-quality.md 3.2 KB
- references/sources.md 9.4 KB
- references/translation-and-cross-cultural-equivalence.md 2.7 KB
- references/word-output.md 4.3 KB
- scripts/validate_questionnaire_spec.py 16 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.
- 9d ago First seen · 150 lines · 192 tokens per session scan A 606dc862074c
questionnaire-design is a skill published in the GitHub repository Lambenthan/mixed-methods-instrument-design (4 stars, last pushed 27d ago), licensed MIT. It adds 192 tokens to every session and 3,052 once invoked, about $0.0010 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
presubmission-check
Use when a finished manuscript is about to be submitted and the question is what to fix first: a pre-submission check, a submission-readiness pass, "what will get me desk rejected", reporting-guideline gaps (STROBE, CONSORT, PRISMA, COREQ), a missing ethics or funding or competing-interests or data-availability…
methodvahti-design-defensibility
Use when a researcher is deciding or defending a qualitative sample size, or appraising how defensible a study's methodological decisions are before results exist. Triggers on sample size justification, how many interviews, how many focus groups, saturation, information power, thematic saturation, defend my sample…
vahtian-research-support
Use when a researcher needs literature-search, screening, evidence-synthesis, reference-checking, or citation-checking support — a systematic or scoping review, a reproducible multi-source search, blinded dual screening, inter-rater reliability (Cohen's κ / Krippendorff's α), full-text retrieval, checking a reference…
ob-methods-results-check
Audit organizational behavior, management, HRM, and work-psychology manuscript Methods and Results evidence before submission. Use when checking full manuscripts, methods/results sections, tables, figures, appendices, field surveys, experiments, mediation, moderation, CFA, SEM, multilevel reporting, statistical…
interview-guide
Create qualitative interview guides — discussion guides, probing questions, thematic analysis, and synthesis frameworks.
survey-design
Use this Skill to design, validate, and deploy research surveys: Likert scale construction, attention checks, pilot testing, ICC reliability, and Qualtrics/LimeSurvey export.