Survey Experiment Eval

Evaluates survey experiment designs for economics research. Produces a structured diagnostic report covering identification, randomization, power, survey instrument quality, demand effects, ethics, pre-registration, and analysis plan. Use this skill whenever the user describes a survey experiment, shares a pre-analysis plan, uploads a survey instrument or Qualtrics file, asks "does this design work", "review my experiment", "what's wrong with this RCT", "check my survey experiment", "evaluate my experimental design", "audit my design", or discusses any planned or ongoing survey-based randomize

36 stars 11 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add dariia-m/my_claude_skills --skill survey-experiment-eval
Manual install
git clone --depth 1 https://github.com/dariia-m/my_claude_skills.git /tmp/my_claude_skills
mkdir -p ~/.claude/skills
cp -r /tmp/my_claude_skills/survey-experiment-check ~/.claude/skills/survey-experiment-eval

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Survey Experiment Design Evaluator

You are a methodological reviewer for survey-based experiments in economics and political economy. Your job is to be the tough-but-constructive referee who catches design flaws *before* the data is collected, when they can still be fixed.

## Philosophy

Most survey experiments in economics fail not because the research question is bad, but because of preventable design mistakes: underpowered samples, treatments that are too subtle, outcome measures that don't capture the theoretical mechanism, or demand effects that confound everything. A good evaluation catches these problems early and offers concrete fixes, not just complaints.

Be direct. If something is a fatal flaw, say so. If something is a minor concern, say that too. Calibrate severity honestly. Researchers benefit from knowing which problems are worth losing sleep over and which are "nice to fix but not essential."

## Before You Begin

Read the full checklist in `references/checklist.md` before producing your evaluation. It contains the detailed diagnostic questions organized by domain. Use it as your backbone, but apply judgment - not every item applies to every design, and some designs will have issues the checklist doesn't anticipate.

## Information Gathering

When the user presents a design, first assess what information you have. You need to understand at minimum:
Read the full skill on GitHub

Details

Skill name
survey-experiment-eval
Path
survey-experiment-check/SKILL.md
License
MIT
Repo updated
16 November 2026

FAQ

What does the Survey Experiment Eval skill do?

Evaluates survey experiment designs for economics research. Produces a structured diagnostic report covering identification, randomization, power, survey instrument quality, demand effects, ethics, pre-registration, and analysis plan. Use this skill whenever the user describes a survey experiment, shares a pre-analysis plan, uploads a survey instrument or Qualtrics file, asks "does this design work", "review my experiment", "what's wrong with this RCT", "check my survey experiment", "evaluate my experimental design", "audit my design", or discusses any planned or ongoing survey-based randomize

How do I install the Survey Experiment Eval skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add dariia-m/my_claude_skills --skill survey-experiment-eval. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Survey Experiment Eval popular?

It lives in dariia-m/my_claude_skills, which has 36 GitHub stars and 11 forks.

Related skills

Academic Paper Verify

36

dariia-m/my_claude_skills

Thoroughly verify all code, tables, figures, modeling decisions, and quantitative claims in an academic paper against its source R scripts and output files. Use this skill whenever you need to audit, replicate, or verify an academic research paper - including cross-checking LaTeX tables against R output, validating econometric modeling choices, ensuring sample sizes are consistent, building a verification manifest, and running automated replication tests. Trigger this skill for any mention of: paper verification, replication check, table audit, code-paper consistency, reproducing results, veri

Research & Science11

Academic Writing

36

dariia-m/my_claude_skills

Activate when the user is drafting any academic economics content from scratch (e.g., outlines, abstracts, introductions, data/methods/identification sections, results narratives, conclusions, referee responses, table/figure captions) and needs economics-specific structure, phrasing options, and quality checks to produce publication-ready prose.

Research & Science11

Anti Hallucination

36

dariia-m/my_claude_skills

ALWAYS activate this skill. Apply these rules to every task regardless of domain. This skill governs how Claude Code verifies information, writes code, references documentation, and avoids fabricating functions, arguments, APIs, file paths, data structures, or facts. These rules override any inclination to guess.

Writing & Content11

Zyte

33

zytedata/claude-skills

Zyte account work that has no Zyte MCP tool: credentials (set up, log in, get an API key, or a blocked site); deploying or pushing a project to Scrapy Cloud, and saving a job's full items, log or requests to a file (Zyte MCP results are truncated); Zyte API plan pricing (plans, tiers, discounts, commitments, free credit); how-to and docs questions about any Zyte product or account/billing, from docs.zyte.com. Scrapy Cloud jobs, recorded usage and per-website prices are Zyte MCP tools; use this skill for them only when those tools are missing, to tell the user how to connect the Zyte MCP. NOT f

AI, LLMs & Agents

Subagent Driven Development

43

obra/clank

Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks

AI, LLMs & Agents26

Agent Collaboration

45

Azure-Samples/agent-skills-dotnet-demo

Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication

AI, LLMs & Agents11

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.