user-research

user-research is a skill for Claude Code, Codex from nicepkg/ai-workflow. It costs 19 tokens per session (1,064 once invoked), scanned A, original, MIT.

A set of user-research methods for learning about customers, their behaviour, needs, and problems. It covers interviews, surveys, usability tests, observation, and analytics, with guidance on choosing and running each method.

In plain words
What is it for?
Use it to prepare interviews and surveys, investigate workflow problems, test usability, observe users, and understand the time or cost of customer pain points.
Why use it?
It reduces guesswork in product decisions by helping you collect evidence from real or measured user behaviour. It also provides structures for asking useful questions and turning answers into insights.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nicepkg/ai-workflow/user-research
Any agent
npx skills add nicepkg/ai-workflow --skill user-research
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for user-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicepkg/ai-workflow/user-research.svg)](https://agentmods.dev/skills/nicepkg/ai-workflow/user-research)
Your own site
<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/user-research"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/user-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,064 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.01064
Opus 5 $0.00010 $0.00532
Sonnet 5 $0.00004 $0.00213
Haiku 4.5 $0.00002 $0.00106

Measured yesterday against content hash bba8c128cf42, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

user-research 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

workflows/product-manager-workflow/.claude/skills/user-research/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Research Skill

Conduct effective user research to understand customer needs, behaviors, and pain points. Master interview techniques and insight synthesis.

Research Methods

Method Selection Guide

Method When Sample Duration
Interviews Deep understanding 15-25 45-60 min
Surveys Quantitative validation 100+ 5-10 min
Usability UX issues 5-8 30-60 min
Observation Real behavior 3-5 2-4 hours
Analytics Scale patterns All users Ongoing

Qualitative Research

Interview Structure

OPENING (5 min):
- Intro & rapport
- Permission to record
- Context setting

CONTEXT (10 min):
- Role and responsibilities
- Day-to-day workflow
- Tools used

DEEP DIVE (20 min):
- "Walk me through [process]..."
- "Tell me about last time [problem]..."
- "What frustrates you most?"

IMPACT (10 min):
- "What happens when [problem]?"
- "How much time/money does it cost?"

FUTURE (10 min):
- "What would ideal look like?"
- "What would you pay for [solution]?"

CLOSING (5 min):
- "Anything else?"
- "Can I follow up?"

Interview Best Practices

  • Listen 70%, talk 30%
  • Ask "Why?" 5 times
  • Avoid leading questions
  • Use silence effectively
  • Capture quotes verbatim

Quantitative Research

Survey Design

Question Types:

  • Rating scale (1-5, 1-10)
  • Multiple choice
  • Open-ended (limit 1-2)
  • Ranking

NPS Question: "How likely are you to recommend [product] to a friend? (0-10)"

Sample Size Calculator

For 95% confidence, 5% margin:
- Population 100 → Sample 80
- Population 500 → Sample 217
- Population 1000 → Sample 278
- Population 10000 → Sample 370

Synthesis

Affinity Mapping

  1. Write each insight on sticky note
  2. Group similar insights
  3. Name each group (theme)
  4. Rank by frequency/impact
  5. Extract top 5-10 themes

Persona Template

NAME: [Descriptive name]
ROLE: [Job title, company type]
QUOTE: "[Real quote from research]"

GOALS:
- [Goal 1]
- [Goal 2]

FRUSTRATIONS:
- [Pain 1]
- [Pain 2]

BEHAVIORS:
- [How they work]
- [Tools they use]

NEEDS:
- [Need 1]
- [Need 2]

Read the full file on GitHub · 182 lines

Files

What ships with it

5 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.

Changes

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.

  1. yesterday First seen · 182 lines · 19 tokens per session scan A bba8c128cf42

Subscribe to this mod's changes

user-research is a skill published in the GitHub repository nicepkg/ai-workflow (283 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 1,064 once invoked, about $0.0001 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 2026-09-03.