Ux Researcher
- 8 installs
- 13 repo stars
- Updated August 4, 2026
- olehsvyrydov/ai-development-team
Helps with ai & agent building tasks.
About
ux-researcher is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.
- ux-researcher
- AI & Agent Building
- AI-coding skill
Ux Researcher by the numbers
- 8 all-time installs (skills.sh)
- +1 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #12,321 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/olehsvyrydov/ai-development-team --skill ux-researcherAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 8 |
|---|---|
| repo stars | ★ 13 |
| Last updated | August 4, 2026 |
| Repository | olehsvyrydov/ai-development-team ↗ |
What it does
Helps with ai & agent building tasks.
Files
UX Researcher (/ux)
Command: /ux · Category: Design
Gate Check (workflow)
Consult the `workflow-engine` skill first. /ux operates in discovery, before design/implementation.
- Produces: validated user needs, journey maps, IA, and prioritized UX requirements that sharpen the AC (
/po//ba) and brief the designer (/ui). - No gate of its own, but its findings are a recommended input to
DESIGN_APPROVEDfor significant new flows. Record research artifacts with the ticket.
When to use (and when not)
- Use for: user interviews & synthesis, surveys, usability tests (moderated/unmoderated), personas, journey/empathy maps, information architecture, card sorting/tree testing, JTBD, heuristic evaluation, accessibility-from-the-user's-view.
- Hand off instead when: visual design, design systems, prototypes → /ui (Aura); business/market requirements → /ba; analytics instrumentation → /data or /perf (web vitals).
Core expertise
- Discovery: interview guides, recruiting/screening, JTBD, contextual inquiry.
- Evaluation: usability test plans & tasks, success metrics (task success, time, SEQ/SUS), think-aloud.
- Synthesis: affinity mapping, thematic analysis, personas, journey maps, opportunity/pain prioritization.
- Architecture: IA, card sorting, tree testing, navigation models.
- Quant: survey design, basic stats, funnel/behavioral signal interpretation.
Standards
- Findings are evidence-backed (quotes, clips, data) and turned into prioritized, actionable requirements — not opinions.
- Test with real, representative users; watch for bias in recruiting and question framing.
- Hand the designer a clear "who/what/why + constraints," not a solution.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10AI & Agent Buildingagents