Cookiy AI User Research Skill connects AI coding agents to a user-research service for planning studies, conducting interviews and surveys, recruiting participants, and synthesizing results. Product teams and researchers use it to gather real human feedback through an agent or the connected Cookiy web app. The catalogue skills and plugin provide the agent-side workflow for that service.
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.
git clone --depth 1 https://github.com/cookiy-ai/user-research-skillWrote 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/plugins/cookiy-ai/user-research-skill/user-research)<a href="https://agentmods.dev/plugins/cookiy-ai/user-research-skill/user-research"><img src="https://agentmods.dev/badge/plugins/cookiy-ai/user-research-skill/user-research/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/plugins/cookiy-ai/user-research-skill/user-research"><img src="https://agentmods.dev/badge/plugins/cookiy-ai/user-research-skill/user-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 21d 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.
What it actually says
{
"name": "user-research",
"version": "1.2.0",
"description": "End-to-end user research skill for AI agents — plan qualitative studies (research plans, screening questionnaires, interview guides), synthesize interview transcripts into evidence-backed reports with codebooks and personas, run AI-moderated interviews with real or synthetic participants, and design and distribute multilingual quantitative surveys with conditional logic — all via natural language, powered by Cookiy AI.",
"author": {
"name": "Cookiy AI",
"email": "[email protected]",
"url": "https://cookiy.ai"
},
"homepage": "https://cookiy.ai",
"repository": "https://github.com/cookiy-ai/user-research-skill",
"license": "MIT",
"keywords": [
"user research",
"qualitative research",
"quantitative research",
"user interviews",
"interview guide",
"discussion guide",
"research plan",
"screening questionnaire",
"research synthesis",
"thematic analysis",
"survey design",
"participant recruitment",
"synthetic users",
"AI-moderated interviews",
"usability study",
"research report",
"discovery research",
"contextual inquiry",
"diary study"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 0 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 21d ago Changed ce9719620d4b
- 2mo ago First seen · 36 lines scan A fb0f14a5cb4d
user-research is a plugin published in the GitHub repository cookiy-ai/user-research-skill (1,568 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
user-research compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| user-researchcookiy-ai/user-research-skill | Plugin | 1.6k | 4d ago | MIT | A | — | Claude Code |
| padPerpetualSoftware/pad | Plugin | 203 | yesterday | Apache-2.0 | A | — | Claude Code |
| skillreaperthousandflowers/skillreaper | Plugin | 64 | 2d ago | MIT | A | — | Claude Code |
| personalanton-abyzov/vskill | Plugin | 47 | 3d ago | MIT | A | — | Claude Code |
| securityanton-abyzov/vskill | Plugin | 47 | 3d ago | MIT | A | — | Claude Code |
| happyhackingspace-skillsHappyHackingSpace/skills | Plugin | 5 | 5d ago | MIT | A | — | Gemini CLI |
| shield-kyaThe-Pixel-Boys/shield-kya | Plugin | 3 | yesterday | MIT | A | — | Gemini CLI |