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 agentmods add skills/yonatangross/orchestkit/user-researchnpx skills add yonatangross/orchestkit --skill user-researchgit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/user-research)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/user-research"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/user-research.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.01419 |
| Opus 5 | $0.00022 | $0.00709 |
| Sonnet 5 | $0.00009 | $0.00284 |
| Haiku 4.5 | $0.00004 | $0.00142 |
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.
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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Research
Frameworks for building deep user understanding through structured research methods. Covers personas, journey mapping, interviews, usability testing, and Jobs-to-be-Done.
Research Method Selection
Choose the right method for your question:
| Method | When to Use | Sample Size | Time | Output |
|---|---|---|---|---|
| User Interviews | Early discovery, deep understanding | 5-8 | 2-3 weeks | Qualitative insights |
| Usability Testing | Validate designs, find issues | 5-10 | 1-2 weeks | Actionable fixes |
| Surveys | Quantify attitudes, preferences | 100+ | 1-2 weeks | Statistical data |
| Card Sorting | Information architecture | 15-30 | 1 week | IA recommendations |
| A/B Testing | Compare alternatives | 1000+ | 2-4 weeks | Statistical winner |
Rule of thumb: Start with interviews (5-8 participants) to discover unknowns. Switch to surveys once you have hypotheses to validate.
Persona Quick Reference
Personas are fictional composites built from research synthesis. Keep to 3-5 max.
## Persona: [Name]
### Demographics
- Age: [Range]
- Role: [Job title]
- Company: [Type/size]
- Tech savviness: [Low/Medium/High]
### Quote
> "[Characteristic statement that captures their mindset]"
### Goals
1. [Primary goal - what success looks like]
2. [Secondary goal]
### Pain Points
1. [Frustration with current state]
2. [Obstacle they face]
### Key Insight
[The most important thing to remember about this persona]
Incorrect — vague persona without goals:
Persona: Sarah, Age 35, Marketing Manager. Likes social media and coffee.
Correct — actionable persona with goals and pain points:
Persona: DevOps Dana
Quote: "I don't have time for tools that create more work than they save."
Goals: Reduce deployment failures, give devs self-service capabilities
Pain Points: Alert fatigue from false positives, context-switching between 10+ tools
Key Insight: Evaluates tools by "time saved vs. time invested" — needs immediate value.
What ships with it
8 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.
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.
- yesterday First seen · 182 lines · 44 tokens per session scan A 9f4fe5a88038
user-research is a skill published in the GitHub repository yonatangross/orchestkit (229 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,419 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
gr-user-interview
用户访谈框架。HeyGen 做 937 次访谈找到 PMF 的完整方法论。覆盖访谈招募、问题设计、 访谈执行、数据合成、决策驱动。从 gingiris-user-interview 提炼。.
Agent Workflow Builder
Build multi-agent AI workflows with orchestration, tool use, and state management.
delegate
Delegate implementation to Cursor via the cursor-delegate-mcp MCP delegate tool. Use when the user says delegate to Cursor, Composer, or cursor-agent; have Cursor handle or do this; offload this; send this to Composer; use Composer/Cursor for coding; hand off implementation; plan before building; ask Cursor a question…
tdd
Use when implementing features or bug fixes test-first.
feature-optimiser
Deterministically audit and optimise a published feature page on the register ladder: struggling-moment heroes with zero implementation jargon, mechanism evidence relocated to section bodies and dropdowns in the HashiCorp / Stripe / Tailscale register. Runs an 11-section quality audit plus register-ladder checks (hero…
feature-writer
Write and rewrite systemprompt.io feature pages on a register ladder: heroes lead with the reader's struggling moment and ownership stake in plain language, mechanism evidence relocated intact into section bodies and dropdowns where it stays dense, metaphor-free, and tied to a verifiable reference. Research-first…