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 skills add lenar-amirov/product-pipeline-public --skill user-testinggit clone --depth 1 https://github.com/lenar-amirov/product-pipeline-publicWrote 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/lenar-amirov/product-pipeline-public/user-testing)<a href="https://agentmods.dev/skills/lenar-amirov/product-pipeline-public/user-testing"><img src="https://agentmods.dev/badge/skills/lenar-amirov/product-pipeline-public/user-testing/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/skills/lenar-amirov/product-pipeline-public/user-testing"><img src="https://agentmods.dev/badge/skills/lenar-amirov/product-pipeline-public/user-testing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00097 | $0.00861 |
| Opus 5 | $0.00048 | $0.00430 |
| Sonnet 5 | $0.00019 | $0.00172 |
| Haiku 4.5 | $0.00010 | $0.00086 |
Grade A, and why
user-testing 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Testing — concept mode / study mode
One skill, two depths. Pick by what's at stake:
| Concept test (quick) | Usability study (full) | |
|---|---|---|
| When | after /sketch — validate direction before hi-fi |
before/after launch — measure task performance |
| Duration | 15 min × 3–5 users, days to run | 30–60 min × 5–8/segment, weeks |
| Answers | "do users get it, do they want it" | "can users complete it, where does it break" |
| Output | keep / change / rethink per screen | severity-ranked issue list |
Default to concept mode; escalate to a study only when the decision needs task-level measurement.
Concept mode (step 8.5)
- Scenario — realistic context from CONTEXT.md + job-to-be-done from the solution hypothesis. Don't lead toward the "right" answer.
- Questions per screen (3–5 max): first impression (5 sec — "what is this?"), comprehension ("how would you [key action]?"), value ("better than how you do it today?"), friction ("anything confusing/missing?"). Open-ended only; never explain the UI.
- Success/fail criteria BEFORE the sessions, tied to the hypothesis:
e.g. 4/5 understand the purpose in 5 sec; 3/5 complete the primary task
unaided. Fail triggers (2+ misunderstand the core concept) mean back to
/sketch, not "note it and proceed". - Protocol: setup ("we test the design, not you"; think-aloud) →
screens → wrap-up rating. Write plan + empty results sections to
research/concept-test-results.md.
Study mode
- Research questions ≠ tasks: 3–5 questions the business needs answered, each mapped to scenario-based tasks (real trigger, no UI vocabulary in the task text).
- Participants: from the CONTEXT.md segment; 5–8 per distinct segment; screener excludes proxies (people who "know about" vs "do").
- Measures: completion, time-on-task, error types + think-aloud coding. Moderated when exploring, unmoderated for benchmarks.
- Severity classification for findings: blocker (task impossible) / major (workaround found, with pain) / minor (friction) / cosmetic — prioritized against segment share affected.
- Plan →
research/ux-research-brief.md; create a dependency (kind: ux_research, owner, deadline) — studies stall exactly like analyst briefs.
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.
- 11d ago First seen · 62 lines · 97 tokens per session scan A df12a676a510
user-testing is a skill published in the GitHub repository lenar-amirov/product-pipeline-public (12 stars, last pushed 21d ago), licensed MIT. It adds 97 tokens to every session and 861 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
presentation-design
Designs slide decks and one-pagers that carry an argument rather than decorate one — deck structure, headlines that state the takeaway, charts that make a single point, and the different rules board decks and conference talks follow. Use this to build or fix a pitch deck, board deck, or conference talk, to design a…
ux-product-auditor
Audits a website, app, onboarding flow, or design for usability, conversion, and product problems, tying every finding to a business outcome and a severity. Use this to review an interface, diagnose low conversion or activation, find where users drop off, get structured product feedback, or decide which UX fixes to…
visual-content
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…
brand-identity
Defines and applies visual brand — logo usage, palette, typography, imagery direction, and the guidelines that keep expression consistent across product and marketing surfaces. Use this to establish a brand from scratch, audit whether an existing brand is being applied consistently, build brand guidelines, or decide…
design-styles
Applies a deliberate visual direction to an interface — minimalist editorial, industrial utilitarian, or high-polish commercial — each with its own type scale, palette behavior, surface treatment, and motion. Use this when a product needs a point of view rather than defaults, when choosing between visual directions…