Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/synthetic-user-research/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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/dynokostya/just-works/synthetic-user-research)<a href="https://agentmods.dev/skills/dynokostya/just-works/synthetic-user-research"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/synthetic-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/skills/dynokostya/just-works/synthetic-user-research"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/synthetic-user-research.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 | $0.00089 | $0.01232 |
| Opus 5.5 | $0.00036 | $0.00493 |
| Sonnet 5.5 | $0.00018 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
synthetic-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 17d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthetic User Research
AI personas are useful in a narrow lane of questions and misleading outside it. A synthetic panel can catch comprehension failures, confusing flows and survey defects before real participants are spent on them. It cannot tell you what people will pay for, feel or do. This skill checks that the question is in the lane, then runs the method. Sometimes the result is "no, here is the human study to run instead".
The lane (checked before anything runs)
Synthetic methods can probe questions whose answer lives in the artifact, not in people's feelings:
- Comprehension: is this copy, onboarding or explanation understandable, and where does a reader stumble?
- Instrument defects: leading questions, double-barrelled items and missing answer options, found before a survey is fielded.
- Information architecture: can someone with a goal find the thing, and where does the navigation mislead?
- Message differentiation: do these three positionings read as different?
- Edge cases: which user situations did the design forget? Personas serve as brainstorming here, not as evidence.
Synthetic methods cannot establish the following, so refuse these questions and say why:
- Willingness to pay, purchase intent or price sensitivity. Models have no budget and agree too readily.
- Emotional response, delight or trust. A model's simulated feeling carries no information.
- Unknown needs. Personas recombine known data, and discovery is about what is not yet known.
- Behavior. What people say they would do is already unreliable, and a model's guess at it is worse.
- Validation of a launch or investment decision. Synthetic output is not evidence of demand.
Required inputs
Ask for these if they are not provided:
- The research question. Run the lane check first and give the verdict before choosing a method.
- Real data to ground the personas: interview notes, support tickets, reviews, analytics segments. With no real data there is no panel, because ungrounded personas only repeat the model's stereotypes.
- The artifact under test: the copy, flow, survey or navigation.
- The decision this feeds and its stakes. Higher stakes narrow the lane.
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.
- 17d ago Changed · -7 lines · -35 tokens per session 0841cf3fb2f4
- 1mo ago First seen · 81 lines · 124 tokens per session scan A 56fcb97736f3
synthetic-user-research is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,232 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-20.
synthetic-user-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| synthetic-user-researchDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 89 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |