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/predictive-ux-evaluation/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/predictive-ux-evaluation)<a href="https://agentmods.dev/skills/dynokostya/just-works/predictive-ux-evaluation"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/predictive-ux-evaluation/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/predictive-ux-evaluation"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/predictive-ux-evaluation.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 | $0.00134 | $0.01676 |
| Opus 5.5 | $0.00054 | $0.00670 |
| Sonnet 5.5 | $0.00027 | $0.00335 |
| Haiku 4.5 | $0.00013 | $0.00168 |
Grade A, and why
predictive-ux-evaluation 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Predictive UX Evaluation
Inspection methods that predict where a first-time user fails and how long a practiced expert takes. They do not predict conversion, preference, or emotion. Run the lane check before any method. Hand every pass to a real-user study.
The lane (checked before anything runs)
These methods can usefully predict — the answer lives in the artifact's structure:
- First-time-user failure points at a named step (cognitive walkthrough), including whether the first screen carries the cues for a stated comprehension
- Expert, error-free task time on a named path (KLM / GOMS)
- Relative target-acquisition time from size and distance (Fitts's law)
- Decision time among already-known, labelled alternatives (Hick–Hyman), with the visual-search limit stated
- Likely first-look ranking under a named heuristic or a named saliency model
These methods cannot establish — refuse, and name the human method instead:
- Conversion, purchase intent, or "which variant wins"
- Whether visitors will actually understand the product, or feel it is for them (five-second test, interview)
- Preference, delight, trust, or any felt quality
- What people will actually do, pay, or remember
- Launch or investment validation
Mixed questions: answer the in-lane part; refuse the rest in the same report. Do not invent success-rate percentages, conversion lifts, or emotion scores. A walkthrough produces failure stories, not "% of users will fail."
Required inputs
Ask only for what is missing:
- Artifact — live URL, HTML prototype, screenshots of a flow, or source files
- Tasks — user goal, start state, success criterion. Comprehension ("what is this?") is a valid task: success is a statement, not a click. If omitted, infer 1–3 primary tasks from the artifact and state the inference
- User assumption — first-time (walkthrough) and/or practiced expert (KLM). Default: both
- Arrival context (optional) — search title/snippet or referrer. Default: words on screen only
- Pointer — mouse or touch. Default: mouse on desktop, touch on a mobile viewport
- Prior report (optional) — a previous pass from this skill. If present, this is a verification run: load
references/verify.md
What ships with it
7 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.
- 17d ago Changed · -19 lines · -96 tokens per session d9220cf41617
- 1mo ago First seen · 133 lines · 230 tokens per session scan A 55d2d6947a5c
predictive-ux-evaluation is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 134 tokens to every session and 1,676 once invoked, about $0.0005 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 2026-09-24.
predictive-ux-evaluation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| predictive-ux-evaluationDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 134 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |