Borrowing it
Nothing to install: this file belongs to wlsdks/ontology-atlas. 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/wlsdks/ontology-atlas/main/.agents/skills/user-walkthrough/SKILL.mdgit clone --depth 1 https://github.com/wlsdks/ontology-atlasWrote 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/wlsdks/ontology-atlas/user-walkthrough)<a href="https://agentmods.dev/skills/wlsdks/ontology-atlas/user-walkthrough"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/user-walkthrough/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/wlsdks/ontology-atlas/user-walkthrough"><img src="https://agentmods.dev/badge/skills/wlsdks/ontology-atlas/user-walkthrough.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01100 |
| Opus 5 | $0.00018 | $0.00550 |
| Sonnet 5 | $0.00007 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
user-walkthrough 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 5d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User walkthrough
Screen reviews do not prove a journey. When pnpm design:route includes this
skill, walk its declared scope: the changed path for a local journey change, the
agent-handoff path for a handoff change, or the continuous north-star path for a
new surface.
Authority and limit
Judge facts that live in the artifact: vocabulary, next-step visibility, control discoverability, feedback, perceived reversibility, waiting state, missing paths, and visible craft. Each can be proven by pointing at the screen.
Do not claim facts that live in a person's mind: whether they want it, will return, recommend it, or pay. Simulated users mispredict real people inconsistently. “No observable stall” does not mean “they like it.” Demand, retention, and willingness come only from real people.
Name patterns, not emotions
Every finding carries a reusable pattern name. “This person will feel frustrated” is invention; “dead-end CTA—the primary button opens an empty destination” is a checkable pattern.
Common patterns:
| Pattern | Definition |
|---|---|
| Dead-end CTA | the strongest action leads nowhere useful |
| Implementation-language label | the label describes program work, not the user's outcome |
| Gate before value | the product requires something before showing why it matters |
| Silent wait | work is happening with no visible progress |
| Unknown reversibility | a risky-looking action shows no undo or cancellation path |
| Builder vocabulary leak | internal developer terms appear on the user surface |
| Missing next step | the screen does not say what follows the completed action |
Name and define a new repeatable pattern when needed. Repeated patterns in the decision ledger may deserve a product rule.
Declare the walker
Use only knowledge state, situation, and concern. Do not invent demographic or emotional backstory.
Default:
Knows: uses Claude Code daily; maintains AGENTS/CLAUDE Markdown; comfortable with Git.
Does not know: Atlas; product use of “ontology”; graph databases.
Context: technical lead on a 2–10 person team, received a link while doing other work, meeting in 10 minutes.
Cares about: agents losing context, software touching local files, and the ability to leave later.
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.
- 5d ago Changed · +4 lines 0628443bbc48
- 7d ago Changed · +6 lines b179a4b11305
- 12d ago First seen · 109 lines · 37 tokens per session scan A b9cb9c306cf9
user-walkthrough is a skill published in the GitHub repository wlsdks/ontology-atlas (103 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,100 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 2026-08-30.
Other skills, from other repositories
design-brief
Parse a structured design brief written in I-Lang protocol format into a concrete design spec. Eliminates ambiguity from vague requests like "make it professional" by requiring explicit dimensions: palette, typography, layout, mood, density, and constraints. Trigger keywords: "design brief", "create a design brief"…
fs-electric-studio
OpenDesign as an enterprise design platform: a buyer-forwardable proposal for a design-org's economic buyer — pain, value, ROI, rollout. Built as a decision-grade B2B sales deck for economic buyer, design VP, procurement.
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
open-design-landing-deck
OpenDesign's brand-story deck for partners and press: why it exists, what it believes, and where design is going. Built as a decision-grade marketing & GTM deck for partners, press, community.
fs-editorial-forest
Art-directing a fashion house's annual report — the editorial system, the photography rhythm, and the data spreads. Built as a decision-grade design craft deck for brand stakeholders, exec audience.