Borrowing it
Nothing to install: this file belongs to ctxpipe-ai/ctxpipe. 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/ctxpipe-ai/ctxpipe/main/.agents/skills/product-ui/SKILL.mdgit clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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/ctxpipe-ai/ctxpipe/product-ui)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/product-ui"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/product-ui/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/ctxpipe-ai/ctxpipe/product-ui"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/product-ui.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 | $0.00049 | $0.02336 |
| Opus 5.5 | $0.00020 | $0.00934 |
| Sonnet 5.5 | $0.00010 | $0.00467 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
product-ui 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 4d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product UI (apps/ui)
Designer-quality Operate UI from intent. Identity lives in apps/ui/DESIGN.md. Implementation stays in the react and storybook skills. Radical / landing-page exploration stays in prototype.
Do not install marketing frontend-design on this surface. Do not invent a palette, typeface, or shell.
1. Read identity
Open apps/ui/DESIGN.md. Apply it on new or touched UI.
Done when: you can name the radius (rounded-md), primary (white/light), accent (teal), title scale (text-lg / text-xl on product screens), and which brand signatures you will reuse (crosses, .ctx-label, status pill + text, quiet glow).
2. Feature, not shell
Design the feature content first. Smallest useful version: the fields, rows, or CTA the user asked for. Empty / loading / error only for this feature. No implied attachments, extra tabs, or marketing chrome.
Leave AppShell, SideNav, and page-wide atmosphere alone unless the user asked to change them. Product chrome stays undecorated (no grid, no teal/blue glow).
When polishing a named region of existing chrome or a dense control list: change only that region — do not push experiments into shared class helpers that restyle siblings. After visual polish, Tab the surface once — focus rings, clipping, and non-outline affordances (resize line + arrows) are part of done. Use focus-styles.ts; see DESIGN.md Focus / keyboard and visual-craft.md Finishing.
Done when: the planned surface is the feature; the shell is unchanged; every control has a backend or an explicit out-of-scope note.
3. Translate intent → pattern
User words are jobs, not HTML tags. For each chunk of UI, name:
- Job — scan, compare, act, learn, or confirm? (Not “render a list.”)
- Shape of each item — title only? title + supporting line? title + meta + action?
- Count and relationship — 2–5 peers, a sequence, one protagonist + extras, or 20+ rows?
- Pattern — pick from references/information-design.md, or write one sentence justifying a new one.
- Primitive test — if the markup is the HTML word the user said (
ul,table,form,p) and nothing else, revise.
What ships with it
3 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.
- 4d ago Changed · +15 lines 16ffe52b4a36
- 21d ago Changed 06a0151a239d
- 1mo ago First seen · 97 lines · 49 tokens per session scan A cfa368d4bc9e
product-ui is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 2,336 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
design
Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…
design-an-interface
Generate radically-different module or API contract designs in parallel, then compare on depth, simplicity, and ease-of-correct-use. Trigger when the user is shaping a new module surface, exploring contract options, comparing module shapes, or applying "design it twice" to a first-pass sketch.
{skill_name}
Personal taste skill — 5 evidence-derived anchors ({anchornames}) for prose, code, design, and decisions. Two modes: audit judges an artifact against the two-sided charter; anchor loads the taste register before producing. Trigger with "{triggerphrase}", "taste-test", "is this slop?", or "overkill?".
loft
Loft the shape before cutting steel — answer a design question that prose cannot settle by building a throwaway artifact: a pure logic module in a clickable shell, or structurally different UI variants behind one route. The captain reacts to the artifact; the answer folds into the decision; the artifact never docks.…
gsd-ui-phase
Generate UI design contract (UI-SPEC.md) for frontend phases.
moai-design-tools
Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.