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 agentmods add skills/abilityai/abilities/websitenpx skills add Abilityai/abilities --skill websitegit clone --depth 1 https://github.com/Abilityai/abilitiesWhat 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 | $0.00055 | $0.06523 |
| Opus 5 | $0.00028 | $0.03261 |
| Sonnet 5 | $0.00011 | $0.01305 |
| Haiku 4.5 | $0.00006 | $0.00652 |
Grade A, and why
create-website 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 2d 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 — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Website
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.create-website vX.Y — recent: <summary>. Then proceed.
Scaffold a complete, production-ready Next.js 15 website deployable to Vercel.
For tech stack details and component patterns, see reference.md.
Workflow
Step 1: Gather Requirements
If $ARGUMENTS contains a project name or description, use it as context. Otherwise, ask:
Use AskUserQuestion:
- Question: "What website are you building?"
- Header: "Website Builder"
- Gather these details (ask in one prompt, not separately):
- Project name — lowercase-with-hyphens (used for directory and package name)
- What is it? — One sentence: company site, SaaS landing page, portfolio, docs site, agency site, etc.
- Pages needed — Homepage + what else? (about, pricing, blog, contact, etc.)
- Brand basics — Company/product name, tagline, primary color (hex or description like "deep blue")
- Destination — Where to create the project directory (default:
./$PROJECT_NAME)
If the description mentions more than one language, also ask which languages and which is canonical — a multilingual site switches the content layer and Studio to the multilingual variant (reference.md → Multilingual sites).
Step 2: Choose Design Direction
Use AskUserQuestion:
- Question: "Pick a design direction:"
- Header: "Design System"
- Show these options:
- Minimal Clean — White/light background, subtle borders, no gradients. Swiss-inspired.
- Bold Dark — Dark background, vivid accents, glassmorphism cards.
- Warm Professional — Warm neutrals, rounded shapes, friendly and approachable.
- Custom — I'll describe what I want.
Map the choice to CSS variable values in Step 4.
Step 3: Initialize Project
What ships with it
1 file 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.
- 2d ago First seen · 650 lines · 55 tokens per session scan A 77a4a3857b26
create-website is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 55 tokens to every session and 6,523 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.