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/ancoleman/ai-design-components/building-formsnpx skills add ancoleman/ai-design-components --skill building-formsgit clone --depth 1 https://github.com/ancoleman/ai-design-componentsWrote 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/ancoleman/ai-design-components/building-forms)<a href="https://agentmods.dev/skills/ancoleman/ai-design-components/building-forms"><img src="https://agentmods.dev/badge/skills/ancoleman/ai-design-components/building-forms.svg" alt="Measured on agentmods" 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 | $0.00102 | $0.03381 |
| Opus 5 | $0.00051 | $0.01690 |
| Sonnet 5 | $0.00020 | $0.00676 |
| Haiku 4.5 | $0.00010 | $0.00338 |
Grade A, and why
building-forms 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 — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Form Systems & Input Patterns
Build accessible, user-friendly forms with systematic component selection, validation strategies, and UX best practices.
Purpose
Forms are the primary mechanism for user data input in web applications. This skill provides systematic guidance for:
- Selecting appropriate input types based on data requirements
- Implementing validation strategies that enhance user experience
- Ensuring WCAG 2.1 AA accessibility compliance
- Creating complex patterns (multi-step wizards, conditional fields, dynamic forms)
When to Use This Skill
Triggers:
- Building contact forms, login/registration flows, checkout processes
- Implementing surveys, questionnaires, or settings pages
- Adding validation to user inputs
- Creating multi-step workflows or wizards
- Ensuring form accessibility
- Collecting structured data (addresses, credit cards, dates)
Common Requests:
- "Create a registration form with validation"
- "Build a multi-step checkout flow"
- "Add inline validation to email input"
- "Make this form accessible for screen readers"
- "Implement a survey with conditional questions"
Universal Form Concepts
Component Selection Framework
The Golden Rule: Data Type → Input Component → Validation Pattern
Start by identifying the data type to collect, then select the appropriate component:
Quick Reference:
- Short text (<100 chars) → Text input, Email input, Password input
- Long text (>100 chars) → Textarea, Rich text editor, Code editor
- Numeric → Number input, Currency input, Slider
- Date/Time → Date picker, Time picker, Date range picker
- Boolean → Checkbox, Toggle switch
- Single choice → Radio group (2-7 options), Select dropdown (>7 options), Autocomplete (>15 options)
- Multiple choice → Checkbox group, Multi-select, Tag input
- File/Media → File upload, Image upload
- Structured → Address input, Credit card input, Phone number input
For detailed decision tree: See references/decision-tree.md
What ships with it
42 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.
- assets/error-messages/errors-en.json 2.5 KB
- assets/error-messages/errors-es.json 2.8 KB
- assets/error-messages/errors-fr.json 2.8 KB
- assets/form-schemas/contact-form.json 1.3 KB
- assets/form-schemas/registration-form.json 1.8 KB
- assets/validation-rules/common-validations.json 1.7 KB
- assets/validation-rules/email-patterns.json 1.6 KB
- assets/validation-rules/phone-formats.json 1.3 KB
- examples/basic-form.tsx 5.2 KB
- examples/conditional-form.tsx 20 KB
- examples/inline-validation.tsx 11 KB
- examples/javascript/async-validation.tsx 8.6 KB
- examples/javascript/file-upload-preview.tsx 8.1 KB
- examples/multi-step-wizard.tsx 13 KB
- examples/python/async_database_validation.py 4.4 KB runs code
- examples/python/basic_form.py 11 KB runs code
- examples/python/django_forms_example.py 6.9 KB runs code
- examples/python/fastapi_forms.py 6.0 KB runs code
- examples/python/flask_wtf_example.py 7.4 KB runs code
- examples/python/pydantic_validation.py 15 KB runs code
- examples/settings-form.tsx 18 KB
- outputs.yaml 16 KB
- references/accessibility-forms.md 25 KB
- references/decision-tree.md 17 KB
- references/javascript/examples/basic-form.tsx 7.8 KB
- references/javascript/examples/inline-validation.tsx 12 KB
- references/javascript/examples/multi-step-wizard.tsx 14 KB
- references/javascript/react-hook-form.md 24 KB
- references/javascript/zod-validation.md 20 KB
- references/python/examples/basic_form.py 11 KB runs code
- references/python/examples/pydantic_validation.py 15 KB runs code
- references/python/pydantic-forms.md 21 KB
- references/python/wtforms.md 20 KB
- references/ux-patterns.md 30 KB
- references/validation-concepts.md 22 KB
- scripts/generate_error_messages.py 7.6 KB runs code
- scripts/generate_form_schema.py 6.7 KB runs code
- scripts/validate_form_accessibility.py 6.5 KB runs code
- scripts/validate_form_data.py 5.5 KB runs code
- skill-methology/critique.md 16 KB
- skill-methology/release1.md 9.3 KB
- skill-methology/release2.md 4.2 KB
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 First seen · 430 lines · 102 tokens per session scan A e7d715b1ade2
building-forms is a skill published in the GitHub repository ancoleman/ai-design-components (517 stars, last pushed 8mo ago), licensed MIT. It adds 102 tokens to every session and 3,381 once invoked, about $0.0005 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
ux-design
Use when the user asks for UX, product flow, user journey, wireframes, usability, conversion, onboarding, checkout, signup, navigation, forms, state design, dashboard workflows, command palettes, settings, permissions, long-running task progress, admin/internal tools, activation, retention, or making an app easier to…
design-with-claude
Use when design work needs a product designer's eye: auditing a codebase for design-system gaps, fixing WCAG contrast and unlabeled inputs, choosing type scales or spacing steps, reviewing UI that looks generic or AI-generated, or designing forms, tables, dashboards, navigation, checkout, onboarding, dark mode, and…
mimic-ai
Use when building, editing, or iterating on a Figma design via the Mimic AI MCP server (mimicstatus, mimicdiscoverds, figmacreateframe, figmainsertcomponent, mimicbuildtable, mimicbuildchart, etc. are available), or when the user asks to turn HTML, a prompt, or a Claude Design/Figma Make prototype into real Figma…
pencilplaybook
PencilPlaybook is the UI Skills / Taste-Skill for Pencil.dev + Claude Code — a design playbook that gives Claude real perceptual psychology and senior-level guardrails so it stops producing averaged-out AI slop.
screenshot-to-design-system
Extracts color tokens and component styles from UI screenshots by reading each control region individually (not full-page layout). Generates a complete design system demo with tokens.css and components.html. Ignores backgrounds and icons. Use when the user uploads a UI screenshot, asks for design tokens, color palette…
Brand
Complete brand development system with emotive foundation. Triggers on requests for brand identity, logos, visual systems, or design guidelines. Creates distinctive, anti-AI-slop design from strategy through delivery.