Wonder Blocks
Khan/wonder-blocks
Implements user interfaces using the Wonder Blocks (WB) design system — Khan Academy's React component library.
Generate Figma Code Connect mappings that link React components to their Figma counterparts.
$ npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bitovi/ai-enablement-prompts figma-connect-component --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/bitovi/ai-enablement-prompts.git skills-src && mkdir -p .claude/skills && cp -r skills-src/figma/figma-connect-component .claude/skills/figma-connect-component && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "figma-connect-component" agent skill from https://github.com/bitovi/ai-enablement-prompts/tree/main/figma/figma-connect-component into .claude/skills/figma-connect-component/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-connect-component", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bitovi/ai-enablement-prompts/tree/main/figma/figma-connect-componentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bitovi/ai-enablement-prompts figma-connect-component --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitovi/ai-enablement-prompts.git skills-src && mkdir -p .agents/skills && cp -r skills-src/figma/figma-connect-component .agents/skills/figma-connect-component && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "figma-connect-component" agent skill from https://github.com/bitovi/ai-enablement-prompts/tree/main/figma/figma-connect-component into .agents/skills/figma-connect-component/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-connect-component", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bitovi/ai-enablement-prompts figma-connect-component --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitovi/ai-enablement-prompts.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/figma/figma-connect-component .cursor/skills/figma-connect-component && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "figma-connect-component" agent skill from https://github.com/bitovi/ai-enablement-prompts/tree/main/figma/figma-connect-component into .cursor/skills/figma-connect-component/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-connect-component", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bitovi/ai-enablement-prompts.git --path figma/figma-connect-component--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bitovi/ai-enablement-prompts figma-connect-component --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitovi/ai-enablement-prompts.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/figma/figma-connect-component .gemini/skills/figma-connect-component && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "figma-connect-component" agent skill from https://github.com/bitovi/ai-enablement-prompts/tree/main/figma/figma-connect-component into .gemini/skills/figma-connect-component/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-connect-component", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bitovi/ai-enablement-prompts figma-connect-componentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bitovi/ai-enablement-prompts.git skills-src && mkdir -p .github/skills && cp -r skills-src/figma/figma-connect-component .github/skills/figma-connect-component && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "figma-connect-component" agent skill from https://github.com/bitovi/ai-enablement-prompts/tree/main/figma/figma-connect-component into .github/skills/figma-connect-component/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-connect-component", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bitovi/ai-enablement-prompts figma-connect-component --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitovi/ai-enablement-prompts.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/figma/figma-connect-component .opencode/skills/figma-connect-component && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "figma-connect-component" agent skill from https://github.com/bitovi/ai-enablement-prompts/tree/main/figma/figma-connect-component into .opencode/skills/figma-connect-component/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-connect-component", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
figma-connect-componentGenerate Figma Code Connect mappings that link React components to their Figma counterparts.
Figma Connect Component is an agent skill from bitovi/ai-enablement-prompts. Generate Figma Code Connect mappings that link React components to their Figma counterparts. Use when a component exists in code and needs a Code Connect file so Figma shows real code snippets in Dev Mode. Also triggers on phrases like "connect this component to Figma", "generate Code Connect", "publish to Figma", "add figma.connect for this component", "link this to Figma Dev Mode".
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Frontend & Design, covering React components. It works with Figma and Model Context Protocol. The repository describes itself as: Prompts Bitovi uses for software development. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit df229b1. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
tscnpxFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
figma.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Figma Connect Component loads about 3.3k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 859 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from bitovi/ai-enablement-prompts at commit df229b1, republished under its MIT licence (© bitovi). 859 words, ~3,285 tokens.
.claude/skills/figma-connect-component/SKILL.md (or your agent's skills folder).User provides a Figma component URL (or component name) and wants to generate the Code Connect mapping for it.
https://figma.com/design/{fileKey}/{fileName}?node-id={nodeId}fileKey: abc123, nodeId: 45:67.temp/figma-explore/{component}.jsonsrc/components/Button/Button.tsx)Option A: Evidence File Provided (Preferred)
If an evidence file from figma-explore is provided (e.g., .temp/figma-explore/{component}.json):
id (node ID), name, variants, variantProperties, componentPropertyDefinitionsExample evidence file structure:
{
"id": "16:1234",
"name": "Button",
"type": "COMPONENT_SET",
"variants": [
{ "name": "Type=Primary, Size=Small", "id": "16:1235" },
{ "name": "Type=Primary, Size=Large", "id": "16:1236" }
],
"variantProperties": {
"Type": ["Primary", "Secondary", "Ghost"],
"Size": ["Small", "Medium", "Large"]
},
"componentPropertyDefinitions": {
"Label": { "type": "TEXT", "defaultValue": "Button" },
"Show Icon": { "type": "BOOLEAN", "defaultValue": false }
}
}Option B: URL/Node ID Provided (MCP Fallback)
If only a Figma URL or node ID is provided:
.temp/figma-explore/ that match the component namemcp_figma_get_metadata with nodeId and fileKeymcp_figma_get_design_context with nodeId and fileKeyIf no URL or evidence file provided, search for it:
{ComponentFolder}/README.md for "Figma Source" sectionspecs/**/tasks.md for component-to-Figma mapping tables.temp/figma-explore/figma-components-index.json for matching component names.temp/design-components/{component-name}/proposed-api.md exists, read it and inline the prop-to-Figma mapping table into your working context. Do not reference this file by path during generation — the full mapping must be in active context so no property is guessed or missed.className, id) are omitted from Code Connect.figma.* helpers{ComponentFolder}/{ComponentName}.figma.tsxIf {ComponentFolder}/README.md exists, ensure it has a Design-to-Code Mapping section with a mermaid flowchart at the top showing the Figma-to-React property relationships.
Diagram format:
flowchart LR
subgraph Figma["Figma Variants"]
FProp1["PropertyName1"]
FProp2["PropertyName2"]
end
subgraph React["React Props"]
RProp1["propName1"]
RProp2["propName2"]
end
FProp1 -->|"Value1 → 'code1'<br>Value2 → 'code2'"| RProp1
FProp2 -->|"mapping description"| RProp2
style Figma fill:#f3e8ff,stroke:#9333ea
style React fill:#dbeafe,stroke:#3b82f6Placement: The mermaid diagram should be placed immediately after the ## Design-to-Code Mapping heading, before any tables.
Example README structure:
## Design-to-Code Mapping
```mermaid
flowchart LR
subgraph Figma["Figma Variants"]
FSize["Size"]
FType["Type"]
end
subgraph React["React Props"]
RSize["size"]
RVariant["variant"]
end
FSize -->|"Small → 'sm'<br>Medium → 'md'<br>Large → 'lg'"| RSize
FType -->|"Primary → 'primary'<br>Secondary → 'secondary'"| RVariant
style Figma fill:#f3e8ff,stroke:#9333ea
style React fill:#dbeafe,stroke:#3b82f6
` ` `
### Variant Mappings
| Figma Variant | Figma Value | React Prop | React Value |
...Rules for the diagram:
figma.enum() calls)"Small → 'sm'")<br> for multiple value mappings on one arrowCritical: Code Connect requires the EXACT property names as they appear in Figma.
.figma-components/*.json) or get_metadata outputButtonType, Type, Size must match EXACTLY (case-sensitive)get_design_context MCP tool normalizes to camelCase - do NOT use those namesSize ≠ sizeExample from metadata:
name="ButtonType=Responsive, Type=Primary, Size=Small"Use in Code Connect:
variant: { ButtonType: 'Responsive' }, // ✅ Exact match
props: {
size: figma.enum('Size', { ... }), // ✅ Exact match
variant: figma.enum('Type', { ... }), // ✅ Exact match
}Map based on what exists in Figma:
figma.boolean(), figma.string(), figma.instance()figma.enum()figma.textContent('LayerName')figma.children('LayerName') or figma.children('*')figma.nestedProps('LayerName', { ... })Never invent properties that don't exist in Figma.
hover, pressed, focused, state, interactionPrimary → 'primary', Small → 'sm'true/falseCode Connect snippets are strings, NOT executed code.
NEVER use:
{hasIcon && <Icon />}
{disabled ? 'disabled' : ''}
{icon || <Fallback />}Instead, use mapping objects:
figma.boolean('Has Icon', {
true: <Icon />,
false: undefined
})// String property
figma.string('Label')
// Boolean property (simple)
figma.boolean('Disabled')
// Boolean with mapping
figma.boolean('Has Icon', {
true: <Icon />,
false: undefined
})
// Conditional string based on boolean
figma.boolean('Has label', {
true: figma.string('Label'),
false: undefined
})
// Enum/Variant property
figma.enum('Size', {
'Small': 'sm',
'Medium': 'md',
'Large': 'lg'
})
// Text content from a layer
figma.textContent('Button Label')
// Instance swap property (nested component)
figma.instance('Icon')
// Child instances by layer name
figma.children('Tab')
figma.children(['Tab 1', 'Tab 2'])
figma.children('Icon*') // wildcard
figma.children('*') // all children// Nested props - access child component's properties on parent
figma.nestedProps('Button Shape', {
size: figma.enum('Size', { ... })
})
// className builder
figma.className([
'btn-base',
figma.enum('Size', { 'Large': 'btn-large' }),
figma.boolean('Disabled', { true: 'btn-disabled', false: '' })
])
// Instance with type inference
figma.instance<React.FunctionComponent>('Icon') // Returns component type
figma.instance<string>('Icon') // Returns string ID
// Access nested instance props in parent
figma.instance('Icon').getProps<{ iconId: string, size: 'sm' | 'lg' }>()
// Custom render for nested instance
figma.instance('Icon').render<{ id: string }>(props => <CustomIcon id={props.id} />)Only use this pattern when different Figma variants map to entirely different React components. If all variants map to the same React component with different props, use a single figma.connect():
figma.connect(PrimaryButton, 'https://...', {
variant: { Type: 'Primary' },
example: () => <PrimaryButton />
})
figma.connect(SecondaryButton, 'https://...', {
variant: { Type: 'Secondary' },
example: () => <SecondaryButton />
})
// Boolean variant restriction
figma.connect(IconButton, 'https://...', {
variant: { 'Has Icon': true },
example: () => <IconButton />
})
// Multiple variant combination
figma.connect(DangerButton, 'https://...', {
variant: { Type: 'Danger', Disabled: true },
example: () => <DangerButton />
})import figma from '@figma/code-connect'
import { Button } from './Button'
figma.connect(Button, 'https://figma.com/design/abc123/File?node-id=1:2', {
props: {
variant: figma.enum('Variant', {
Primary: 'primary',
Secondary: 'secondary'
}),
size: figma.enum('Size', {
Small: 'sm',
Medium: 'md',
Large: 'lg'
}),
disabled: figma.boolean('Disabled'),
label: figma.textContent('Label'),
icon: figma.boolean('Has Icon', {
true: figma.instance('Icon'),
false: undefined
})
},
example: ({ variant, size, disabled, label, icon }) => (
<Button variant={variant} size={size} disabled={disabled} icon={icon}>
{label}
</Button>
)
})// Icon component
figma.connect('https://...icon-url...', {
example: () => <IconHeart />
})
// Parent using the icon
figma.connect(Button, 'https://...button-url...', {
props: {
icon: figma.instance('Icon')
},
example: ({ icon }) => <Button>{icon}</Button>
})
// Renders: <Button><IconHeart/></Button>// Icon returns component reference (not JSX)
figma.connect('https://...icon-url...', {
example: () => IconHeart // No angle brackets
})
// Parent receives component type
figma.connect(Button, 'https://...', {
props: {
Icon: figma.instance<React.FunctionComponent>('Icon')
},
example: ({ Icon }) => <Button Icon={Icon} />
})
// Renders: <Button Icon={IconHeart} />// Icon returns string ID
figma.connect('https://...icon-url...', {
example: () => 'icon-heart'
})
// Parent uses string
figma.connect(Button, 'https://...', {
props: {
iconId: figma.instance<string>('Icon')
},
example: ({ iconId }) => <Button iconId={iconId} />
})
// Renders: <Button iconId="icon-heart" />These mistakes produce Code Connect files that fail silently or publish incorrect mappings:
get_design_context property names. MCP normalizes them to camelCase. The actual Figma property names are Title Case with spaces (e.g., Has Icon, ButtonType, Size). Use get_metadata output or the raw variant names from evidence files.proposed-api.md lists a prop like className that has no Figma source, omit it from Code Connect entirely.{hasIcon && <Icon />} is invalid — Code Connect snippets are static strings. Use figma.boolean('Has Icon', { true: <Icon />, false: undefined }) instead.tsc --noEmit check. Run it after writing the .figma.tsx file. A type error in the Code Connect file will break the publish step.hover, focus, pressed, active Figma variants have no corresponding props — exclude them from all figma.enum() and figma.boolean() calls.proposed-api.md by path during generation. The mapping contract must be inlined into your working context in Step 3. Reaching back to re-read it mid-generation means the context wasn't loaded correctly.Write raw file content only—no markdown fences, no explanations.
File location: {ComponentFolder}/{ComponentName}.figma.tsx
Example: src/components/inline-edit/EditableText/EditableText.figma.tsx
File must be immediately usable with npx @figma/code-connect connect publish.
© bitovi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in figma/figma-connect-component of bitovi/ai-enablement-prompts.
Open the folder on GitHubat commit df229b1
Figma Connect Component next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Figma Connect Component this skillbitovi/ai-enablement-prompts | 121 | — | ~3.3k | Automated safety check: Pass | MIT | |
| Wonder BlocksKhan/wonder-blocks | 163 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Loora Design Guidelassejlv/loora | 140 | — | ~2.4k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Useshepherdjerred/monorepo | 112 | — | ~946 | Automated safety check: Pass | GPL-3.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Integrating shadcn/ui Componentsgoogle-labs-code/stitch-skills | 8.4k | 4 repos | ~2.3k | Automated safety check: Notes | Apache-2.0 |
Khan/wonder-blocks
Implements user interfaces using the Wonder Blocks (WB) design system — Khan Academy's React component library.
lassejlv/loora
Build, edit, refine, troubleshoot, and review polished responsive product interfaces through the Loora MCP server and its structured Canvas schemas.
shepherdjerred/monorepo
This skill should be used when the user asks to "create a Figma design", "design in Figma", "make a Figma mockup", "create an app icon", "design UI", "render JSX to Figma", "export from Figma"…
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
google-labs-code/stitch-skills
Guides finding, installing, customizing and wiring up shadcn/ui components in a project, with MCP tools for the component catalog and registries.
warpdotdev/warp
Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.
bitovi/ai-enablement-prompts
Track reusable UI components and unextracted patterns. An agent skill from bitovi/ai-enablement-prompts.
bitovi/ai-enablement-prompts
Extract and compare computed CSS styles between a baseline URL and a dev/Storybook URL using Playwright MCP evaluate calls.
bitovi/ai-enablement-prompts
A skill your agent uses when the user asks to "create a plugin", "add a plugin", "make a new plugin", "build a plugin", or wants to package skills into an installable plugin for this marketplace.
bitovi/ai-enablement-prompts
Create React components, hooks, or utilities following the modlet pattern.
bitovi/ai-enablement-prompts
A skill your agent uses when the user asks to "create a skill", "add a skill", "make a new skill", "build a skill", or wants to automate a repeated workflow into a reusable prompt.
bitovi/ai-enablement-prompts
Create new Agent Skills for this project. An agent skill from bitovi/ai-enablement-prompts.
Works with
Categories
Generate Figma Code Connect mappings that link React components to their Figma counterparts. Figma Connect Component is an agent skill from bitovi/ai-enablement-prompts. Generate Figma Code Connect mappings that link React components to their Figma counterparts.
Figma Connect Component fits situations like: A component exists in code and needs a Code Connect file so Figma shows real code snippets in Dev Mode; phrases like connect this component to Figma; generate Code Connect; publish to Figma.
Run `npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a claude-code`. Or copy the skill folder (figma/figma-connect-component in bitovi/ai-enablement-prompts) into .claude/skills/figma-connect-component in your project. Claude Code loads it when a task matches its description.
Run `npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a codex`. Or copy the skill folder (figma/figma-connect-component in bitovi/ai-enablement-prompts) into .agents/skills/figma-connect-component in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bitovi/ai-enablement-prompts --skill figma-connect-component -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/figma-connect-component, .gemini/skills/figma-connect-component, .github/skills/figma-connect-component and .opencode/skills/figma-connect-component in your project.
Going by SKILL.md and its folder, Figma Connect Component needs the command-line tools its instructions call (tsc and npx).
SKILL.md names 1 domain. In commands or code: figma.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Figma Connect Component is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Figma Connect Component: Wonder Blocks (Khan/wonder-blocks, 163 stars), Loora Design Guide (lassejlv/loora, 140 stars), Figma Use (shepherdjerred/monorepo, 112 stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
bitovi (a GitHub organization) maintains it in bitovi/ai-enablement-prompts, which has 121 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on September 11, 2026.
Source: bitovi/ai-enablement-prompts on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.