Agent skill

Review Doc

by Endava in Endava/BEEQ

Audit a BEEQ Mintlify MDX documentation page against the documentation guidelines — component docs, non-component docs, CodeLivePreview behavior, code tab rules, source accuracy, tone, and…

Apache-2.0Auto-check passedFrontend & Design

Install Review Doc

skills CLI
$ npx skills add Endava/BEEQ --skill review-doc -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Endava/BEEQ review-doc --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Endava/BEEQ.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/review-doc .claude/skills/review-doc && rm -rf skills-src

Use ~/.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/

Facts

Skill name
review-doc
GitHub stars
163
Token cost
~4.1k tokens
SKILL.md length
1,749 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
Apache-2.0

At a glance

Audit a BEEQ Mintlify MDX documentation page against the documentation guidelines — component docs, non-component docs, CodeLivePreview behavior, code tab rules, source accuracy, tone, and…

  • Works in 5 steps: Temporary Zeroheight migration check… → Load the authoritative rules → Locate and read the files → …
  • Tasks that involve Markdown
  • SKILL.md covers When to Use, When NOT to Use, Step 0 — Temporary Zeroheight… and 1. Load the authoritative rules, plus 4 more sections
  • Reaches storybook.beeq.design

What it does

Review Doc is an agent skill from Endava/BEEQ. Audit a BEEQ Mintlify MDX documentation page against the documentation guidelines — component docs, non-component docs, CodeLivePreview behavior, code tab rules, source accuracy, tone, and accessibility guidance. Also supports temporary Zeroheight-to-Mintlify migration audits when explicitly requested or confirmed.

Its SKILL.md is about 4.1k 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 Markdown and Design systems. The repository describes itself as: BEEQ Design System, a web component library ruled by Endavan developers :). The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Markdown
  • Tasks that involve Design systems

Example prompts

  • “/review-doc”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Temporary Zeroheight migration check (optional)
  2. Load the authoritative rules
  3. Locate and read the files
  4. Audit checklist
  5. Report format

What it can do on your machine

Read from SKILL.md and the folder at commit 5f4728d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • storybook.beeq.design

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Doc loads about 4.1k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 1,749 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~4.1k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from Endava/BEEQ at commit 5f4728d, republished under its Apache-2.0 licence (© Endava). 1,749 words, ~4,070 tokens.

Download SKILL.mdSave it as .claude/skills/review-doc/SKILL.md (or your agent's skills folder).
name
review-doc
description
Audit a BEEQ Mintlify MDX documentation page against the documentation guidelines — component docs, non-component docs, CodeLivePreview behavior, code tab rules, source accuracy, tone, and accessibility guidance. Also supports temporary Zeroheight-to-Mintlify migration audits when explicitly requested or confirmed.
argument-hint
Component name (e.g. "card") or path to an .mdx file in apps/beeq-docs/
metadata.internal
true

Review a BEEQ Documentation Page

When to Use

  • Before merging a new or migrated MDX page in apps/beeq-docs/components/
  • Before merging a non-component MDX page in apps/beeq-docs/ such as foundations, theming, setup, framework integrations, or usage guides
  • When normalizing pages for consistency across the docs site
  • When a docs reviewer flags structure or tone issues
  • When migrating a page from Zeroheight to Mintlify and you want to verify the result (see Step 0)

When NOT to Use


Step 0 — Temporary Zeroheight migration check (optional)

This is a temporary migration-only check. Use it only when the user explicitly mentions a Zeroheight migration or when the current task context references Zeroheight. Do not run this check for ordinary docs reviews after the migration work is complete.

If either condition is met, ask for confirmation before proceeding:

"This looks like a migrated Zeroheight page. Do you want me to cross-check against the original Zeroheight source as part of this review?"

If the user confirms, use the mcp_beeq_zeroheig tools to fetch the original page content before starting Step 3:

mcp_beeq_zeroheig_list-pages        → find the page by component name
mcp_beeq_zeroheig_get-page          → fetch the original content
mcp_beeq_zeroheig_get-page-images   → fetch image references

Use the Zeroheight content to:

  • Cross-check that all When to use, Anatomy, Design guidelines, and Best practices content has been migrated — not silently dropped
  • Verify that image descriptions and anatomy part labels are preserved
  • Flag any content present in Zeroheight that has no equivalent in the new MDX page
  • Flag stale values or wording that conflict with current source

Add a Zeroheight Migration section to the report (see Step 4) if this step is executed.


1. Load the authoritative rules

Read .github/instructions/documentation.instructions.md in full before starting any checks. Every checklist item below maps to a rule in that file.


2. Locate and read the files

Resolve the target file:

  • If $ARGUMENTS is a component name → apps/beeq-docs/components/$ARGUMENTS.mdx
  • If $ARGUMENTS is a file path → read it directly

Read the full MDX file before running any checks.

If the target is a component page in apps/beeq-docs/components/, read the component source to verify API table accuracy:

  • packages/beeq/src/components/$ARGUMENTS/bq-$ARGUMENTS.tsx — @Prop, @Event, @slot, @part, @cssprop
  • packages/beeq/src/components/$ARGUMENTS/scss/bq-$ARGUMENTS.variables.scss — CSS custom properties and defaults
  • packages/beeq/cem/ — Custom Elements Manifest as canonical API reference

If the target is a non-component page, read the source files that define the documented behavior, values, or utilities. Examples include Tailwind theme files, reset styles, global CSS variables, integration setup files, or snippets used by the page. Current repo source is canonical over older docs.


3. Audit checklist

A. Page structure and section order — component pages
  • Frontmatter present with title and description
  • All imports immediately after frontmatter, using absolute paths (e.g. /snippets/…); no unused imports
  • Overview Frame with light + dark image pair is the first content after imports
  • Introduction paragraph (1–2 sentences, no ## heading) immediately follows the overview frame
  • Optional Note present only when there is a gotcha that affects all uses
  • When to use section present as a 2-column CardGroup
  • Optional Patterns section present only when real-world contexts genuinely add value
  • Anatomy section present with Frame + parts table (Part / Element / Description columns)
  • Design guidelines section present using CardTile, Steps, or Note as appropriate
  • Usage section present with at least one CodeLivePreview + CodeGroup
  • Options section present for additional configurations
  • Best practices section present as a 2×2 CardGroup (minimum 4 Do/Don't pairs = 8 cards)
  • Accessibility section present
  • API reference section present with all four subsections
  • Resources section is the last section with Storybook + GitHub source links
A2. Page structure and flow — non-component pages
  • Frontmatter present with title and description
  • Imports immediately after frontmatter, using absolute paths; no unused imports
  • Introduction clearly states what the page helps the reader understand or do
  • Page explains what BEEQ provides, recommends, or deliberately leaves to the consuming app
  • Core concepts are source-backed and written in a practical order
  • Values, utilities, classes, tokens, or setup steps match current source
  • Practical examples match the rendered CodeLivePreview
  • Usage guidelines are concise and scannable, using AccordionGroup, CardTile, or prose where appropriate
  • Accessibility, constraints, or implementation gotchas are included when relevant
  • Resources section appears last and links to relevant docs or source files
  • No visible Keywords section remains in migrated content
B. Images
  • Component image paths follow /components/images/[component]/[component]-[variant]-[light|dark].svg
  • Every image appears twice: className="block dark:hidden" (light) and className="hidden dark:block" (dark)
  • Overview Frame uses the -overview- variant; anatomy Frame uses the -anatomy- variant
  • No overview image re-used in the anatomy section
  • Non-component images are present only when they support a clear visualization; intentionally deferred placeholder assets are called out but not treated as content failures
C. When to use section
  • 2-column CardGroup with exactly one Do card and one Don't card
  • Do card: thumbs-up icon, color="var(--bq-stroke--success)"
  • Don't card: thumbs-down icon, color="var(--bq-stroke--danger)"
  • Both cards use bullet lists, not prose paragraphs
D. CodeLivePreview isolation
  • Every CodeLivePreview passes mode explicitly
  • New examples prefer mode="iframe" for full isolation from Mintlify CSS, scripts, and layout
  • Every iframe preview includes an explicit height
  • Iframe examples use removePadding when default preview padding would hide the real layout behavior
  • Shadow mode is used only for small, component-local examples that will not disrupt or be affected by the Mintlify page
  • Iframe examples use normal document CSS selectors inside the preview, not :host for preview layout
  • Shadow-mode examples use :host { ... } to override the shadow host layout — not @scope
  • Shadow-mode :host overrides use !important for properties that the CodeLivePreview stylesheet already defines (e.g., flex-direction, justify-content, gap, padding)
  • Descendant selectors (.my-class, bq-button, etc.) are plain selectors at the top level of <style> — no wrapper at-rule needed
  • No @scope { :scope {} } — this is the old light-DOM approach; flag any remaining instances as errors
  • No @scope (.class-name) — same reason
  • No <style scoped> — not a real browser feature
  • @media and @supports used normally inside <style> (no nesting restriction)
  • Every <script> inside a code prop wrapped in an IIFE: (() => { ... })()
  • Scripts use previewRoot to query elements, not document.currentScript
  • Scripts avoid document.querySelector in shadow mode because it cannot cross the shadow boundary; iframe mode may use document only when the script intentionally targets the isolated iframe document
  • No unnecessary wrapper <div> added only for alignment — use the preview mode's layout tools instead
  • When a wrapper <div> is genuinely needed, it has a BEM-style class name and is styled via a plain selector inside <style>
Show full SKILL.md (724 more words)Show less
E. CodeGroup framework tabs
  • Every CodeLivePreview is immediately followed by a CodeGroup
  • Tab order: CSS when needed → JavaScript when needed → HTML → React → Angular → Vue
  • Fenced code blocks used as Mintlify tabs include expandable only when they have more than 7 lines; short snippets and all apps/beeq-docs/index.mdx code tabs stay open
  • Icons are correct: CSS icon="css", JavaScript icon="js", HTML icon="html5", React icon="react", Angular icon="angular", Vue icon="vuejs"
  • One empty line separates each fenced code block inside a CodeGroup
  • Code tabs match the rendered CodeLivePreview structure, state, and behavior
  • HTML: kebab-case attributes (e.g. alt-text, only-icon)
  • HTML includes JavaScript inline when applicable, unless the script is long enough to justify a separate JavaScript tab
  • Angular: ts code block (not html); full standalone @Component; imports from @beeq/angular/standalone; all BEEQ components used in the template listed in imports; events use (bqEventName) binding syntax; no Angular modules — flag any plain html Angular blocks as errors
  • Angular examples use inline styles unless external CSS is critical to the example and appears in a CSS tab
  • React: camelCase props (e.g. altText, onlyIcon); events use onBqEventName handler props
  • React imports the CSS filename shown in the CSS tab when a CSS tab exists, for example import "./styles.css";
  • Vue: camelCase props (e.g. altText); events use @bqEventName binding syntax — never HTML attribute names
  • Vue examples use inline styles unless external CSS is critical to the example and appears in a CSS tab
  • Non-component pages omit framework tabs when they do not add value
F. CSS code tab

Only applies when a CSS tab is present in the CodeGroup:

  • CSS tab exists only when the styles are essential for understanding or reusing the example, not for incidental preview layout
  • CSS tab uses an explicit filename when React imports it, e.g. styles.css
  • Uses plain CSS selectors — not @scope (users manage their own scope)
  • Uses modern CSS nesting: & child, &::part(x), &:hover
  • Uses --bq-* CSS custom properties and design tokens, not hardcoded values
  • Uses CSS logical properties (margin-inline-start, not margin-left)
  • CSS tab omitted when the wrapper exists only for preview isolation (no copy-paste value for users)
G. Best practices section
  • 2×2 CardGroup with minimum 4 pairs (8 cards)
  • Do cards: check icon, color="var(--bq-stroke--success)"
  • Don't cards: xmark icon, color="var(--bq-stroke--danger)"
  • Pairs cover distinct aspects: layout, content, accessibility, consistency
  • Cards use a complete sentence or clear imperative — not just a label
H. Accessibility section
  • Documents what the component handles automatically (built-in role, aria-* attributes)
  • States which props feed each ARIA attribute (e.g. "label prop maps to aria-label")
  • Lists developer responsibilities (e.g. providing meaningful labels, managing focus)
  • Does not repeat API property descriptions already in the reference table
I. API reference
  • Properties table: columns Property, Attribute, Description, Type, Default
  • Slots table: columns Slot, Description
  • Shadow parts table: columns Part, Description
  • CSS custom properties: if >5 variables, wrapped in <Expandable title="CSS variables" defaultOpen={true}> (use defaultOpen={false} for very long lists, e.g. 20+); if ≤5 variables, displayed as a plain table with no <Expandable> wrapper. Columns Variable, Description, Default
  • CSS variables Default values use var(--bq-*) CSS custom properties — not Tailwind theme() function calls; hardcoded values (transparent, none, solid, unset, 0, 24px, etc.) are kept as-is
  • CSS variables table is accurate — cross-checked against bq-*.variables.scss
  • CSS variables section is followed by a <Tip> linking to /usage-guides/customizations/styles#component-shadow-dom-parts and /usage-guides/customizations/styles#global-css-custom-properties
  • No undocumented props, events, slots, or shadow parts relative to the component source
J. Resources section
  • 2-column CardGroup with exactly two horizontal Card components
  • First card: icon="code", links to https://storybook.beeq.design/?path=/story/components-[component]--default
  • Second card: icon="github", links to https://github.com/Endava/BEEQ/tree/main/packages/beeq/src/components/[component]
K. Tone and language
  • Plain, direct language — no internal jargon or Zeroheight/internal tool references
  • Active voice; short sentences
  • Second-person ("you") when addressing the reader
  • No filler phrases: "simply", "just", "easily", "note that", "please", "for clarity"
  • Sections explain why a pattern exists, not only what it does
  • No "also known as" alias definitions — use the correct term and trust the reader (anti-pattern 1)
  • No "once X is Y, you can Z" constructions — go straight to the action (anti-pattern 2)
  • Outcomes stated directly, not as hedged observations ("works well together when…") (anti-pattern 3)
  • <Note>, <Tip>, and <Warning> callouts give useful constraints or shortcuts — not disclaimers about documentation choices (anti-pattern 4)
  • Voice matches content type: reference pages (API, tables) are precise and scannable; guide pages are task-oriented and conversational
  • Non-component pages distinguish what BEEQ ships from what BEEQ recommends
  • Non-component pages do not imply BEEQ ships unavailable APIs, utilities, classes, tokens, or components

4. Report format

markdown
## Documentation Review: [page]

### Summary
<1–2 sentence overall quality assessment and top priority items>

### Results

For non-component pages, mark component-only categories such as API reference or When to use as `N/A` unless the page intentionally includes them.

| Category | Status | Issues |
|---|---|---|
| Page structure | ✅/⚠️/❌ | … |
| Images | ✅/⚠️/❌ | … |
| When to use | ✅/⚠️/❌ | … |
| CodeLivePreview isolation | ✅/⚠️/❌ | … |
| Framework tabs | ✅/⚠️/❌ | … |
| CSS code tab | ✅/⚠️/❌ | … |
| Best practices | ✅/⚠️/❌ | … |
| Accessibility | ✅/⚠️/❌ | … |
| API reference | ✅/⚠️/❌ | … |
| Resources | ✅/⚠️/❌ | … |
| Tone & language | ✅/⚠️/❌ | … |

### Issues

For each problem:
- **Location** — section heading or approximate line, as a markdown link where possible
- **Severity** — `error` (missing required section or broken behavior) | `warning` (inconsistency) | `suggestion` (improvement)
- **Rule** — the specific guideline from `documentation.instructions.md`
- **Fix** — the concrete, ready-to-apply change

### Zeroheight Migration (only if Step 0 was executed)
List any content present in Zeroheight that is absent from the new MDX page, and flag any stale values, images, labels, or wording that conflict with current source.

Example invocations

/review-doc card
/review-doc apps/beeq-docs/components/dropdown.mdx
/review-doc apps/beeq-docs/foundations/grid.mdx
/review-doc badge     ← I just migrated this from Zeroheight, please cross-check

© Endava, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/review-doc of Endava/BEEQ.

Open the folder on GitHubat commit 5f4728d

Compare with similar skills

Review Doc 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.

Review Doc compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Review Doc this skillEndava/BEEQ163—~4.1kAutomated safety check: PassApache-2.0
Building With Lobe UIlobehub/lobe-ui2.2k—~2kAutomated safety check: PassMIT
Using Docs Kitlobehub/lobe-ui2.2k—~2.8kAutomated safety check: PassMIT
Storybook Storyradix-ng/primitives274—~3.7kAutomated safety check: PassMIT
Build Resource Pagesonvoyage-ai/gtm-engineer-skills1.3k—~3.6kAutomated safety check: PassMIT
React Component Documentationgetsentry/sentry46k—~3.6kAutomated safety check: PassCustom licence

Similar skills

  • Building With Lobe UI

    lobehub/lobe-ui

    Build UI with the LobeHub design ecosystem — @lobehub/ui (plus its base-ui, chat, mobile, awesome, brand, mdx, i18n namespaces), @lobehub/icons, @lobehub/charts, @lobehub/fluent-emoji and…

    2.2k GitHub stars~2k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Using Docs Kit

    lobehub/lobe-ui

    Set up and author a documentation site with @lobehub/docs-kit (the lobedocs CLI, React Router + Vite static docs used by ui.lobehub.com).

    2.2k GitHub stars~2.8k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Storybook Story

    radix-ng/primitives

    Write or update Storybook stories and docs MDX for a Radix NG primitive following project conventions.

    274 GitHub stars~3.7k tokensUpdated 10 days ago
    Frontend & DesignAuto-check passed
  • Build Resource Pages

    onvoyage-ai/gtm-engineer-skills

    Takes existing content markdown files and builds production-final resource center pages on client websites using their existing tech stack and design system.

    1.3k GitHub stars~3.6k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed
  • Official

    Create or update component documentation in Sentry's MDX stories format.

    46k GitHub stars~3.6k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Ds Document Component

    baloise/design-system

    A skill your agent uses when writing or generating Storybook documentation for a Baloise Design System component — creates stories.ts, doc-config.ts, and six MDX subpages (Overview, Usage, Variants…

    114 GitHub stars~6.3k tokensUpdated yesterday
    Frontend & DesignAuto-check passed

More from Endava/BEEQ

All 9 skills in this repo
  • Beeq

    Endava/BEEQ

    Builds, styles, and reviews UI with BEEQ, Endava's web-component design system.

    163 GitHub stars~5.6k tokensUpdated today
    Auto-check passed
  • Create Component

    Endava/BEEQ

    Create a new BEEQ StencilJS web component. An agent skill from Endava/BEEQ.

    163 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Audit and fix WCAG 2.1 Level AA accessibility issues in BEEQ StencilJS components.

    163 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Review Component

    Endava/BEEQ

    Review a BEEQ StencilJS component against design system guidelines and project standards.

    163 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Write E2E Tests

    Endava/BEEQ

    Write E2E tests for BEEQ StencilJS components using @stencil/vitest in browser mode (Playwright/Chromium).

    163 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Write Stories

    Endava/BEEQ

    Write Storybook stories and MDX docs for BEEQ web components.

    163 GitHub stars~968 tokensUpdated today
    Auto-check passed

Questions about Review Doc

What does Review Doc do?

Audit a BEEQ Mintlify MDX documentation page against the documentation guidelines — component docs, non-component docs, CodeLivePreview behavior, code tab rules, source accuracy, tone, and…. Review Doc is an agent skill from Endava/BEEQ. Audit a BEEQ Mintlify MDX documentation page against the documentation guidelines — component docs, non-component docs, CodeLivePreview behavior, code tab rules, source accuracy, tone, and accessibility guidance.

When should I use Review Doc?

Review Doc fits situations like: tasks that involve Markdown; tasks that involve Design systems.

How do I install Review Doc in Claude Code?

Run `npx skills add Endava/BEEQ --skill review-doc -a claude-code`. Or copy the skill folder (.agents/skills/review-doc in Endava/BEEQ) into .claude/skills/review-doc in your project. Claude Code loads it when a task matches its description.

How do I install Review Doc in Codex?

Run `npx skills add Endava/BEEQ --skill review-doc -a codex`. Or copy the skill folder (.agents/skills/review-doc in Endava/BEEQ) into .agents/skills/review-doc in your project. Codex loads it when a task matches its description.

Can I use Review Doc in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Endava/BEEQ --skill review-doc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-doc, .gemini/skills/review-doc, .github/skills/review-doc and .opencode/skills/review-doc in your project.

What does Review Doc need to run?

SKILL.md names no scripts, command-line tools or credentials: Review Doc is instructions for the agent only.

Does Review Doc access the network?

SKILL.md names 1 domain. In commands or code: storybook.beeq.design; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Review Doc safe to install?

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.

What licence does Review Doc use?

Review Doc is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review Doc use?

About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Review Doc?

Skills that share tags, products or a category with Review Doc: Building With Lobe UI (lobehub/lobe-ui, 2.2k stars), Using Docs Kit (lobehub/lobe-ui, 2.2k stars), Storybook Story (radix-ng/primitives, 274 stars) and Build Resource Pages (onvoyage-ai/gtm-engineer-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Review Doc?

Endava (a GitHub organization) maintains it in Endava/BEEQ, which has 163 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 8, 2026.

Source: Endava/BEEQ on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.