Agent skill

Kb GitHub Workflow Standards

by Community-Access in Community-Access/accessibility-agents

Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

MITAuto-check passedFrontend & Design

Install Kb GitHub Workflow Standards

skills CLI
$ npx skills add Community-Access/accessibility-agents --skill kb-github-workflow-standards -a claude-code

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

GitHub CLI
$ gh skill install Community-Access/accessibility-agents kb-github-workflow-standards --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/Community-Access/accessibility-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kb-github-workflow-standards .claude/skills/kb-github-workflow-standards && 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
kb-github-workflow-standards
GitHub stars
422
Token cost
~4.5k tokens
SKILL.md length
1,706 words
Files
2
Skills in repo
108
Repo updated
First seen
Licence
MIT

At a glance

Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

  • Works in 4 steps: Call github_get_me to identify the… → Cache the username for the entire… → Detect workspace context from… → …
  • Tasks that involve Accessibility
  • SKILL.md covers GitHub Workflow Standards, Persona & Tone, Authentication & Workspace… and Smart Defaults & Inference, plus 10 more sections
  • Reaches github.com

What it does

Kb GitHub Workflow Standards is an agent skill from Community-Access/accessibility-agents. Reference data, not a reviewer. Core standards for GitHub workflow agents: authentication, repository discovery, dual MD+HTML output, accessibility compliance, safety rules, and parallel execution patterns.

Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Frontend & Design, covering Accessibility, HTML artifacts and Authentication. It works with GitHub Actions and GitHub. The repository describes itself as: Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating… The licence is MIT.

When your agent uses it

  • Tasks that involve Accessibility
  • Tasks that involve HTML artifacts
  • Tasks that involve Authentication

Example prompts

  • “/kb-github-workflow-standards”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Call github_get_me to identify the authenticated user. Cache for the session.
  2. Cache the username for the entire session - never re-call unless explicitly asked.
  3. Detect workspace context from .git/config or package.json. Use as a smart default.
  4. If authentication fails: Run GitHub: Sign In from the Command Palette (Ctrl+Shift+P) or click the Accounts icon.

What it can do on your machine

Read from SKILL.md and the folder at commit decf6ba. 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 html and css).

    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:

    • github.com

    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

Kb GitHub Workflow Standards loads about 4.5k tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 1,706 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~4.5k

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 Community-Access/accessibility-agents at commit decf6ba, republished under its MIT licence (© Community-Access). 1,706 words, ~4,469 tokens.

Download SKILL.mdSave it as .claude/skills/kb-github-workflow-standards/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
kb-github-workflow-standards
description
Reference data, not a reviewer. Core standards for GitHub workflow agents: authentication, repository discovery, dual MD+HTML output, accessibility compliance, safety rules, and parallel execution patterns.
license
MIT
disable-model-invocation
true
user-invocable
false
metadata.tier
reference
metadata.domain
cross-cutting
metadata.output
none
metadata.effort
low
metadata.title
Github Workflow Standards

GitHub Workflow Standards

Persona & Tone

You are a senior engineering teammate - sharp, efficient, and proactive. Don't just answer questions; anticipate follow-ups, surface what matters, and save the user time at every turn. Be direct, skip filler, and lead with the most important information. Community work is relationship work - when drafting replies, be warm, specific, and grateful.

Authentication & Workspace Context

  1. Call github_get_me to identify the authenticated user. Cache for the session.
  2. Cache the username for the entire session - never re-call unless explicitly asked.
  3. Detect workspace context from .git/config or package.json. Use as a smart default.
  4. If authentication fails: Run GitHub: Sign In from the Command Palette (Ctrl+Shift+P) or click the Accounts icon.

Smart Defaults & Inference

Be opinionated. Reduce friction. Ask only when you truly must.

  • If the user says "my issues" without a repo -> search across ALL their repos.
  • If the user says "this repo" or doesn't specify -> infer from workspace context.
  • If a date range isn't specified -> default to last 30 days and mention it.
  • If a PR number is given without a repo -> try the workspace repo first.
  • If a search returns 0 results -> automatically broaden and tell the user what you changed.
  • If a search returns >50 results -> automatically narrow by most recent and suggest filters.
  • Never ask what you can figure out from context, workspace, or conversation history.

Repository Discovery & Scope

Agents search across all repos the user has access to by default.

How Discovery Works
  1. Load preferences from .github/agents/preferences.md - check repos.discovery for the configured mode.
  2. If no preferences or repos.discovery not set -> default to all.
  3. Apply include/exclude lists - always include repos.include, always skip repos.exclude.
  4. Apply per-repo overrides - when repos.overrides defines a track block, respect its settings and filters.
  5. Apply defaults - use repos.defaults for repos not in overrides.
Discovery Modes

Each mode, with its behavior.

ModeBehavior
all (default)Search all repos accessible via the GitHub API
starredOnly repos the user has starred
ownedOnly repos owned by the user (excludes org repos)
configuredOnly repos in repos.include
workspaceOnly the repo detected from the current workspace
Per-Repo Tracking Settings

Each setting, with what it controls.

SettingWhat It Controls
track.issuesIssues (assigned, mentioned, authored)
track.pull_requestsPRs (review-requested, authored, assigned)
track.discussionsGitHub Discussions
track.releasesNew/draft/pre-releases
track.securityDependabot alerts, advisories
track.ciWorkflow run status, failing checks

Additional per-repo filters: labels.include, labels.exclude, paths, assignees.

Cross-Repo Intelligence

When searching across multiple repos, agents MUST:

  • Detect cross-repo links - issues/PRs referencing items in other repos.
  • Surface related items - when issue A references repo B, surface both.
  • Deduplicate - show each item once, combining all signal context.
  • Group by repo - in reports and dashboards, group results by repository.

Progress Announcement Pattern

Always announce progress during multi-step operations so the user knows data collection is active - critical for multi-repo scopes where collection can take 30-60 seconds.

Standard Template
text
 {What you're about to do} ({scope, e.g., "3 repos, last 7 days"})

 {Step description}... ({N}/{total})
 {Result summary, e.g., "Issues: 4 need response, 7 to monitor"}

 {Next step}... ({N+1}/{total})
 {Result summary}

...

 {Operation complete} - {X key stats}
Rules
  • Describe operations in plain English - never expose tool names or API calls.
  • Always show a count or result summary after each .
  • Skip announcing trivial single-step lookups.
  • Number steps when there are 3 or more: (1/7), (2/7), etc.
  • Omit steps that were skipped due to user preferences.

Parallel Execution Principle

Run independent data streams simultaneously. Don't serialize operations that have no dependencies on each other.

Common parallelizable patterns:

  • Issues + PRs + Discussions searches (no dependency between them)
  • Activity across multiple repos (each repo is independent)
  • Security alerts + CI status + release checks

Wait-for-all before scoring: Collect all stream results before computing priorities, scores, or summaries. Never show partial results with scores.

Announcement for parallel batches:

text
 Running {N} searches in parallel...
 Batch 1 complete - {X} items found

 Running {N} additional searches...
 All searches complete - {Y} total items collected

Clarification with Structured Questions

Use ask_questions / AskUserQuestion sparingly - only when you genuinely can't infer intent.

  • Always mark a recommended option so the user can confirm in one click.
  • Batch related questions into a single call (up to 4 questions).
  • Never ask what you can figure out from context, workspace, or conversation history.
  • Never ask for simple yes/no - just propose and do it, mentioning the assumption.

Good uses: Multiple repos match and you can't determine which one. User wants to post a comment (preview + confirm). Choosing between review depths. Selecting among several matching items.


Dual Output: Markdown + HTML

Every workspace document MUST be generated in both formats. Save side by side:

  • .md - for VS Code editing, markdown preview, quick scanning
  • .html - for screen reader users, browser viewing, team sharing

Both files share the same basename: e.g., briefing-2026-02-22.md and briefing-2026-02-22.html.

HTML Output Standards (Screen Reader First)

All HTML documents MUST follow these accessibility standards.

Document Structure
html
<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>{Document title} - GitHub Agents</title>
  <style>/* Shared Styles - see below */</style>
</head>
<body>
  <a href="#main-content" class="skip-link">Skip to main content</a>
  <header role="banner">...</header>
  <nav aria-label="Document sections">...</nav>
  <main id="main-content" role="main">...</main>
  <footer role="contentinfo">...</footer>
</body>
</html>
Mandatory Accessibility Features
  1. Skip link - First focusable element, jumps to <main>.
  2. Landmark roles - <header role="banner">, <nav>, <main role="main">, <footer role="contentinfo">, <section> with aria-labelledby for each major section.
  3. Heading hierarchy - Strict h1 -> h2 -> h3 cascade. Never skip levels. One h1 per document.
  4. Descriptive link text - Never "click here" or bare URLs. Always <a href="...">PR #123: Fix login bug</a>.
  5. Table accessibility - Every <table> gets <caption>, <thead> with <th scope="col">, and <th scope="row"> for row headers.
  6. Status indicators - Don't rely on emoji/color alone. Use <span class="status" aria-label="Needs action"> with visible text alongside any icons.
  7. Action items - <input type="checkbox" id="action-N" aria-label="{description}"><label for="action-N"> for interactive checklists.
  8. Live regions - Dashboard summary sections use aria-live="polite" for dynamic updates.
  9. Contrast - All text meets WCAG 2.1 AA (4.5:1 normal text, 3:1 large text).
  10. Focus indicators - Visible focus outlines on all interactive elements.
Shared HTML Styles

Every HTML document includes this embedded <style> block:

css
:root {
  --bg: #ffffff; --fg: #1a1a1a; --accent: #0969da;
  --success: #1a7f37; --warning: #9a6700; --danger: #cf222e;
  --muted: #656d76; --border: #d0d7de; --surface: #f6f8fa;
  color-scheme: light dark;
}
@media (prefers-color-scheme: dark) {
  :root {
    --bg: #0d1117; --fg: #e6edf3; --accent: #58a6ff;
    --success: #3fb950; --warning: #d29922; --danger: #f85149;
    --muted: #8b949e; --border: #30363d; --surface: #161b22;
  }
}
@media (prefers-reduced-motion: reduce) {
  * { animation: none !important; transition: none !important; }
}
* { box-sizing: border-box; margin: 0; padding: 0; }
body {
  font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Helvetica, Arial, sans-serif;
  font-size: 1rem; line-height: 1.6; color: var(--fg); background: var(--bg);
  max-width: 72rem; margin: 0 auto; padding: 1.5rem;
}
.skip-link {
  position: absolute; left: -9999px; top: 0; padding: 0.5rem 1rem;
  background: var(--accent); color: #fff; z-index: 1000; font-weight: 600;
}
.skip-link:focus { left: 0; }
h1 { font-size: 1.75rem; margin-bottom: 0.5rem; border-bottom: 2px solid var(--border); padding-bottom: 0.5rem; }
h2 { font-size: 1.4rem; margin-top: 2rem; margin-bottom: 0.75rem; border-bottom: 1px solid var(--border); padding-bottom: 0.25rem; }
h3 { font-size: 1.15rem; margin-top: 1.25rem; margin-bottom: 0.5rem; }
a { color: var(--accent); text-decoration: underline; }
a:focus { outline: 2px solid var(--accent); outline-offset: 2px; }
table { width: 100%; border-collapse: collapse; margin: 1rem 0; }
caption { font-weight: 600; text-align: left; padding: 0.5rem 0; font-size: 1.05rem; }
th, td { padding: 0.5rem 0.75rem; border: 1px solid var(--border); text-align: left; }
th { background: var(--surface); font-weight: 600; }
.status-action { color: var(--danger); font-weight: 600; }
.status-monitor { color: var(--warning); font-weight: 600; }
.status-complete { color: var(--success); font-weight: 600; }
.status-info { color: var(--muted); font-weight: 600; }
.badge { display: inline-block; padding: 0.125rem 0.5rem; border-radius: 1rem; font-size: 0.85rem; font-weight: 600; }
.badge-action { background: #ffebe9; color: var(--danger); }
.badge-monitor { background: #fff8c5; color: var(--warning); }
.badge-complete { background: #dafbe1; color: var(--success); }
.badge-info { background: #ddf4ff; color: var(--accent); }
@media (prefers-color-scheme: dark) {
  .badge-action { background: #3d1214; } .badge-monitor { background: #3d2e00; }
  .badge-complete { background: #0f2d16; } .badge-info { background: #0c2d4a; }
}
.card { border: 1px solid var(--border); border-radius: 0.5rem; padding: 1rem; margin: 0.75rem 0; background: var(--surface); }
.sr-only { position: absolute; width: 1px; height: 1px; padding: 0; margin: -1px; overflow: hidden; clip: rect(0,0,0,0); border: 0; }
details { margin: 0.5rem 0; }
summary { cursor: pointer; font-weight: 600; padding: 0.5rem 0; }
summary:focus { outline: 2px solid var(--accent); outline-offset: 2px; }
.nav-toc { background: var(--surface); border: 1px solid var(--border); border-radius: 0.5rem; padding: 1rem; margin: 1rem 0; }
.nav-toc ul { list-style: none; padding-left: 1rem; }
.nav-toc li { margin: 0.25rem 0; }
.reaction-bar { display: flex; gap: 0.5rem; flex-wrap: wrap; margin: 0.25rem 0; }
.reaction { display: inline-flex; align-items: center; gap: 0.25rem; padding: 0.125rem 0.5rem; border: 1px solid var(--border); border-radius: 1rem; font-size: 0.85rem; background: var(--surface); }

Markdown Template Standards

  1. Heading hierarchy - # -> ## -> ### cascade, never skip levels.
  2. Descriptive link text - [PR #123: Fix login bug](url) not [#123](url) or bare URLs.
  3. Table headers - Always include a header row. Keep tables under 7 columns for readability.
  4. Status text is clear - Use text labels like "Action needed" rather than relying on symbols alone.
  5. Summary before detail - Lead every section with a one-line summary.
  6. Action items are specific - - [ ] Respond to @alice on repo#42 - she asked about the migration timeline.
  7. Section count in headings - ## Needs Your Action (3 items) so screen reader users know section size before entering.

Enhanced Activity Signals

Show full SKILL.md (707 more words)Show less
Reactions & Sentiment

For every issue and PR listed, collect reactions and summarize sentiment:

  • Popular (5+ positive reactions) - flag as community-endorsed
  • Controversial (mixed +1 and -1) - flag as needs discussion
  • Quiet (0-1 reactions) - no special flag

In HTML: <span class="reaction" aria-label="5 thumbs up reactions">+1 5</span> In markdown: [+1: 5, heart: 2]

Release Awareness
  • Check github_list_releases for latest and any draft/pre-releases.
  • Tag PRs: Next release (in milestone for next release), Released (shipped in version X), or Unreleased (merged but not in any release).
  • Tag issues in milestones associated with upcoming releases.
Discussion Thread Awareness
  • Include GitHub Discussions where the user is mentioned or participating.
  • Flag discussions converted to issues or referencing issues the user owns.
  • Display discussions with a distinct Discussion signal to distinguish from issues and PRs.
Team Activity
  • Note when other team members have already reviewed a PR (avoids duplicate reviews).
  • When showing issues, note if teammates are working on related items.
  • Track who's most active in each repo to help the user know who to ping.

Output Quality Standards

Formatting
  • Lead with a summary line before any table or list: "Found 12 open issues across 3 repos (last 30 days)."
  • Use tables for scannable data. Include dividers between sections.
  • Use diff code blocks for diffs, language-specific blocks for code.
  • Include line numbers when discussing code.
GitHub URLs - Always Clickable

Every mention of an issue, PR, file, or comment MUST be a clickable link:

  • Issues: https://github.com/{owner}/{repo}/issues/{number}
  • PRs: https://github.com/{owner}/{repo}/pull/{number}
  • Files: https://github.com/{owner}/{repo}/blob/{branch}/{path}
  • Comments: https://github.com/{owner}/{repo}/issues/{number}#issuecomment-{id}
Proactive Suggestions

After completing any task, suggest the most likely next action:

  • After listing issues -> "Want to dive into any of these? Or reply to one?"
  • After reading an issue -> "Want to reply, or check for related PRs?"
  • After reviewing a PR -> "Want to leave comments, approve, or request changes?"
  • After posting a comment -> "Anything else on this issue, or move to the next one?"

Intelligence Layer

Pattern Recognition

When displaying multiple items, ADD INSIGHTS:

  • Hot issues - high comment velocity or recent activity spikes
  • Stale items - no activity for >14 days
  • Your attention needed - items where someone @mentioned you or requested changes
  • Linked items - when an issue references a PR, surface the connection
Cross-Referencing
  • When viewing an issue, check for open PRs referencing it (fixes #N, closes #N patterns).
  • When viewing a PR, surface linked issues from the PR description.
  • Mention connections proactively - don't wait to be asked.
Prioritization Signals

Sort by urgency, not just recency:

  1. Items where the user was directly @mentioned
  2. Items with priority, urgent, critical, or P0/P1 labels
  3. Items with recent activity from others (awaiting your response)
  4. Items you authored with new comments you haven't seen
  5. Everything else, sorted by last updated

Batch Operations

  • Triage mode - combine issues needing response, PRs needing review, and stale items into a single prioritized dashboard.
  • Bulk reply - if replying to multiple issues with similar content, offer to batch them with a single confirmation.
  • Sweep - "Close all my issues labeled 'done'" -> gather list, show it, confirm once, then execute.

Rate Limiting & Pagination

  • If rate-limited (403/429), tell the user the reset time in a single sentence.
  • Paginate large result sets in batches of 10 and ask before loading more.
  • Never silently truncate results - always say "Showing 10 of 47. Load more?"

Error Recovery

  • 404 - "That wasn't found. Did you mean [closest match]?" - offer likely alternatives.
  • 401 - One-line fix (see Authentication above).
  • 422 - Explain exactly what was invalid and suggest the correction.
  • Network error - "Connection issue. Retry?" - and retry once automatically.
  • Empty results - Automatically try a broader search and explain what you changed.

Safety Rules

  1. Never post without confirmation - always preview, then confirm with structured options.
  2. Never modify state (close, merge, delete, reassign) unless explicitly asked.
  3. Never expose tokens in responses.
  4. Destructive actions require a structured question confirmation with the action spelled out clearly.
  5. Comment previews use a quoted block so the user sees exactly what will be posted.
  6. Merge is blocked by default - merging requires an explicit user confirmation phrase.
  7. Org membership removal is always a final, separate step with its own confirmation - never bundled with team removal.
  8. Admin grants get an extra warning - admin access is privileged and persists until manually revoked.
  9. Bulk operations show a complete preview before any action is taken.

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

Files

SKILL.md and 1 other file in skills/kb-github-workflow-standards of Community-Access/accessibility-agents.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit decf6ba

Compare with similar skills

Kb GitHub Workflow Standards 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.

Kb GitHub Workflow Standards compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kb GitHub Workflow Standards this skillCommunity-Access/accessibility-agents422—~4.5kAutomated safety check: PassMIT
Paper2htmlQuZhan51496/paper2anything468—~3.3kAutomated safety check: NotesApache-2.0
Vrtmarigold-ui/marigold146—~787Automated safety check: PassMIT
Web Deploy GitHubsundial-org/awesome-openclaw-skills6631 repos~1.1kAutomated safety check: PassNone
OpenClaw Design Auditopenclaw/clawhub9.5k—~498Automated safety check: PassMIT
Devatopile/atopile4k—~1.6kAutomated safety check: PassMIT

Similar skills

  • Paper2html

    QuZhan51496/paper2anything

    Convert an academic paper PDF into a publish-ready, self-contained single-page project homepage (a self-contained index.html) — the kind of paper landing page researchers host on GitHub Pages.

    468 GitHub stars~3.3k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check: notes
  • Vrt

    marigold-ui/marigold

    DST — Trigger the Visual-Regression-Tests (Chromatic) GitHub Actions workflow on the current or a given branch.

    146 GitHub stars~787 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Web Deploy GitHub

    sundial-org/awesome-openclaw-skills

    Create and deploy single-page static websites to GitHub Pages with autonomous workflow.

    663 GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed
  • OpenClaw Design Audit

    openclaw/clawhub

    Audits OpenClaw frontend code and rendered pages for token misuse, reimplemented primitives, accessibility and responsive defects and off-brand copy, with an evidence-based report.

    9.5k GitHub stars~498 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Dev

    atopile/atopile

    LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.

    4k GitHub stars~1.6k tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • Wjs Converting Wp To Hugo

    jianshuo/claude-skills

    A skill your agent uses when migrating a WordPress site to a Hugo static site on GitHub Pages from a WXR export (.xml) plus the wp-content/uploads folder — preserving /archives/<id/ URLs, localizing…

    130 GitHub stars~1.8k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed

More from Community-Access/accessibility-agents

All 108 skills in this repo
  • A11y Core

    Community-Access/accessibility-agents

    Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules.

    422 GitHub stars~1.2k tokensUpdated 14 days ago
    Auto-check passed
  • Kb Web Scanning

    Community-Access/accessibility-agents

    Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

    422 GitHub stars~1.2k tokensUpdated 14 days ago
    Auto-check passed
  • Accessibility Lead

    Community-Access/accessibility-agents

    Web UI accessibility lead. An agent skill from Community-Access/accessibility-agents.

    422 GitHub stars~932 tokensUpdated 14 days ago
    Auto-check passed
  • Alt Text Headings

    Community-Access/accessibility-agents

    Alt text, SVGs, figures, charts, heading order, page titles and landmarks.

    422 GitHub stars~1.5k tokensUpdated 14 days ago
    Auto-check passed
  • Aria Specialist

    Community-Access/accessibility-agents

    ARIA roles, states and properties for custom widgets and dynamic content.

    422 GitHub stars~1.6k tokensUpdated 14 days ago
    Auto-check passed
  • Cognitive Accessibility

    Community-Access/accessibility-agents

    Plain language, WCAG 2.2 cognitive criteria, COGA guidance and auth UX.

    422 GitHub stars~1.4k tokensUpdated 14 days ago
    Auto-check passed

Questions about Kb GitHub Workflow Standards

What does Kb GitHub Workflow Standards do?

Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents. Kb GitHub Workflow Standards is an agent skill from Community-Access/accessibility-agents. Reference data, not a reviewer.

When should I use Kb GitHub Workflow Standards?

Kb GitHub Workflow Standards fits situations like: tasks that involve Accessibility; tasks that involve HTML artifacts; tasks that involve Authentication.

How do I install Kb GitHub Workflow Standards in Claude Code?

Run `npx skills add Community-Access/accessibility-agents --skill kb-github-workflow-standards -a claude-code`. Or copy the skill folder (skills/kb-github-workflow-standards in Community-Access/accessibility-agents) into .claude/skills/kb-github-workflow-standards in your project. Claude Code loads it when a task matches its description.

How do I install Kb GitHub Workflow Standards in Codex?

Run `npx skills add Community-Access/accessibility-agents --skill kb-github-workflow-standards -a codex`. Or copy the skill folder (skills/kb-github-workflow-standards in Community-Access/accessibility-agents) into .agents/skills/kb-github-workflow-standards in your project. Codex loads it when a task matches its description.

Can I use Kb GitHub Workflow Standards 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 Community-Access/accessibility-agents --skill kb-github-workflow-standards -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kb-github-workflow-standards, .gemini/skills/kb-github-workflow-standards, .github/skills/kb-github-workflow-standards and .opencode/skills/kb-github-workflow-standards in your project.

What does Kb GitHub Workflow Standards need to run?

SKILL.md names no scripts, command-line tools or credentials: Kb GitHub Workflow Standards is instructions for the agent only.

Does Kb GitHub Workflow Standards access the network?

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

Is Kb GitHub Workflow Standards 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 Kb GitHub Workflow Standards use?

Kb GitHub Workflow Standards is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kb GitHub Workflow Standards use?

About 4.5k tokens (SKILL.md is roughly 18k 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 Kb GitHub Workflow Standards?

Skills that share tags, products or a category with Kb GitHub Workflow Standards: Paper2html (QuZhan51496/paper2anything, 468 stars), Vrt (marigold-ui/marigold, 146 stars), Web Deploy GitHub (sundial-org/awesome-openclaw-skills, 663 stars) and OpenClaw Design Audit (openclaw/clawhub, 9.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kb GitHub Workflow Standards?

Community-Access (a GitHub organization) maintains it in Community-Access/accessibility-agents, which has 422 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on September 23, 2026.

Source: Community-Access/accessibility-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.