a11y-core
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched…
Reference data, not a reviewer. Search GitHub for issues, PRs, discussions, releases, and alerts. Includes query construction, date range handling, repo scoping, and cross-repo intelligence.
Claude Code
$ npx -y skills add Community-Access/accessibility-agents --skill kb-github-scanning --agent claude-code
Codex
$ npx skills add Community-Access/accessibility-agents --skill kb-github-scanning -a codex -y
Cursor
$ npx skills add Community-Access/accessibility-agents --skill kb-github-scanning -a cursor -y
Gemini CLI
$ npx skills add Community-Access/accessibility-agents --skill kb-github-scanning -a gemini-cli -y
GitHub Copilot
$ npx skills add Community-Access/accessibility-agents --skill kb-github-scanning -a github-copilot -y
OpenCode
$ npx skills add Community-Access/accessibility-agents --skill kb-github-scanning -a opencode -y
Windsurf
$ npx skills add Community-Access/accessibility-agents --skill kb-github-scanning -a windsurf -y
name: kb-github-scanning description: Reference data, not a reviewer. Search GitHub for issues, PRs, discussions, releases, and alerts. Includes query construction, date range handling, repo scoping, and cross-repo intelligence. license: MIT disable-model-invocation: true user-invocable: false metadata: tier: reference domain: cross-cutting output: none effort: low title: Github Scanning
Each intent, with its query pattern and scope.
| Intent | Query Pattern | Scope | |--------|--------------|-------| | Assigned to you | `is:issue is:open assignee:USERNAME` | All repos | | You were @mentioned | `is:issue is:open mentions:USERNAME` | All repos | | Authored by you | `is:issue is:open author:USERNAME` | All repos | | Specific repo | `is:issue repo:owner/repo is:open` | Single repo | | By keyword | `is:issue {keyword} is:open` | All repos | | Org-wide | `is:issue org:ORGNAME is:open` | Org repos | | Closed (for recap) | `is:issue is:closed author:USERNAME` | All repos |
Each intent, with its query pattern and scope.
| Intent | Query Pattern | Scope | |--------|--------------|-------| | Awaiting your review | `is:pr review-requested:USERNAME state:open` | All repos | | Your open PRs | `is:pr author:USERNAME state:open` | All repos | | Assigned to you | `is:pr assignee:USERNAME state:open` | All repos | | You reviewed, check for updates | `is:pr reviewed-by:USERNAME state:open` | All repos | | Specific PR | Fetch directly with owner, repo, number | Single repo | | Org-wide | `is:pr org:ORGNAME state:open` | Org repos |
Each intent, with its action.
| Intent | Action | |--------|--------| | You're mentioned | Search with `mentions:USERNAME` | | You're participating | Search discussions you've commented on | | High activity | Filter for 10+ comments in last 24h | | Linked to your issues | Scan description/comments for issue references |
---
Convert natural language to GitHub query qualifiers:
| User Says | GitHub Qualifier | |-----------|-----------------| | "last week" | `created:>YYYY-MM-DD` (7 days ago) | | "this month" | `created:>YYYY-MM-01` | | "today" | `closed:YYYY-MM-DD` | | "this week" | `closed:>YYYY-MM-DD` (7 days ago) | | "between X and Y" | `created:X..Y` | | Not specified | Use `search.default_window` from preferences (default: `updated:>YYYY-MM-DD` 30 days) - mention this assumption | | "for current month" (a11y tracker) | `milestone:"{Month} {Year}"` |
---
Add qualifiers to narrow by scope when the user specifies one:
| Scope | Qualifier | |-------|-----------| | Single repo | `repo:owner/name` | | All org repos | `org:orgname` | | All repos by user | `user:username` | | Everything (default) | No qualifier - searches all accessible repos |
---
Read `.github/accessibility-agents/preferences.md` (the user creates it from `docs/reference/preferences.example.md`) and apply these filters before and after searching. If that file does not exist, read `.github/agents/preferences.md` (the older location) and suggest moving it: VS Code loads every `.md` file in `.github/agents/` as a custom agent.
1. **`repos.discovery`** - determines the default search scope (all / starred / owned / configured / workspace). 2. **`repos.include`** - always include these repos even in restricted modes. 3. **`repos.exclude`** - skip these repos in all searches. 4. **`repos.overrides`** - per-repo settings:
5. **`search.default_window`** - default time range if the user doesn't specify one. 6. **`briefing.sections`** - which sections to include in the daily briefing. 7. **`accessibility_tracking`** - config for the a11y tracker (repos, labels, channels).
---
When results arrive from different repos, look for and surface these patterns:
| Pattern | Action | |---------|--------| | Cross-repo references | When issue A contains `owner/repo#N`, fetch and surface item N | | Shared label patterns | Group items in different repos tagged `P0` together in triage | | Related PRs in different repos | Flag: _"This issue depends on PR #N in repo-B which is still open"_ | | Merged PR not yet released | Note: _"Your PR #N is merged but not in any release yet"_ | | Issue with merged fix PR | Flag: _"This may be resolved - PR #N that closes it was merged on {date}"_ | | Branch naming patterns | Group PRs in different repos using the same branch naming convention |
---
For agents that collect from multiple data streams, run independent streams simultaneously.
WCAG 2.2 AA enforcement for agentic coding, as a set of Agent Skills. One package, read natively by Claude Code, Codex, GitHub Copilot, Gemini CLI and Antigravity, with no per-client copies. Models forget accessibility while generating code.
Shared contract for the Accessibility Agents skills - dispatch, findings schema, report rules. Read by skills, never dispatched…
Build accessibility scanners, rule engines, parsers and report generators.
Web UI accessibility lead. Use before writing or changing HTML, JSX, TSX, Vue, Svelte, CSS or templates. Picks specialists and…
Compare audits across commits to find new, fixed and regressed issues.
Generate a W3C or EU model accessibility statement from audit results.
GitHub Actions: workflow runs, logs, re-runs and CI failure triage.
Produce the "Playwright 1.xx API Review" artifact for a range of commits - the public API additions and the breaking or behavior…
Write, refine, run, and QA promptfoo evaluation suites: promptfooconfig.yaml, prompts, providers, vars, tests, assertions,…
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent,…