accessibility-patterns
WCAG 2.2 AA compliance, ARIA patterns, keyboard navigation, screen reader optimization
@vibeevalInstall SkillDevelopment
Skill
/factcheck-guard
Verify claims about code behavior, existence, or absence with the relevant implementation and execution evidence.
Claude Code
$ npx -y skills add vibeeval/vibecosystem --skill factcheck-guard --agent claude-code
Codex
$ npx skills add vibeeval/vibecosystem --skill factcheck-guard -a codex -y
Cursor
$ npx skills add vibeeval/vibecosystem --skill factcheck-guard -a cursor -y
Gemini CLI
$ npx skills add vibeeval/vibecosystem --skill factcheck-guard -a gemini-cli -y
GitHub Copilot
$ npx skills add vibeeval/vibecosystem --skill factcheck-guard -a github-copilot -y
OpenCode
$ npx skills add vibeeval/vibecosystem --skill factcheck-guard -a opencode -y
Windsurf
$ npx skills add vibeeval/vibecosystem --skill factcheck-guard -a windsurf -y
SKILL.md
factcheck-guard.SKILL.mdname: factcheck-guard description: Verify claims about code behavior, existence, or absence with the relevant implementation and execution evidence.
Verify Code Claims
Use search to locate evidence, then read the relevant implementation and callers. A matching name or comment does not establish live behavior.
For a behavior claim, follow the applicable branch, configuration, state and errors. Exercise the public entry point when runtime behavior matters. Distinguish source inspection from a reproduced result; cite the supporting location and the scope of any test.
For absence claims, inspect likely entry points and alternate names before concluding. Prefer a bounded statement such as "no registration in this manifest" over an unproven repository-wide claim.
State uncertainty candidly when evidence is missing. Do not invent percentages, force confidence labels into every sentence, or imply tests ran because their source exists. Prioritize evidence that resolves the user's decision; avoid ritual searches and full-file reads unrelated to it.
Stats
549
Stars
45
Forks
Active
Maintenance
C#
Language
MIT
License
Last commit
Created
Ships withvibecosystem
A focused runtime for Claude Code. A bounded worker for Codex. Catalog (in repo): Default core: vibecosystem packages agents, skills and hooks for software work.
547200 skills138 agents
Stars on GitHub
Momentum
- stars in total
- 547
Other skills on vibecosystem.
@vibeevalInstall Skillaccessibility-testing
axe-core integration, WCAG 2.2 AA checklist, keyboard navigation testing, screen reader testing, and ARIA pattern validation.
@vibeevalInstall Skillachievements
Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements…
@vibeevalInstall Skillagent-benchmark
Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when…
@vibeevalInstall Skillagent-linter
Agent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik…
@vibeevalInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about factcheck-guard.
- Which coding agents can use factcheck-guard?
- factcheck-guard installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.