aiskillstore/marketplace / skills/aakashh242/gauntlet
gauntlet
VerifiedEvidence-driven adversarial review and root-cause repair of code, designs, APIs, infrastructure, tests, and agent workflows. Use for deep reviews, red-team reviews, edge-case audits, production-readiness checks, or requests to find and fix defects iteratively. Supports sub-agents or a tracked solo workflow. Not for ordinary implementation or cosmetic edits unless explicitly invoked.
references/frontend-accessibility.md
View on GitHub# Frontend, accessibility, and interaction lens
Trigger: browser/app interaction, UI state, forms, asynchronous views, or client-side changes.
Trace user state across loading, success, error, retry, navigation, reconnect, cancellation, and unmount. Check stale responses overwriting newer input, duplicate submit, pending actions after logout/tenant switch, optimistic updates that cannot roll back, missing cleanup, and derived state drifting from the source of truth. Controlled deferred responses are more useful than fast happy-path mocks for races.
Inspect keyboard order, focus visibility and restoration, accessible names, semantic controls, disabled/error states, screen-reader announcements, contrast, zoom/reflow, motion preferences, touch targets, and non-color-only feedback where applicable. Use the project's target accessibility standard and primary official documentation when compliance is claimed. Do not call a visual inspection an accessibility certification.
Test responsive and overflow behavior with long labels, translated text, empty content, large content, and slow/failing requests. For forms, distinguish client guidance from server validation; the server still owns security and data invariants. Confirm destructive actions have the intended confirmation and recoverability, not simply a hidden button.
Inspect browser/server rendering boundaries, hydration assumptions, storage permissions, multi-tab state, history/back navigation, clipboard/file APIs, and focus traps only when present in the scope.
Evidence should identify the interaction sequence, snapshot, environment, expected/actual state, and screenshot or reproducible automated check where available. Test the original failure plus a neighboring schedule and normal behavior. If no browser is available, perform source-level review and explicitly label untested layout, accessibility, and runtime behavior.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |