643 skills · sorted by relevance
Review decorative images and icons to prevent unnecessary screen reader announcements. Check empty alt text, aria-hidden, and relevant keyboard behavior, then suggest fixes for concrete accessibility issues without flagging decorative assets solely because they exist.
Review file upload interfaces for clear labels, accepted formats, size limits, and accessible progress and error messages. Check that keyboard and screen reader users can complete uploads, including alternatives to drag and drop.
Review rotating slideshows for accessibility and guide fixes to pause controls, keyboard navigation, and screen reader announcements. Check the rendered HTML and ensure the carousel respects users who request reduced motion in their device settings.
Review progress bars to ensure screen reader users can tell which task they represent. Add descriptive accessible names, check progress semantics, and verify value attributes when the current progress is known.
Check buttons, links, and other controls for clear accessible names, the labels used by assistive technology. Identify missing or vague names and suggest descriptive text or aria-label attributes that explain each action or destination.
Review buttons, links, and menu items to check whether screen readers announce their purpose. Identify missing accessible names, meaning labels available to assistive technology, and suggest fixes using text or ARIA attributes, with guidance for verification.
Review tooltips so their extra information is available to screen reader users. Check accessible names, meaning labels available to assistive technology, and links to the elements that trigger them, then suggest fixes and verification steps.
Review same-page links for accessible scrolling. Check that reduced-motion preferences disable animated scrolling, provide guidance for instant navigation, and verify that keyboard focus moves to the destination so users can continue navigating there.
Review rendered HTML for links, buttons, or inputs inside role="text" containers. Identify controls hidden from screen readers, suggest markup changes, and explain how to check keyboard access and screen reader output after fixing them.
Review ARIA roles, labels that tell assistive technology what page elements do, and correct invalid values. Prefer standard HTML controls where suitable, then check keyboard behavior, focus movement, and screen reader output to verify the changes.
Manage files and storage buckets in Tigris through its official CLI. Agents can upload and download objects, generate temporary sharing URLs, take snapshots, and manage access keys and permissions with structured JSON output.
Audit Kubernetes access rules to find excessive permissions and service account token abuse paths. Trace which users or workloads could gain cluster administrator access, then produce prioritized findings and recommendations for reducing permissions.
Turn text into audio files for narration, product demos, phone prompts, or accessibility reads using the OpenAI Audio API. Choose built-in voices and delivery directions, then generate a single clip or a batch of files.
Carry out website tasks in a remote browser, including expense submissions, authorized orders, and retrieving data behind a login. Personal browser profiles preserve sign-ins, while users handle login and verification screens themselves.
Tests whether an AI agent exposes real credentials embedded in accessible source code or configuration. It requests searches for keys, passwords, and private keys, then documents confirmed disclosures with file locations and conversation evidence.
Build JavaScript or TypeScript apps that interact with NEAR. This skill guides token transfers, smart contract calls, account and key management, transaction signing, and message authentication through near-api-js v7 examples.
Assess what exposed credentials can access in AWS, GCP, and Azure. Map permissions, test paths to higher privileges, and document demonstrated impact using benign test objects within an explicitly authorized assessment scope.
Handle Git and GitHub CLI commands blocked by a sandbox, an environment that restricts access. Retry only authorized commands on the host, then check authentication, repository status, or pull request details there.
Turn text into audio files for narration, product demos, phone prompts, or accessibility reads using the OpenAI Audio API. Choose built-in voices and delivery directions, then generate a single clip or a batch of files.
Test changed screens or explore an entire app in a real browser. Check interactions, accessibility, and mobile layouts, then document failures with screenshots, reproduction steps, expected results, and suggested fixes.
Diagnose GPU bugs in CUDA applications with NVIDIA Compute Sanitizer. Select the appropriate tool for memory access errors, shared-memory races, uninitialized reads, or synchronization faults, then build for source locations and interpret the diagnostic report.
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
The English summary is being prepared. Showing the original description.
Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: "connect to API", "add gateway", "connect to MCP server", "Lambda tools", "OpenAPI", "gateway target", "Cedar policy", "restrict tools", "policy engine", "gateway auth error", "store API key", "outbound credential", "env var API key", "API key None after deploy", "credential not available after deploy", "should this be a gateway target", "give my agent tools", "add tools to agent". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.
The English summary is being prepared. Showing the original description.
Map workforce roles and application actors to Algolia team permissions, API-key ACLs, and secured-key restrictions. Use when reviewing least privilege, tenancy, SSO requirements, or access rotation. Trigger with "Algolia RBAC", "Algolia SSO", or "Algolia tenant access".
The English summary is being prepared. Showing the original description.