Coding standards, frameworks, refactoring, and code review (16.4K skills)
Review HTML tables so screen reader users can understand how headers and data relate. Check header markup, table descriptions, and merged cells, then identify specific fixes and ways to verify them.
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 how pages return from the browser’s back/forward cache, which restores them from memory. Identify event handlers that block restoration, fix lifecycle assumptions, and refresh time-sensitive information when a cached page resumes.
Check checkboxes, radio buttons, and switches for descriptive names that screen readers can announce. Identify missing or unclear labels, suggest appropriate HTML or ARIA labeling, and explain how to verify the changes with accessibility tools.
Review dialogs to check whether screen readers can announce their purpose when they open. Identify missing or unclear labels, suggest title or label associations, and explain how to verify the changes with accessibility tools.
Review dynamic page updates so screen reader users hear status changes without moving focus. Check ARIA live regions, areas that announce updates, choose suitable announcement urgency, and identify markup or interaction issues to verify with accessibility tools.
Review meter elements for accessible names, the labels screen readers use to explain what a value measures. Identify missing labels, add aria-label or aria-labelledby, and describe checks using browser accessibility tools or assistive technology.
Check that ARIA roles, which describe interface elements to assistive technology, include their required attributes. Identify missing state or value information in rendered HTML and get guidance on fixes and accessibility verification.
Design and test rules for activating skills through human requests, AI selection, applications, or other skills. Check eligibility before matching descriptions, then return a JSON decision showing the selected channel, score, and policy reason.
Build a catalog from multiple skill directories using an explicit priority order. Review duplicate names, selection decisions, and omitted entries before loading the instruction text of the chosen skill.
Review database migration files before merging changes. It gathers evidence about what the changes do, rollback limits, database locks, and risks from large data volumes, then reports blockers when evidence needed for a decision is missing.
Review a reusable Agent Skill package before implementation. Validate its identity fields, separate instructions from external capabilities and execution timing, and receive a validation report with a minimal set of building blocks and reasons for each choice.
Explore ideas, investigate problems, and clarify requirements in an OpenSpec project through discussion grounded in existing code and specifications. Compare approaches, sketch diagrams, and identify open questions, with planning documents saved only within an explicitly approved scope.
Continue an existing OpenSpec change by creating one planning artifact, such as a proposal or specification, per request. Read its dependencies and workflow instructions, complete missing files when needed, and report progress and newly available steps.
Finalize an implemented OpenSpec change by checking planning files, task completion, and specification differences. Review whether to merge specification updates, verify any requested merge, then archive the change and report its location and outstanding warnings.
Archive several OpenSpec changes together after reviewing their documents and task progress. The skill checks code to resolve overlapping specification updates, syncs the selected updates, and reports which changes were archived, skipped, or failed.
Turn a feature idea or fix request into an OpenSpec implementation plan. The skill examines the project and prepares the required proposal, specification changes, design, and tasks for review, without changing project code.
Update main OpenSpec specifications from a change's delta specs, which describe specification changes. The skill merges requirement additions, edits, removals, and renames while preserving unrelated content, validates the results, and leaves the change active.
Revise an existing OpenSpec change plan and reconcile related planning documents. Incorporate new decisions, identify contradictions or gaps, and apply proposed document edits after confirmation, while leaving implementation code untouched.
Start an OpenSpec change for a feature, fix, or modification. Create its initial structure, show the workflow and current progress, and present the first planning document template for review before drafting any documents.
Implement pending tasks from an OpenSpec change using its specifications and design documents. The skill updates task checkboxes, confirms progress, supports resuming unfinished work, and pauses when requirements or implementation issues need clarification.
Prepare the OpenSpec documents needed to start implementation in one pass. It examines the project and creates required proposals, specifications, designs, and tasks in dependency order, following the project's configured workflow.
Use this integration guide to check API contracts, model choices, routing, and output requirements across audio, image, and video providers. It documents provider-specific constraints and resume behavior so production requests use an explicit host and model.
Improve GSAP animation performance by reviewing animated properties, browser layout work, and simultaneous updates. Use transforms, grouped updates, reusable animations, and targeted cleanup to reduce stuttering in lists, mouse followers, and scroll effects.