1.5K skills · sorted by relevance
Build a website prototype as a single HTML file using a supplied template and section layouts. Suitable for landing pages, pricing pages, and documentation indexes, with colors adapted to an existing design system.
Generate posters, key art, and editorial illustrations from a brief. The skill organizes composition, lighting, colors, and textures into an image prompt, then saves the result as a PNG or JPEG in the project folder.
Review documentation and prose against the Vercel Writing Guidelines, checking voice, tone, formatting, and structure. Findings identify files and line numbers, using a bundled guideline snapshot as the default reference for repeatable reviews.
Guide agents to produce complete code or written deliverables without omitted sections or placeholder comments. It checks the requested item count and defines clear stopping points and resume instructions when a response reaches its length limit.
Discover a UI/UX design resource during planning through this catalog entry. It identifies the upstream skill, but its pattern data, templates, and search tools require a separate installation before the full workflow can run.
Build polished web pages with explicit guidance for typography, spacing, colors, layered cards, and restrained animation. The skill provides layout options and mobile adaptation rules, producing React, Tailwind, or HTML code for a consistent visual direction.
Review interface animation code for timing, natural movement, responsiveness, rendering performance, and accessibility. Receive a table of specific problems, suggested changes, and reasons, followed by a clear decision on whether the motion meets the review standards.
Build React or Next.js interfaces with specific rules for typography, color, spacing, and animation. The skill guides responsive layouts, loading and error states, and performance-conscious interactions while preserving the original v1 design behavior.
Generate mobile app screen concepts and connected screen flows for iOS, Android, or cross-platform products. The skill emphasizes readable text, consistent colors and navigation, and clean phone mockups. It produces images rather than implementation code.
Build and review web animations with GSAP's core API, including movement, rotation, fades, and staggered starts. Adjust timing and easing, meaning changes in speed, and adapt animations to screen size and reduced-motion preferences.
Create a three-scene video composition in a retro pixel style using a Hyperframes HTML template. Customize titles, labels, and colors while preserving scene transitions, short scene durations, and repeatable animation timing.
Turn agent activity and transcript token counts into a cost report organized around completed outcomes. Separate estimates from measured spending, examine waste and rework, and export readable HTML with supporting JSON, CSV, and evidence.
Search persistent claude-mem memories to recover past decisions, solutions, and work history. Review compact search results, surrounding context, and selected details, or let the tool handle these steps automatically for a clear query.
Set up claude-mem for Grok Bot with a local worker and CMEM Pro service for recording observations. The skill also covers an optional host-login setup and remote cmem.ai connection, without requiring Cursor.
Review and strengthen security in claude-flow v3 by addressing dependency risks, password hashing, credential generation, input validation, file paths, and command execution. It also guides threat modeling and tests for security-critical code.
Check a DeerFlow installation from code updates through deployment and basic service checks. Supports local and Docker setups, verifies frontend pages and API health, and produces a report with results and troubleshooting recommendations.
Keep coding changes small by questioning unnecessary work and reusing existing code, standard libraries, and native platform features. Apply this approach to implementation, bug fixes, reviews, and dependency choices while preserving validation, security, and accessibility.
Read and update application settings through APIs, including system prompts, reasoning limits, IP filters, and login requirements. Also manage proxy and cache settings, with guidance on how reasoning settings affect requests sent to AI providers.
Set up OmniRoute and manage its command-line configuration. Inspect and validate tool settings, manage environment variables, check for updates, and control automatic startup using commands that support both interactive and unattended setup.
Inspect evolved prompt configurations, validate their structure, and view the system prompts they produce. You can also classify failures in run transcripts to support reviews before adopting or changing an agent policy.
Create a starter structure for a custom AI agent harness, the setup that supports agent execution. Choose a template and host, preview the plan, then explicitly confirm generation in a new directory outside the current project.
Review pending database migration SQL before applying schema changes. Check references between tables, rollback coverage, required defaults, destructive operations, and naming conventions, then report errors, warnings, and suggestions with file paths and line numbers.
Inspect local AGNTCY integration settings and summarize endpoint configuration, the optional SLIM package, transport status, and session counters in a short table. Distinguish available components from unimplemented features without making network calls or changing settings.
Dry-run one cycle of a sales agent workflow without calling language models. Validate the template and agent types, check budget reservations, generate agent prompts, and record a structured status summary for downstream automation.