Loading...
Loading...
Found 2,476 Skills
Run edit, real check, read the actual error, fix the root cause, rerun, until the check passes or the cap is hit. Use when you change code that has tests, a type checker, a build, or a runnable app, or before you claim any fix works. Invoke as /ds-verify-loop.
Use the HTTP client with sensible timeouts, retries, and backoff; capture context and handle failures explicitly
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Guide for setup Serena MCP server for semantic code retrieval and editing capabilities
Use when assembling assets a user already has into one finished video with Layer: sequencing clips, adding transitions, overlaying text, captions, a logo or a CTA, layering music or voice-over, or cutting a trailer, ad, or promo from generated shots. Also when a multi-shot piece needs to become a single deliverable file. Keywords: video editor, timeline, assemble, stitch, sequence, concatenate, transitions, overlay, captions, CTA, trailer, montage, render.
Use when an agent drives Unity 6.3 (6000.3) on a Mac for any task: batch mode and -executeMethod jobs, a running editor (the user's GUI editor or a headless one), the Unity CLI and com.unity.pipeline, MCP servers, the Test Framework, command-line builds; when a batch run fails silently, 'Scripts have compiler errors', a capture comes back black or pink, or a result must be proven with numbers and a frame; or when a Unity brief must go to the right scenario-unity-* specialist.
VMware Carbon Black Cloud Enterprise EDR authoring guidance — distinguishes process search query syntax (CBC search language) from watchlist feeds, scheduled searches, and live response. Covers indicator vs IOC discipline, watchlist subscription model, alert override / interrupt, sensor capability boundaries, and entity identifier alignment for cross-platform correlation. Use for carbon_black_cloud-keyed configurations in OpenTide MDR objects.
Use to build a hashtag and discoverability strategy for social posts — the modern (2026) approach, not the outdated "30 hashtags to go viral" playbook. Run when the user says "hashtags," "what hashtags should I use," "how many hashtags," "hashtag strategy," "help me get discovered/reach," asks "do hashtags still work / are hashtags dead," or asks how to tag a post. Reads brand-profile and audience first. Sets the keyword/social-SEO layer first (caption, on-screen text, spoken audio) because that — plus engagement and the content itself — drives discovery far more than hashtags now; then picks a tight, relevant, per-platform hashtag set (respecting caps like Instagram's enforced 5-tag limit), favors niche/mid-tier tags over generic mega-tags, and designs branded/campaign hashtags for community and tracking. Rotates sets rather than copy-pasting one block, and hands placement/publishing to scheduling-and-queue. Sets honest expectations: hashtags categorize and aid search; they are not a reach hack.
Select models and reasoning effort for implementation, review, recommendations, or delegated agent work using required capability, cached costs, and unresolved reasoning.
Plan a week or a month of YouTube uploads - what to post, when, and in what order, sized to the creator's actual capacity. Use for "plan my week", "content calendar", "what should I post", "I have no idea what to make next".
Create, revise, review, and audit prompts for clear, bounded handoffs to another agent or conversation. Validate findings and status responses brought into the current conversation. Use this skill when work must continue with an external agent or in an environment with the required access, when results or decisions need to move between conversations, or when a user message primarily contains pasted findings or a status response, even without an explicit request to act. Also use it for explicitly requested subagent prompts, reusable relay maintenance, and decision capture prompt maintenance. Do not use for autonomous in-client delegation. Do not treat archival, explicitly deferred, illustrative, or incidental agent text as an inbound handoff, or outdated agent text unless the user requests reassessment.
Clone a website — two modes. SNAPSHOT = a faithful, self-contained offline copy of a page (HTML+CSS+JS+images in one file, exact bytes, SingleFile-style). RECONSTRUCT = AI reverse- engineer the page into a clean editable Next.js/Tailwind codebase (design tokens → component specs → parallel builders → visual-diff QA, the ai-website-cloner-template method). Use when the user wants to "clone this site", copy a page's design/UI + interactions, mirror a layout, save offline, or rebuild a site as editable code. Built-now-adapt-later: snapshot builtin works now; faithful live capture + the reconstruct pipeline are one-config engine adapters.