Microck

Base UI reference and workflows for @base-ui/react (unstyled, accessible React components, composition utilities, and form helpers). Use when implementing Base UI components, portals, styling/state hooks, render-prop composition, eventDetails customization,…

Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.

Upload files to catbox.moe (permanent) or litterbox.catbox.moe (temporary). Use when you want to upload files for sharing via catbox services. Trigger phrases: "upload to catbox", "upload file", "share file via catbox".

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or…

Skill for creating auth layers in TypeScript/JavaScript apps using Better Auth.

Deep research with multi-stage verification pipeline inspired by Lutum Veritas. Use for comprehensive, verified research with claim audits and cross-referencing. Triggered by "deep research", "thorough research", or "/deep-research".

Design and analyze business models using the Business Model Canvas framework. Use when evaluating startups, planning new products, pivoting existing businesses, or understanding how companies create and capture value.

Guides Tailwind CSS v4 patterns for buttons and components. Use this skill when creating components with variants, choosing between CVA/tailwind-variants, or configuring Tailwind v4's CSS-first approach.

Terminal CLI for Kagi subscribers with search, quick answers, assistant, translate, summarization, batch processing, and JSON-first output for automation. Use this skill when the user mentions kagi, wants to search via kagi, needs CLI-based AI assistance, or…

Configure Kagi CLI credentials, profiles, lenses, custom bangs, redirects, site preferences, and account-backed assistants. Use when the user wants to inspect or change how Kagi authenticates, searches, or applies account settings.

Use Kagi's paid AI allowance for reasoning, coding, research, file analysis, structured generation, or model comparison. Use when a task should spend Assistant value instead of only searching the web or transforming one known page.

Use Kagi Assistant for conversational answers, thread continuity, attachments, streaming, model selection, or custom assistants. Use when the task benefits from an account-backed conversation rather than direct search or page extraction.

Search the web, extract or summarize a page, translate it, or check the news with the kagi CLI instead of WebSearch or WebFetch. Load this first for any Kagi task: it covers search and page content, and routes Assistant, automation, and account work to the…

Automate repeated Kagi queries with batch search, watches, notifications, history, caching, and MCP. Use when the user needs bulk processing, scheduled discovery, change detection, or a stable integration surface.

Setup Satelle hosts from an AI-agent workflow. Use when configuring a host, planning onboarding, installing or updating the Host Daemon, selecting provider auth, validating readiness, or preparing MCP/client integrations.

Recover Satelle failures. Use when setup, run, steer, status, logs, MCP, provider auth, readiness, transport, Host Daemon, or session operations fail or produce blockers.

Route Satelle work to the narrow setup, use, or recover skill. Use when an agent is asked to configure, operate, troubleshoot, or explain Satelle but the correct Satelle workflow is not obvious.

Operate Satelle sessions. Use when running prompts, steering existing sessions, checking status, reading logs, following events, stopping turns, choosing output formats, or continuing remote computer-use work.

Install Canonfig 2 from its scoped npm package and initialize a Source Machine or securely enroll a Linux, macOS, or Windows Follower Machine. Use for Canonfig prerequisites, package installation, first-time source setup, follower invitations and pinned…

Operate Canonfig 2 Source and Follower Machines safely. Use for discovery and proposal review, explicit profile publication, follower invitations, groups or revocation, profile selection, synchronization planning or apply, no-input automation, agent policy…

analyze a repo and generate seedance 2.0 montage packs (30s script + 5 segment mini-montage prompts) for software promos.

seedance 2.0 prompting reference - montage method, templates, asset planning, selection rubric.

Discord operations via CLI with daemon mode for fast execution. Send messages, read channels, list guilds and threads with persistent connection and auto-restart on code changes.

Install, configure, expose, verify, and troubleshoot Mullgate as an operator on a real machine. Use when the request is to actually use Mullgate rather than develop the Mullgate codebase, including first-run setup, non-interactive setup, Tailscale or…

Autonomous overnight code quality bot. 69 tasks across 7 categories with plan-implement-review architecture. 26 PR tasks + 43 issue tasks.

Operate gitquarry correctly for GitHub repository search, inspection, comparison, remote tree/code lookup, recipes, authentication, host selection, and script-safe output. Use when running gitquarry commands, choosing between native and discover search,…

Use when a user needs to manage Namecheap domains or DNS through the normal Namecheap website without registrar API access. Covers the working flow, the flaky parts, and the fastest fallback path.

Use Pangram's MCP tools for bounded AI detection, plagiarism, combined text analysis, task and bulk inspection, and explicitly enabled local history or configuration work. Use when an agent needs Pangram analysis, task or bulk polling, canonical result…

Remove formulaic AI-generated styling from existing web UI. Use when a page, component, or layout looks generic, templated, over-decorated, vibe-coded, or needs a final design cleanup while preserving behavior, brand, and accessibility.