commit
>
context7
>
deepwiki
>
linkup
>
tmux
>
fiction-workshop
Use when writing or editing novels, short stories, or any fiction manuscript. Trigger on: 'write fiction', 'edit my novel', 'developmental edit', 'line edit', 'character voice', 'plot hole', 'brainstorm', or fiction writing tasks.
narrative-nonfiction
Use when writing self-help books, memoirs, or prescriptive guides with story elements. Trigger on: 'self-help book', 'transformation arc', 'metaphor consistency', 'reader journey', 'exercise design', or narrative nonfiction projects.
timeboxed-iterating
Use when the user specifies a task and a duration, and the work should be done iteratively by subagents over that time period
agent-integration-testing
Use when the user requests integration testing, feature validation, or test plan execution
boost-modules
Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
bugbash
Systematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases. Produces a structured report with full reproduction evidence (exact commands, inputs, logs, and tracebacks) for every issue.
preact-buildless-frontend
Build-less ESM frontends that run directly in the browser without bundlers. Use this skill when creating static frontends, SPAs without build tools, prototypes, or when the user explicitly wants no Vite/Webpack/bundler. Covers import maps, CDN imports, cache-busting, hash routing, and performance patterns.
pull-llamacpp-model
Use when pulling or downloading a new llamacpp model. The active ROCm image (kyuz0/amd-strix-halo-toolboxes) fails to start in the ephemeral pull container without ROCm device access. Must temporarily switch to the standard CPU image.
run-llms
Comprehensive guide for setting up and running local LLMs using Harbor. Use when user wants to run LLMs locally, set up or troubleshoot Ollama, Open WebUI, llama.cpp, vLLM, SearXNG, Open Terminal, or similar local AI services. Covers full setup from Docker prerequisites through running models, per-service configuration, VRAM optimization, GPU troubleshooting, web search integration, code execution, profiles, tunnels, and advanced features. Includes decision trees for autonomous agent workflows and step-by-step troubleshooting playbooks.
tinygrad
Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural networks, training models, implementing tensor operations, working with UOps/PatternMatcher for graph transformations, or contributing to tinygrad internals. Triggers on tinygrad imports, Tensor operations, nn modules, optimizer usage, schedule/codegen work, or device backends.
turso-db
Install, configure, and work with Turso DB — an in-process SQLite-compatible relational database engine written in Rust. Use when the user needs to (1) install Turso DB, (2) create or query databases with the tursodb CLI shell, (3) use Turso from JavaScript/Node.js via @tursodatabase/database, (4) work with vector search or embeddings in Turso, (5) set up full-text search with FTS indexes, (6) configure transactions including MVCC concurrent transactions, (7) enable encryption at rest, or (8) use Change Data Capture (CDC) for audit logging.
backend-architect
Expert senior en architecture backend pour accompagner le développement (conception, implémentation, review, refactoring). Architecture hexagonale, DDD, SOLID, clean code, tests. Utiliser pour concevoir de nouvelles features, développer du code, reviewer, refactorer, ou résoudre des problèmes architecturaux.
security-guardian
Expert en sécurité applicative pour détecter les vulnérabilités, auditer le code, et guider les bonnes pratiques de sécurité. OWASP Top 10, authentification, autorisation, cryptographie, gestion de secrets. Utiliser pour audits sécurité, reviews de code sensible, conception de features sécurisées, ou résolution de failles.
jk
Jenkins CLI for controllers. Use when users need to manage jobs, pipelines, config.xml, runs, logs, artifacts, credentials, nodes, or queues in Jenkins. Triggers include "jenkins", "jk", "pipeline", "build", "job create", "job config", "config.xml", "run logs", "jenkins credentials", "jenkins node".
template-skill
Replace with description of the skill and when Claude should use it.
scientific-schematics
Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx). Specialized in neural network architectures, system diagrams, and flowcharts. Generates SVG/EPS in figures/ folder with automated quality verification.
dolphindb
DolphinDB 时序数据库完整技术文档与最佳实践。包含1490个技术文档 + 3份官方白皮书。涵盖数据库设计、流计算、量化回测、函数查询等全场景。
project-understanding
Use when you need a fast, reliable architecture or impact view in a large unfamiliar repo, especially under time pressure or tight context budgets where manual grep or folder inference would be risky.
browser-automation
Reliable, composable browser automation using minimal OpenCode Browser primitives.
article-extractor
This skill should be used when the user wants to "download article", "extract article", "save blog post", "get article text", or provides a web URL and asks to extract the main content without ads, navigation, or clutter. Saves clean, readable text from web articles and blog posts.
ship-learn-next
This skill should be used when the user wants to "turn this into a plan", "make this actionable", "create an action plan", "implement the advice", or has learning content (transcript, article, tutorial) and wants concrete implementation steps. Transforms passive content into shippable iterations using the Ship-Learn-Next framework.
tapestry
This skill should be used when the user says "tapestry <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or wants to extract content from a URL and create an action plan. Automatically detects content type (YouTube video, article, PDF) and orchestrates the full extract-to-plan workflow.
youtube-transcript
This skill should be used when the user provides a YouTube URL and wants to "download transcript", "get captions", "get subtitles", "transcribe video", or extract text content from a YouTube video. Handles manual subtitles, auto-generated captions, and Whisper transcription as fallback.
unicon
Help users add icons to their projects using the Unicon icon library. Unicon provides 19,000+ icons from Lucide, Phosphor, Hugeicons, Heroicons, Tabler, Feather, Remix, and Simple Icons. Use when adding icons to React, Vue, Svelte, or any web project; using the unicon CLI to search, get, or bundle icons; setting up .uniconrc.json config for icon management; generating tree-shakeable icon components; using the Unicon API for programmatic icon access; or converting between icon formats (SVG, React, Vue, Svelte, JSON).
unicon-mcp
Help users connect the Unicon MCP server to Claude Desktop, Cursor, and other MCP clients. Use when setting up MCP config, verifying installs, debugging MCP connection issues, or using Unicon tools for icon search and generation through AI assistants.
carbon-icons
Carbon Design System icon usage for React components. MANDATORY when any component includes an icon. Use when implementing UI components that need icons, building atoms/molecules/organisms with icon elements, or adding icons to buttons, inputs, navigation, or any other UI element. Covers icon imports, sizing, color, alignment, touch targets, and the V-Shield Design System icon labeling system.
figma-d3-react-ts
>
figma-illustration-import
Import vector illustrations from Figma as reusable React atom components. Use when a component or page needs a custom illustration (NOT a standard Carbon icon). Triggers on requests like 'implement this illustration from Figma', 'add this Figma illustration', 'create illustration component', or when a Figma node contains a multi-layer vector illustration (lock, envelope, microscope, etc.). BEFORE creating a new illustration, always check if it already exists in `apps/web-app/src/components/atoms/Illustration*.tsx` and `apps/web-app/public/assets/illustrations/`.
figma-storybook-workflow
STRICT pixel-perfect Figma to Storybook workflow with ENFORCED extraction and iterative component implementation. MANDATORY: Extract exact design → Implement → Iterate until perfect → Move to next. NO shortcuts, NO assumptions, NO batch processing. Use when implementing Figma designs as Storybook components with 100% accuracy requirement.
pix-storybook
Autonomous pixel-perfect Stencil component implementation using Figma MCP, Storybook, and Playwright MCP for visual testing and fixing.
pix
Launches an autonomous, pixel-perfect UI implementation loop using Figma MCP and Chrome.
pixel-perfect-ui
Autonomous pixel-perfect UI implementation loop for Next.js/React using Figma MCP and Playwright. Converts Figma designs to production-ready components with iterative visual validation. **AUTO-TRIGGERS** on ANY request to implement Figma designs including: 'implement this Figma', 'build this page/component from Figma', 'create from Figma design', 'implement design', 'build this block', 'create component from design'. Use for: (1) Building pages/components from Figma, (2) Pixel-perfect accuracy, (3) Responsive layouts, (4) Design token conversion.
stencil-atomic-design-system
Use when building a Stencil.js design system with Atomic Design methodology, design tokens, theming support, and slot-based components. Implements a multi-client architecture with standardized patterns for atoms, molecules, organisms, and templates.
stenciljs-component-development
Use when creating or modifying Stencil.js web components. Ensures components follow Stencil best practices, proper decorator usage, lifecycle methods, and TypeScript conventions.
storybook-story-writing
Use when creating or modifying Storybook stories for components. Ensures stories follow CSF3 format, properly showcase component variations, and build successfully.
ralph-tui-create-beads-rust
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI). Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads-rust as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads, br beads.
ralph-tui-create-beads
Convert PRDs to beads for ralph-tui execution. Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads.
ralph-tui-create-json
Convert PRDs to prd.json format for ralph-tui execution. Creates JSON task files with user stories, acceptance criteria, and dependencies. Triggers on: create prd.json, convert to json, ralph json, create json tasks.
ralph-tui-create-linear
Convert PRDs to Linear issues for ralph-tui execution. Creates a master issue (epic) with sub-issues for each user story. Triggers on: create linear issues, convert prd to linear, linear for ralph, ralph linear.
ralph-tui-prd
Generate a Product Requirements Document (PRD) for ralph-tui task orchestration. Creates PRDs with user stories that can be converted to beads issues or prd.json for automated execution. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
skill-creator
Guide for creating effective skills. This skill 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.
check-build-errors
Run compile and type-check commands and report failures
flutter-integration-tests
Best practices and patterns for writing Flutter integration tests using the integration_test package. Use when creating, reviewing, or improving integration tests in Flutter projects. Triggers on tasks involving integration_test/ directory, IntegrationTestWidgetsFlutterBinding, flutter drive commands, end-to-end testing, screenshot testing, golden file testing, or performance profiling in Flutter apps.
slop-remover
Remove AI-generated code slop and clean up code style
vercel-workflow
Best practices for using Vercel Workflow DevKit. Use when creating, modifying, or debugging workflows, steps, hooks, webhooks, or any durable function using the Workflow DevKit. Ensures proper usage of directives, error handling, serialization, streaming, and workflow patterns.
Page 209 of 1445 · 72244 results