pencil-mcp-get-style-guide-tags
Explore design style tags. Use to get design inspiration, such as 'Modern', 'Dark Mode', 'SaaS' directions.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Agents & models
25,109 results
pencil-mcp-replace-all-matching-properties
Global property batch replace. Use for global style adjustment, e.g., 'Replace all red backgrounds with brand blue'.
pencil-mcp-search-all-unique-properties
Global property search. Use for design audit, e.g., 'Find all nodes using red background
pencil-mcp-set-variables
Set or update design variables. Use to establish or maintain a Design Token system.
pencil-mcp-snapshot-layout
Get page layout structure snapshot. Use when you need to understand the current page's DOM-like tree structure to prepare for layout adjustments.
foundry-hosted-agent-copilotkit
Build and evolve agentic web apps that pair a CopilotKit React frontend with a Microsoft Agent Framework agent running as a Microsoft Foundry hosted agent,…
gologin-local-agent-browser-skill
Deprecated compatibility skill. Local GoLogin Orbita automation now belongs to gologin-agent-browser-skill and the unified gologin-agent-browser-cli. Use this…
agento11y-instrument
Sets up and instruments a developer's own LLM app or agent to send generations and agentic workflow to Grafana Agent Observability (the Agent Observability…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
llm-security
LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning,…
dune-mcp-skill
Use Dune MCP through UXC for blockchain table discovery, SQL query creation/execution, execution result retrieval, and visualization with help-first schema…
enode-webhooks
Receive and verify Enode webhooks. Use when setting up Enode webhook handlers, debugging signature verification, or handling EV and energy events like…
foreman
Run an explicitly requested delegation mode for substantial changes: the main agent decides and inspects while subagents write code. Use only when the user…
sentient
Manage, organize and ships your codebase. Use to test Claude Code hook blocking for dangerous commands.
iblai-router
Cost-optimizing model router for OpenClaw. Automatically routes each request to the cheapest capable Claude model (Haiku/Sonnet/Opus) using weighted scoring.…
meta-skills
Patterns for authoring/composing skills (MSF). May propose skill-file edits (confirm before write) and optional localhost $IMAGE_SERVER_URL review uploads.
agent-capability-analyzer
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static…
audit-agent-lifecycle
Audit agent lifecycle — validates agent execution capability against configuration. Accepts plugin path, runs 8 semantic audits (capability vs config…
claude-skills-overview-2026
Claude Code runtime skills router. Use when configuring SKILL.md frontmatter, discovery, invocation, hooks, context forks, substitutions, loading behavior, or…
dispatch
Orchestrate parallel agent dispatch as a manager — not a micromanager. Use when coordinating 2+ independent workers, running SAM task waves, relaying…
example-argument-substitution
Test harness for Claude Code skill argument substitution — demonstrates capture-block pre-declaration, XML tag referencing, unintentional variable corruption…
generate-task
Generates one worker task prompt conforming to the CLEAR + selective CoVe task design standard and swarm-task-planner structure. Use when creating or rewriting…
hook-creator
Guide for creating Claude Code plugin hooks — language selection heuristic (Node.js default, match project runtime when obvious), hooks.json configuration,…
implementation-manager
Manages feature implementation task state via SAM MCP tools. Use when querying task status, listing ready tasks, dispatching tasks for execution, updating task…