pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-07 00:13
Agents & models
25,837 results
rivetkit-actors
Build stateful backends with Rivet Actors: high-performance, long-lived, in-memory, persisted processes. Use when you outgrow HTTP, databases, or queues.…
agent-cli
Design and review CLIs for AI agent consumption. Covers machine-readable output, input hardening against hallucinations, schema introspection, context window…
models-round-table
Answer a task by polling several models blind, then reconciling them into one consensus answer. Fan the RAW prompt out to five seats (Codex, Gemini, Kimi, Opus…
browser-harness
browser-harness — an installable skill for AI agents, published by roentek/claude_code_boilerplate_framework.
dropbox-automation
Automate Dropbox file management, sharing, search, uploads, downloads, and folder operations via Rube MCP (Composio). Always search tools first for current…
instagram-automation
Automate Instagram tasks via Rube MCP (Composio): create posts, carousels, manage media, get insights, and publishing limits. Always search tools first for…
claude-code-delegation
Delegate independent subtasks to `claude -p` instances. Use when you need to parallelize work across multiple files or modules that have no write conflicts.
qwen
Call the Qwen API (Qwen3.6, Qwen3.5, Qwen3-Coder-Next, and Qwen3-VL open-weight models) through RunAPI using OpenAI-compatible Chat Completions. Use for Qwen…
coordinate-team-work
Divide approved work among specialized RuFlo roles and keep task state synchronized.
launch-ai-team
Turn a reviewed goal into a bounded RuFlo AI team, run, and task plan without external side effects.
manage-team-lifecycle
Pause, resume, or complete a RuFlo AI team while preserving its tenant-local evidence.
monitor-ai-team
Report a RuFlo AI team's progress, blockers, task ownership, and remaining planned budget.
remember-team-context
Store and retrieve approved tenant-local team context with RuVector-backed isolation and provenance.
chrome-devtools
Use Chrome DevTools MCP for real-browser debugging: console and network inspection, runtime state checks, Lighthouse audits, and performance tracing. Use it…
grok-search
Use Grok Search MCP for planned web research: define intent, assess complexity, break the task into sub-queries, and then search, fetch, or map sources. Use it…
ref-skill
Use Ref MCP to search documentation sources and then read the exact returned URL. Use it for documentation-site discovery and page-level reading when the right…
sequential-thinking
Use Sequential Thinking MCP for explicit reasoning steps with revisions, branching, and uncertainty handling. Use it when the main need is to structure…
shrimp-task-manager
Use Shrimp Task Manager MCP for structured task analysis, decomposition, execution guidance, tracking, and verification. Use it when the main need is to manage…
agent-development
This skill guides creating autonomous agents for Claude Code plugins using markdown files with YAML frontmatter. Use when building new agents, designing agent…
changelog-interpreter
Interpret Claude Code changelogs and generate user-friendly usage guides
mcp-builder
This skill guides building high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when creating MCP…
skill-creator
This skill guides creating Claude skills—modular packages that extend capabilities with specialized knowledge and workflows. Use when creating new skills,…
empirical-prompt-tuning
Iteratively improve a skill or prompt by having a fresh subagent execute it against fixed scenarios, scoring two-sided (executor self-report + a pre-frozen…