Loading...
Loading...
Found 6,717 Skills
Use this skill whenever the user wants to use AI agents to work with Penpot design files via the Penpot MCP Server. Triggers include: using Penpot through an AI agent, design files, design systems, design tokens, Penpot MCP, design-to-code, generating UI from design, auditing a design system, creating components/variants, renaming layers, exporting assets from Penpot, adding flows, interactions, animations, overlays, or prototyping in Penpot, or prompting an AI agent to read/modify a Penpot file. Also triggers when the user wants to set up Penpot MCP, connect any MCP-compatible AI agent or IDE to Penpot, or produce production-ready HTML/CSS/React from a Penpot design. Use this skill for Penpot-agent workflows — design, code, audit, prototyping, or setup.
Draft, send, reply to, or forward email through the connected AgentMail MCP server. Use for ANY request to send, reply to, or forward mail — even a quick one-line send or a simple forward that looks like a single tool call; the sending rules apply regardless of task size. Also use to compose messages, create or schedule drafts for review, or send to named recipients; do not use for reading or triaging mail (agentmail-check-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
Use for any codebase exploration or understanding task — reads historical intent from Entire checkpoints instead of guessing. Orchestrates other Entire skills to give the agent provenance-backed answers about code.
Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs, and writes a prioritized stakeholder report (analysis.md). Use when the user asks to follow the analysis orchestrator, run the agentic analysis workflow, analyze a trace, compare two traces, or mentions standalone or comparative TraceLens analysis.
(NS) LangGraph.js agent-api — greenfield scaffold (bootstrap-agent-runtime), StateGraph, MCP tools, skill bind/inject, checkpointers, context-window trim, HITL/SSE, prompt/locale placement. Use for new agent-api from scratch, LangGraph graphs, MCP wiring, orphan layout, system-prompt compose, bind parity, graph-spec sync, or "fix my LangGraph agent" / "wire MCP tools" / "translations in the graph". Feature diffs via ns-coder; version features via ns-spec-driven; LangGraph vs CrewAI via ns-multi-agent-architect. Do NOT use for CrewAI crews, generic web apps, or SDD-only requirements with no agent-api.
UiPath AgentHub MCP server registration + resource-tool authoring via `uip agenthub mcp` (six server types: uipath / coded / command / remote / platform / swagger) and `uip agenthub mcp-tools` on `uipath`-type servers. For Python MCP servers / coded-agent integration→uipath-agents.
UiPath read-only reviewer — audit structure, quality, best practices for RPA (.xaml/.cs), agents (.py/agent.json), flows (.flow), BPMN (.bpmn), coded apps, solutions (.uipx). Does NOT edit files. For building/editing→domain skills.
Audit Agent Skills for what no validator can decide: whether a description will ever fire, whether the instructions are followable, whether the body earns its token cost, whether `compatibility` matches what the body requires, and whether mutations are gated. Runs the repo's structural validators first, scores five judgment categories with cited evidence, and returns a PASS / FAIL verdict.
Set up and maintain a repository's agent instruction layer — one real root instruction file, an AGENTS.md symlink so every agent reads the same document, a comment-convention block, and a drift check that catches documented commands, paths, structures, and counts that no longer match the repo.
Compact the current conversation into a handoff so a fresh agent, or future-you, can pick up the work cold. With a `doc`, `document`, or `--doc` keyword, writes a per-project handoff file and prints only its path plus a shortcut to start the next session.
Quick opinion from an agent CLI outside this session — ask a specific question with context, or review code changes. Picks an installed agent that is not the one running this skill, so the answer comes from a different model in a different process. Lighter and faster than a full review board.
Routes explicitly requested agent collaboration across direct work, focused headless Grok delegation, Pi subagents, and Herdr. Use when the user asks to delegate, coordinate agents, run parallel reviewers or researchers, use Herdr or Pi subagents, or choose a collaboration backend. Do not use for ordinary single-agent tasks.