Find, søg i og download klar-til-brug Claude Code Agent Skills — eller lær hvordan du installerer og bruger dem.
A guided co-pilot that turns a vague "I want an agent for this" into a production-ready LOOP.md — a loop spec with goal, triggers, tools, sub-agent roles, state/ledgers, a testable rubric, revision logic, stop conditions and budgets. Runs as a step-by-step interview using the AskUserQuestion tool (tappable multiple-choice, one decision at a time), never a wall of questions. Trigger whenever the user writes /netsi-loop-generator (optionally with an idea or an existing LOOP.md). Also trigger when the user says "byg en loop", "lav et loop prompt", "loop engineering", "write loops not prompts", "turn this into an agent", "automate this weekly task", "make this run on a schedule", "design an agent that keeps working until it's done", "review my loop spec", or asks how to go from prompting to loops. Always run the guided dialogue for any /netsi-loop-generator command — never dump a finished loop spec inline without first clarifying goal, verification and stop conditions.
A conversational co-pilot that guides a user step-by-step through structured questions and produces or improves a PRD.md (Product Requirements Document). Works two ways: (1) build a PRD from scratch through dialogue, or (2) take an existing PRD.md the user provides, review it for gaps and improvement potential, and continue evolving it. Trigger whenever the user writes /netsi-prd-creator (optionally with a short idea or an attached PRD.md). Also trigger when the user asks to "create a PRD", "write a product requirements document", "help me spec out my app idea", "review my PRD", "improve this PRD", or "continue working on my PRD". Always use this skill for any /netsi-prd-creator command — never dump a full PRD inline without first running the guided dialogue.
Create a complete, ready-to-use prompt from a question, idea, or existing prompt, while transparently involving the user in significant prompt-design decisions. Use when a user asks to create, improve, optimize, rewrite, or turn input into a high-quality prompt, especially when role, objective, audience, constraints, output format, or tradeoffs are unclear.
Rewrites a weak prompt into a strong, precise one using only the techniques that empirically improve answers (specification, verification-with-signal, information grounding) — never persona/role-play, which measurably hurt. Use whenever the user writes /netsi-prompt-optimize, or asks to "optimize this prompt", "improve my prompt", "make this prompt better", "rewrite this prompt", "why is my prompt giving bad answers", or wants a prompt that works better on a small/local LLM. Also use when the user pastes a prompt and complains the output is vague, wrong, off-tone, too long, or ignores their constraints. Always run this skill for any /netsi-prompt-optimize command — produce the rewritten prompt, don't just answer the original.
Deliver a precise, executable step-by-step guide for anything the user wants to do or achieve — across any domain (craft, repair, cooking, IT, programming, APIs, admin, creative work). Use whenever the user writes /netsi-show-me-how, or asks "hvordan gør jeg X", "fortæl mig præcist hvordan", "guide mig gennem", "step by step", "vis mig hvordan jeg…", "how do I actually do X", or hands over a goal and expects instructions rather than discussion. Also trigger when a user is stuck mid-task and needs the remaining steps spelled out. Always run this skill for /netsi-show-me-how — clarify the one thing that actually changes the guide, then deliver the full guide, never a vague overview.
Help someone see a real-life situation differently by telling a short fictional story that mirrors its emotional structure and ends on a believable twist — in the spirit of the "cookie thief" story. Use this whenever a user shares a personal situation they feel stuck in, hurt by, angry about, or certain about, and would benefit from a gentler, wider reading: relationship friction, work conflict, parenting, grief, frustration, self-criticism, or anxiety. Trigger even when the user does not ask for a story — if they are looping on a single interpretation ("he clearly doesn't care", "I always ruin things", "she's doing it on purpose"), offer the mirror. Do NOT trigger for factual questions, requests for direct advice, or crisis situations that need real support.
Write short, curiosity-driven explainer content using the Fry-Metoden (Anchor+Promise → Mechanism → Click → Sign-off). Use whenever the user writes /netsi-write-like, or asks to "skriv i Fry-metoden", "gør denne tekst nysgerrighedsdrevet", "lav et hook", "forklar noget overraskende", "make this curiosity-driven", "write a Fry-style explainer", or wants a LinkedIn post / short script / formidlings-tekst that makes the reader NEED the answer. Also trigger when the user hands over a fact, phenomenon, or dry explanation and wants it turned into a tight, hooky piece. Always run this skill for /netsi-write-like — build the piece through the four phases, don't just dump a generic paragraph.
Expert assistant for making web applications "agent-native" using the Web Model Context Protocol (WebMCP). Use this skill whenever the user wants to add WebMCP support to a website, make HTML agent-ready, register tools for AI agents, implement document.modelContext (formerly navigator.modelContext), add toolname/tooldescription attributes, convert forms for AI agent use, or asks anything about WebMCP patterns, declarative vs imperative approaches, or agent-native web development. Trigger even if the user just pastes HTML code and mentions "agent", "AI", or "MCP".