2.1천건 · 관련도순
INVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data, evaluations, and annotations. Covers extracting prompts from spans, gathering performance signal, and running a data-driven optimization loop using the ax CLI.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan, set up, and monitor a multi-agent video production pipeline backed by Hermes Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates Hermes profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever Hermes rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Evolve prompts/regex/SQL/code with Imbue's evolution loop.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Master modern JavaScript with ES6+, async patterns, and Node.js APIs. Handles promises, event loops, and browser/Node compatibility. Use PROACTIVELY for JavaScript optimization, async debugging, or complex JS patterns.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create detailed phase plan (PLAN.md) with verification loop
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
[BETA] AEM Cloud Service expert skill — handle an explicitly-unbounded query (`p.limit=-1` predicate or JCR `setLimit(-1)`): bound it when capping is provably safe, otherwise flag it for human pagination. Use for "bound my query", "unbounded query", "query causing OOM", or a scan that flags `p.limit=-1`. Top CSO OOM cause: an unbounded result set traversed in a loop fills the heap and saturates the instance. The analyzer locates the explicit markers; the recipe triages each by how the result is consumed — single-result → 1, already-bounded list → N, iterate-all on the request path → escalate. Never silently cap a result the caller reads in full. This skill is in beta. Verify all outputs before applying them to production projects.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Render a proposed redesign of a page on the current website as a self-contained static HTML file, then iterate via the impeccable craft loop. Per-page, idempotent, stale-aware. Use when the user asks for a redesign prototype, a before/after comparison, a design preview, a page mockup, a visual diff of the redesign, or invokes /stardust:prototype.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run a bounded red-green-refactor feedback loop only when the user explicitly requests TDD, accepts reproduction-first proof for a bug, or an accepted high-risk behavior specifically requires red/green evidence; do not trigger for every logic, bug, behavior, or implementation change.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run one bounded adversarial pass when the user explicitly requests a report-style stress test or ROSE identifies a concrete material loophole in an existing strategy, spec, plan, review, or claim; do not trigger for an interactive grill/frontier interview or merely before write-back, implementation, reconciliation, or completion.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Repair one concrete reproducible build, typecheck, lint, test, packaging, or CI failure with a bounded root-cause-first loop; do not trigger for runtime bugs without a failing gate, broad test strategy, dependency/toolchain migration, or generic implementation.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a Claude Code session loops, drifts from scope, claims a fix that CI rejects, hits context, PATH, or permission walls, or fails in a way another retry will not solve and a root cause diagnosis is needed instead.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Microsoft Entra ID (Azure AD) authentication for React SPAs with MSAL.js and Cloudflare Workers JWT validation using jose library. Full-stack pattern with Authorization Code Flow + PKCE. Prevents 8 documented errors. Use when: implementing Microsoft SSO, troubleshooting AADSTS50058 loops, AADSTS700084 refresh token errors, React Router redirects, setActiveAccount re-render issues, or validating Entra ID tokens in Workers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Make your AI agent learn and improve automatically. Reviews sessions, extracts learnings, updates memory files, and compounds knowledge over time. Set up nightly review loops that make your agent smarter every day.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Complete community building, engagement, and monetization system. From zero to thriving community — launch strategy, member engagement loops, content programming, moderation frameworks, growth tactics, monetization models, and health metrics. Works for Discord, Slack, Telegram, Circle, forums, or any platform.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Human-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captures the page with a grid overlay, sends it to the human, and injects clicks based on their reply. Token relay mode detects CAPTCHA type + sitekey, serves the real widget on a relay page for native solving, and injects the token via CDP.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generates comprehension questions and language exercises based on the analyzed content to create a complete learning loop.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
ScepticAgent internal architecture reference. Use whenever the user asks how the extension works, wants to add a new AI provider, add a new highlight category, debug communication between components, understand the agent loop or streaming, or work with provider routing and the Gemini CORS proxy.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build production-grade AI agents from scratch using patterns inspired by production-grade agentic systems like Claude Code. Covers two audiences — (1) workflow builders who need planner+executor pipelines, human-in-the-loop checkpoints, and multi-agent orchestration, and (2) application embedders who need HTTP/SSE APIs, multi-user session management, and React frontend integration. Use when asked to build an AI agent, create a coding assistant, embed an agent in an app, build an API agent, clone Claude Code, build a CLI agent, design an agent architecture, scaffold an agentic system, or automate a multi-step workflow. Triggers on keywords like agent builder, agent blueprint, coding assistant, CLI agent, agentic tool, claude code clone, agent scaffold, agent architecture, workflow automation, multi-agent, planner executor, SSE streaming, agent API.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.