1.5천건 · 관련도순
You're a quality engineer who has seen agents that aced benchmarks fail spectacularly in production. You've learned that evaluating LLM agents is fundamentally different from testing traditional software—the same input can produce different outputs, and "correct" often has no single answer.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Structured LLM outputs validated with Pydantic.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII Tespit and content policy enforcement, and the Guardrails AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts, stripping PII, ...
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Validate digital outputs for compliance with accessibility standards (e.g., WCAG, Section 508). Use when reviewing reports, dashboards, documents, or interfaces from pilot projects to identify and remediate accessibility barriers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Technical SEO for AI search engines. Checks AI crawler accessibility, llms.txt compliance, robots.txt configuration, server-side rendering. Outputs problems + fixes (generates llms.txt, robots.txt modifications). Use when user says "AI crawlers", "llms.txt", "GPTBot", "GEO technical".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build project-level design systems based on Material Design principles. Use when creating a new design system, extracting one from an existing product, extending tokens or components, or reviewing UI for design system compliance. Outputs a project-level Agent Skill with token definitions and component specifications.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate HTML reports and structured metrics from model evaluation results. Creates publication-ready reports with embedded outputs (images, audio, charts) and metrics.json for cross-model comparison. Use when generating reports, writing metrics, creating evaluation summaries, or formatting benchmark results. Triggers on "generate report", "write metrics", "create report", "evaluation summary", "benchmark results", "format results".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Personal App-in-Skill customer-support desk (help desk) that triages incoming support tickets from email, WhatsApp, web chat, contact forms, and WeChat, drafts KB-grounded replies, and proposes actions, then holds every send behind a human approval queue with a pre-send quality gate (support-qa) that outputs SHIP/FIX/BLOCK, plus SLA and CSAT tracking. Use when the user invokes $kelly-support or /kelly-support, mentions 客服 / 工单 / 支持台, a support desk, help desk, customer service, support tickets, ticket triage, a knowledge base or canned macros, SLA / first-response time, CSAT, escalations, or refund requests, wants incoming tickets triaged into a needs_review → approved → done pipeline, agent-drafted replies grounded in a knowledge base and reviewed before sending, refunds and commitments gated behind human approval, or breaching-SLA tickets surfaced. This is the OPERATOR desk (agent + human), distinct from a visitor-facing chat bubble.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build, analyze, repair, and audit finance three-statement models and operating forecasts. Use when the user invokes $kelly-finance, asks for 财务三表, 三表模型, income statement, balance sheet, cash flow statement, forecast model, budget model, financial projections, FP&A model, SaaS/unit economics forecast, fundraising model, board finance pack, investor model, model checks, balance-sheet balancing, cash runway, working capital, capex/depreciation schedules, debt schedules, scenario/sensitivity cases, or Excel/Sheets-ready finance outputs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Automates the enrichment of raw indicators of compromise with multi-source threat intelligence context using SOAR platforms, Python pipelines, or TIP playbooks to reduce analyst triage time and standardize enrichment outputs. Use when building automated enrichment workflows integrated with SIEM alerts, email submission pipelines, or bulk IOC processing from threat feeds. Activates for requests involving SOAR enrichment, Cortex XSOAR, Splunk SOAR, TheHive, Python enrichment pipelines, or automated IOC processing.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Produce a single consolidated hardening report for the DSH node. Runs audit.sh, dome-check.sh, and machine-probe.py, parses their outputs, and writes one markdown file listing every passing check, every failure with a specific remediation command, and a top-line verdict (ALL GREEN / N ISSUES). Non-destructive — reads only, no auto-fix.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan and execute reproducible computational research with explicit inputs, environments, provenance, deterministic steps, validation, and workspace outputs. Use for analyses that must be rerun, audited, or handed to another researcher.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Runs and configures curated nf-core community Nextflow pipelines (rnaseq, sarek, atacseq, methylseq, ampliseq, taxprofiler, fetchngs) reproducibly, pinning the pipeline revision with -r and selecting a container engine and institutional config via -profile. Use when deciding to adopt a community pipeline versus author one from scratch; picking a pipeline and pinning its -r revision; selecting -profile test/docker/singularity/conda plus an institutional config from nf-core/configs; building and validating a samplesheet CSV against the pipeline schema (nf-schema); choosing --genome/iGenomes versus custom references; configuring resources and max_memory for SLURM/AWS Batch; using -resume and -stub; and reading MultiQC outputs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build feedback collection for AI outputs. TRIGGERS - Use when user needs help with ai-feedback-collector related tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create evaluation frameworks for AI outputs with rubrics and scoring. TRIGGERS - Use when user needs help with ai-evaluation-framework related tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build content filtering for AI outputs. TRIGGERS - Use when user needs help with ai-content-filter related tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
OpenAI API (developers.openai.com) の Responses API リファレンス。 text generation, embeddings, gpt-6-astra / gpt-6.1-sol / gpt-6-luna, structured outputs, streaming, function calling, programmatic / async tool calling, conversation state, prompt caching, prompt cache diagnostics, reasoning (configuration_update), background mode, compaction, multi-agent, WebSocket mode (mid-turn steering, stream_id), webhooks, error codes, rate limits, Realtime server controls, 公式 SDK (Python / JS / .NET / Java / Go / Ruby), openai CLI, Chat Completions / Assistants 移行, deprecations。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Claude Agent SDK (code.claude.com/docs/en/agent-sdk) の TypeScript / Python リファレンス。 query(), ClaudeAgentOptions / Options, fallbackModel, maxTurns, maxBudgetUsd, custom tools (in-process MCP), createSdkMcpServer, hooks, permissions (canUseTool), subagents, sessions (resume / fork), streaming, structured outputs, Agent Skills (SKILL.md), slash commands (/compact, /clear), tool search, hosting / observability。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Claude API (platform.claude.com) の Messages API リファレンス。 streaming (SSE), thinking (adaptive) / preserved thinking / effort, prompt caching, context editing, compaction (on-demand / threshold), structured outputs, Message Batches, token counting, vision / PDF, Files API, citations, embeddings (Voyage AI), errors, rate limits, beta headers, Bedrock / Vertex AI / Foundry 経由アクセス。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Extracts, filters, annotates, and exports differential expression results from DESeq2 or edgeR with proper handling of padj=NA (independent filtering, Cook's outliers, all-zero), multiple-testing correction choice (BH vs Storey q-value vs IHW vs lfsr), TREAT vs post-hoc fold-change filtering, p-value histogram diagnostics, gene annotation via org.db/biomaRt/mygene, GSEA preranked input, ORA background construction, replication reality (Schurch 2016 small-n result), and SABV/sex-stratified reporting. Use when extracting and interpreting DE results, troubleshooting padj=NA, choosing FDR method, preparing ranked lists for pathway analysis, annotating gene IDs, or comparing DESeq2 vs edgeR outputs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.