'eval' 검색 결과

Records and evaluates event-specific probability forecasts for agent outputs. NOT for validation or automatic acceptance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when designing or fixing a Content Security Policy on a real site, choosing between nonce-based and hash-based CSP, adding strict-dynamic, debugging "Refused to execute inline script" errors, deploying CSP in report-only mode first, configuring report-to / report-uri, or auditing an existing policy for unsafe-inline / unsafe-eval / wildcards. Triggers: "CSP blocks legitimate inline script", strict-dynamic, nonce-{RANDOM}, sha256-{HASH}, object-src none, base-uri none, frame-ancestors, Trusted Types, X-Content-Security-Policy obsolete, report-only vs enforced. NOT for general HTTP security headers (HSTS, COOP/COEP), Trusted Types deep dive, CORS configuration, or building a WAF.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Guides Cloudflare One Zero Trust and SASE work across Access, Gateway, WARP, Tunnel, Cloudflare WAN, DLP, CASB, device posture, and identity. Use when designing, configuring, troubleshooting, or reviewing Cloudflare One deployments. Retrieval-first: use current Cloudflare docs/API schemas instead of embedded product docs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Designing HTTP cache headers that work correctly across browsers, CDNs, and shared proxies — `Cache-Control` directives per RFC 9111, `stale-while-revalidate` and `stale-if-error` per RFC 5861, the Vary header for varying responses, and surrogate keys for tag-based purging. Grounded in IETF RFCs and Cloudflare/Fastly docs. NOT for service-worker or browser-only caching, Redis/memcached application caching, or edge-function compute.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Architecture-level decisions for putting a CDN in front of a web app's static assets, API responses, and file/media delivery: provider selection (hyperscaler vs. specialist $/GB), signed-URL / tokenized access for gating private content at the edge, cache invalidation strategy (versioned URLs vs. purge APIs), origin shield / tiered caching for high-miss-rate content, and CDN-layer geo-restriction. Use when deciding which CDN to put in front of a new or growing service, when private/paywalled files need edge delivery without an origin round-trip per request, or when purge/invalidation behavior is being designed rather than debugged. NOT for HTTP cache-control header syntax, Vary, stale-while-revalidate, or surrogate-key purge mechanics (see `cdn-cache-control-headers`); NOT for Cloudflare-specific product configuration once Cloudflare is already chosen (see `cloudflare`); NOT for video-specific transcoding, adaptive bitrate ladders, or streaming-protocol packaging (see `managed-video-streaming-pipeline`).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Redis caching patterns, cache-aside, write-through, TTL strategies, and invalidation. Activate on: caching, Redis, cache invalidation, cache-aside, write-through, TTL, CDN cache, stale-while-revalidate. NOT for: CDN/reverse proxy setup (use api-gateway-reverse-proxy-expert), database query optimization (use data-warehouse-optimizer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Facilitate idea generation sessions that actually produce diverse, useful options instead of degenerating into the first plausible answer. Use for product ideation, feature exploration, problem-reframing, naming, design alternatives, strategic option-generation, or any task where the failure mode is "we picked the obvious thing too fast." Covers solo and group sessions, divergence/convergence discipline, technique selection (SCAMPER, Crazy Eights, How Might We, 6-3-5 Brainwriting, Reverse Brainstorming, Worst Possible Idea, Random Stimulus), facilitation moves for handling dominant voices and groupthink, and structured convergence to a shortlist with rationale. Outputs a session artifact with options generated, evaluation, shortlist, and the rejected-but-interesting list.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

How to design contextual inputs for an always-on AI agent with episodic memory. Covers what data to feed the agent, how to structure observations and triggers, ambient context capture (screen, audio, calendar), context window budgeting, and retrieval strategies that keep the agent grounded in what's actually happening. Activate on: "what should the agent observe", "context inputs for agent", "ambient context capture", "agent triggers", "agent input design", "screenpipe integration", "context window budget", "what data to feed my agent", "/always-on-agent-inputs". NOT for: memory architecture and storage (use always-on-agent-architecture), application ideas (use always-on-agent-applications), safety concerns (use always-on-agent-safety).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up and connect a new Coval agent for evaluation. Guides through agent type selection, endpoint configuration, system prompt, and default resource attachment. Use when user says "set up an agent", "connect my agent", "create an agent", "add an agent", or "configure agent endpoint".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Delegate a read-only Coval evaluation, simulation, monitoring, product-how-to, or troubleshooting subtask to Sofia through the official Coval MCP consult_sofia tool. Use when the user needs Coval-specific FDE judgment, analysis of organization data, metric or test-set recommendations, or a diagnosis grounded in Coval runs and conversations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

End-to-end Coval adversarial / red-team testing workflow. Builds one adversarial test set (12 core attack vectors plus legitimate controls, each with an expected-behavior checklist), creates a persistent "Adversarial User" persona and a Composite Evaluation metric that scores each scenario against its own expected behaviors, launches a multi-iteration run against the agent (voice or chat), polls for completion, builds a per-scenario pass/fail scorecard, and creates a saved report grouped by Test Case. Use when a user wants to follow the Adversarial & Red-Team Testing cookbook (https://docs.coval.dev/guides/adversarial-red-team-testing) without doing each step by hand. Triggers: "adversarial test set", "red team my agent", "jailbreak / prompt-injection testing", "test my agent against bad actors".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Retrieve and analyze simulation results from a Coval run. Use when user wants to review evaluation outcomes or debug agent behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Enables Claude Code to collaborate with OpenAI Codex CLI on Windows. Use this skill when the user wants to get a second opinion from Codex, compare approaches between Claude and Codex, or leverage both AI assistants for collaborative problem-solving. This skill supports both non-interactive mode (automatic response retrieval) and interactive mode (visual pane splitting with tmux).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

サブエージェントのコンテキスト問題を解決するための段階的コンテキスト取得パターン

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

コーディングエージェント（Claude Code、Aider、Codexなど）のカスタムタスクによる直接比較。合格率、コスト、時間、一貫性メトリクスを測定

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

評価駆動開発（EDD）原則を実装するClaude Codeセッションのための正式な評価フレームワーク

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build an RL environment / eval that trains or measures a skill in any domain (finance, medicine, law, math, science, a niche industry) from real cases that Browser Use agents mine from the web, then baseline and hillclimb a model on it. Use when the user knows a domain and what a model should be able to do in it, but not how to get the data or build the environment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert knowledge of vilkår / vilkårsvurdering (requirements evaluation) in melosys-api. Use when: (1) Understanding inngangsvilkår structure for FTRL bestemmelser (VilkårForBestemmelse), (2) Debugging Vilkaarsresultat / oppfylt status or begrunnelser, (3) Understanding avklarte fakta (AvklarteFaktaForBestemmelse) collection, (4) Investigating why a vilkår fails or which vilkår a bestemmelse requires. Triggers: vilkår, vilkaar, vilkaarsresultat, vilkårsvurdering, oppfylt, begrunnelse, inngangsvilkår, avklarte fakta, FTRL_2_5, FTRL_2_8, VilkårForBestemmelse.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert knowledge of Behandlingsresultat (treatment result) domain in melosys-api. Use when: (1) Understanding result types and their meaning (FASTSATT_LOVVALGSLAND, MEDLEM_I_FOLKETRYGDEN, etc.), (2) Working with periods - Lovvalgsperiode, Medlemskapsperiode, Anmodningsperiode, Utpekingsperiode, (3) Debugging vedtak/decision metadata, criteria evaluation, or social insurance charges, (4) Understanding EU/EEA coordination logic and Article 16 exception handling, (5) Working with trygdeavgift (social insurance charge) calculations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design abstract strategy games with perfect information, no randomness, and strategic depth. Use when designing a board game, exploring abstract strategy games, brainstorming game mechanics, or evaluating game balance. Keywords: board game, game design, strategy, mechanics, balance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Complete workflow for static structural analysis. Use when analyzing stress, displacement, or reaction forces under constant loads. For strength and stiffness evaluation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Perform 12-Factor App compliance analysis on any codebase. Use when evaluating application architecture, auditing SaaS applications, or reviewing cloud-native applications against the original 12-Factor methodology.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.