'cost' 검색 결과

ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate an XLSX inventory report with stock levels, reorder points, unit costs, and total value formulas for purchasing teams.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Extract line-level charges from multiple carrier invoices, then generate an XLSX freight cost tracker in a single pipeline.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OpenAI API (developers.openai.com) の画像生成・画像入力リファレンス。 GPT Image 2.5 (`gpt-image-2.5-sunburst` / `flare`), Images API `images.generate` / `images.edit`, mask, reference images, quality xhigh / max, image prompting, image_generation tool (Responses API), vision (画像入力, detail, image tokens, cost calculator, vision fine-tuning)。 Sora 2 / Videos API は 2026-09-24 終了 (履歴のみ)。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Claude API (platform.claude.com) の組織管理・Admin API (sk-ant-admin)。 users, invites, workspaces, API keys, service accounts, RBAC (groups / roles), Workload Identity Federation (WIF, federation issuers / rules), Usage & Cost API, rate / spend limits, Analytics API, Compliance API (transcripts, access transparency log), Plugins API, OpenTelemetry telemetry, CMEK, zero data retention (ZDR), data residency, inference hooks。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Claude Code (code.claude.com) の権限・セキュリティ・企業管理リファレンス。 permissions (allow / ask / deny), permission modes, auto mode (classifier billing), sandboxing, sandbox environments, sandboxed Bash, zero data retention, data usage, HIPAA, managed settings (MDM / plist / registry), server-managed settings, managedMcpServers, allowedProviders, admin setup, authentication (SSO), network config, corporate launcher, OpenTelemetry monitoring, analytics, costs, large codebases, communications kit / champion kit。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Rory Sutherland's 'psycho-logic' approach to marketing, product, and business problems — solve the human perception, not just the engineering or economic metric. Use when the obvious 'logical' fix is expensive, slow, or already done by every competitor; when the user asks 'how do we make people want X', 'the product/price/funnel is fine but nobody converts', 'how do we stand out', 'is there a cheaper way to fix this', or mentions behavioral economics, nudges, irrational behavior, perception, or 'it doesn't make sense but it works'. This is the ROUTER skill: it diagnoses the problem in human terms, then dispatches to reframing, costly-signaling, counterintuitive-tests, or experience-design. Inspired by Rory Sutherland's book *Alchemy*. 日本語の相談（「商品はいいのに売れない」「値下げしかない？」「競合と差別化できない」）にも使う。中文咨询（“产品很好却卖不动”“只能降价吗？”“无法差异化”）也适用。For a catalogue of individual biases, use marketing-psychology (separate plugin) instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

The perception-by-culture lens for psycho-logic — establish HOW a specific region, country, or subculture reads a signal before you send it, because perception is culturally coded and the same move can mean the opposite elsewhere. Use when adapting a product, price, message, or campaign to a new market; when the user asks 'will this work in [country/region]', 'why does this land in X but flop in Y', 'how do people here perceive Z', 'how do we localise/differentiate by region', or is about to copy a US/global playbook into another market. Covers the cultural dimensions that move Sutherland's levers — uncertainty avoidance, individualism/collectivism, status/power distance, high- vs low-context communication, mental-accounting norms, trust locus, and taboo/sacredness — and how each rewires reframing, costly-signaling, and experience-design. Inspired by Rory Sutherland's *Alchemy*. Routed to from psycho-logic; pair with market-recon for live local data. 日本語・中文の相談（「この地域で通用する？」「适合本地市场吗？」）にも使う。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Bulk mode — maximum development speed by spending tokens aggressively on massive parallel sub-agents and multi-agent workflows, while the orchestrator context stays lean (pairs with /slim). Invoking /bulk is the user's explicit opt-in to Workflow/ultracode-style orchestration for this session. Use when the user types /bulk, asks for "爆速", "並列で大量に", "ultracode", "多エージェント", or hands over a big task where wall-clock speed matters more than token cost.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when preparing or reviewing a construction work-in-progress schedule under AASB 15: measuring progress by input or output method, cost to complete, contract assets and contract liabilities, variations and claims as constrained variable consideration, and tying the schedule to revenue and the general ledger.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when preparing an Australian individual's working from home deduction workpaper under the fixed rate or actual cost method, including the 2026-27 standard deduction comparison.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when preparing an Australian CGT event register, cost-base evidence or capital-loss reconciliation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when preparing Australian managed-fund or ETF annual-tax-statement, AMIT/AMMA attribution and unit cost-base adjustment workpapers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Work on album artwork — reading an image's dimensions, and embedding a folder's cover file into the tags of its tracks. Use this whenever a task touches `services/artwork.py`, the cover half of `services/tags.py`, or `scripts/embed_covers.py` / `embed_covers_cron.sh`. Covers why Lyrion shows the embedded artwork and never the folder file, how covers are compared, why images are never re-encoded, and what embedding costs in rewritten files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Improve test value and feedback cost when auditing slow, flaky, redundant or brittle tests; choosing tests during implementation; or reviewing test changes before a commit or PR. Keep ordinary implementation and pre-commit use scoped to the affected behavior, not a repository-wide audit.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Estima, confirma e acompanha o gasto com geradores pagos. Use quando o usuário disser "quanto vai custar", "orçamento", "quanto gastei", "controlar custo", "está caro", antes de qualquer lote de geração, ou ao fechar campanha. Com APIs no centro, custo deixa de ser detalhe e vira restrição de projeto.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a change is small and already understood - at most three files, such as a typo, a config value, a rename, or a one-line bugfix - and a plan file would cost more than the change

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Analisa custo AWS e identifica desperdício em EC2, RDS, S3, EKS, EBS, Elastic IP, NAT Gateway e tráfego. Use quando o usuário disser "custo", "fatura", "está caro", "FinOps", "reduzir gasto AWS", "Cost Explorer", "otimizar custo". Quase todo leitura — seguro por natureza.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.