「dpo」の検索結果

Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.

日本語の概要は準備中です。原文の説明を表示しています。

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.

日本語の概要は準備中です。原文の説明を表示しています。

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.

日本語の概要は準備中です。原文の説明を表示しています。

Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.

日本語の概要は準備中です。原文の説明を表示しています。

Document a module or public API surface (functions, classes, CLI commands, endpoints) from the code itself. Use when the user asks for API reference, to document a module, or to write usage docs for a public interface.

日本語の概要は準備中です。原文の説明を表示しています。

Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools from a spec", or pastes/attaches an `openapi.yaml`, `openapi.json`, or `swagger.json` and asks for a Claude-compatible version. Trigger even if the user doesn't say "MCP" — if they describe an existing HTTP API (REST endpoints, an internal service, a third-party API they have a key for) and want an LLM to call it, this is the right skill. Covers spec ingestion (file path, URL, or pasted), operation-to-tool mapping, auth wiring (apiKey, bearer, basic, OAuth bearer), scaffolding with `create-mcp-use-app`, tool generation with proper zod schemas, live testing in the mcp-use inspector, and deploying to Manufact / mcp-use cloud.

日本語の概要は準備中です。原文の説明を表示しています。

Convex backend specialist. Use this agent for any code inside a `convex/` directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form function syntax, validator patterns, resource limits, and component ecosystem that generic Claude routinely gets wrong.

日本語の概要は準備中です。原文の説明を表示しています。

Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. Use when analyzing APK files for Firebase vulnerabilities, performing mobile app security audits, or testing Firebase endpoint security. For authorized security research only.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive Windows privilege escalation methodology for offensive security engagements. Covers the full attack surface from a standard user shell to NT AUTHORITY\SYSTEM: token impersonation via SeImpersonate and SeAssignPrimaryToken privileges using JuicyPotato, PrintSpoofer, GodPotato, SweetPotato, and RoguePotato; service misconfigurations including unquoted service paths, weak service DACLs, writable service binaries, and insecure service creation permissions; AlwaysInstallElevated MSI exploitation; DLL hijacking through search order abuse, phantom DLL loading, and writable PATH directory injection; UAC bypass techniques via fodhelper.exe, eventvwr.exe, CMSTP, and environment variable manipulation; scheduled task abuse for writable task actions and new task creation; registry autorun exploitation for persistence and escalation; PrintNightmare (CVE-2021-34527) for remote and local privilege escalation; and credential harvesting from SAM database extraction, DPAPI blob decryption, LSA secret dumping, and Credential Manager enumeration. Integrates automated enumeration with WinPEAS, PowerUp, SharpUp, Seatbelt, and BeRoot. Each technique includes detection signatures and defender-side visibility for purple team operations. Maps to MITRE ATT&CK T1548 (Abuse Elevation Control Mechanism) and T1574 (Hijack Execution Flow). Designed for authorized penetration testing, red team engagements, and CTF competitions where you hold a standard user shell and need to escalate to SYSTEM or local Administrator.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive methodology for auditing and exploiting TLS/SSL implementations and misconfigurations across network services and mobile applications. Covers protocol downgrade attacks including POODLE (CVE-2014-3566) against SSLv3 CBC padding, DROWN (CVE-2016-0800) cross-protocol attack leveraging SSLv2 export ciphers to decrypt TLS sessions, and FREAK (CVE-2015-0204) forcing RSA export-grade key exchange. Addresses BEAST (CVE-2011-3389) exploiting CBC IV predictability in TLS 1.0, CRIME (CVE-2012-4929) and BREACH targeting TLS-level and HTTP-level compression oracles respectively, and Heartbleed (CVE-2014-0160) for OpenSSL memory disclosure. Covers certificate validation bypass techniques for applications with improper hostname verification or chain validation, certificate pinning bypass using Frida and Objection for mobile application interception, HSTS bypass via NTP manipulation and subdomain exploitation, TLS 1.3 0-RTT replay attacks against non-idempotent endpoints, mutual TLS (mTLS) authentication attacks including client certificate theft and relay, and Certificate Transparency log monitoring for reconnaissance. Primary tooling includes testssl.sh for comprehensive TLS auditing, sslyze for Python-integrated scanning, sslscan for quick cipher enumeration, and tlsx for high-speed TLS probing at scale. Maps to CWE-295 (Improper Certificate Validation), CWE-319 (Cleartext Transmission of Sensitive Information), and CWE-757 (Selection of Less-Secure Algorithm During Negotiation).

日本語の概要は準備中です。原文の説明を表示しています。

Advanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that bypass traditional security controls. Covers business logic bypass through API call chaining and workflow manipulation. Addresses GraphQL-specific attacks including batching for credential brute-force, query depth exploitation, and introspection abuse. Includes pagination exploitation for data exfiltration, webhook hijacking for SSRF and data interception, and resource exhaustion through algorithmic complexity attacks. Covers race conditions in API transactions using parallel request techniques. Provides comprehensive JWT manipulation including algorithm confusion, kid injection, jku/x5u abuse, and claim tampering. Details API key leakage detection across source repositories, client-side code, and error messages. Covers undocumented endpoint discovery through predictable naming, debug routes, and source map analysis. Tooling includes Arjun, ParamSpider, jwt_tool, and GraphQL Voyager. Designed for authorized penetration testers targeting business logic layers that automated scanners miss.

日本語の概要は準備中です。原文の説明を表示しています。

Dense description covering Server-Side Template Injection across Jinja2, Twig, Freemarker, Velocity, Pebble, Smarty, Mako, Handlebars, ERB, Thymeleaf, EJS, Pug. Engine fingerprinting, filter bypass, blind exploitation, WAF evasion, SSTI-to-RCE chains. Tools: tplmap. CWE-1336. MITRE T1190. Use when testing template rendering endpoints or exploiting template injection for code execution.

日本語の概要は準備中です。原文の説明を表示しています。

Offensive methodology for attacking GraphQL APIs during penetration tests and bug bounty engagements. Covers the full attack lifecycle: endpoint discovery, introspection abuse and blind schema reconstruction when introspection is disabled, authentication and authorization bypass through Relay node IDs and nested object traversal, injection via variables and directives, query batching for brute force and OTP bypass, denial of service through depth bombs and alias amplification, WebSocket subscription hijacking, information disclosure through verbose errors and field suggestion oracles, and file upload abuse via the multipart GraphQL specification. Includes tool-specific guidance for InQL, graphql-cop, CrackQL, BatchQL, Altair, GraphQL Voyager, and clairvoyance. Trigger on: GraphQL, graphql, introspection query, batching attack, query depth, GraphQL injection, GraphQL IDOR, field suggestion, GraphQL auth bypass, GraphQL DoS, GraphQL security, graphql-cop, InQL, CrackQL, BatchQL, Relay node, alias amplification, subscription abuse, multipart upload GraphQL, schema enumeration, __schema, __type.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.

日本語の概要は準備中です。原文の説明を表示しています。

Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use recipe-runner for recipe deployment and troubleshoot for failure diagnosis.

日本語の概要は準備中です。原文の説明を表示しています。

Submit compact STRING API requests for network, interaction partner, and enrichment endpoints. Use when a user wants concise STRING summaries

日本語の概要は準備中です。原文の説明を表示しています。

Submit compact UniProt REST API requests for UniProtKB, UniRef, UniParc, and FASTA stream endpoints. Use when a user wants concise UniProt summaries; save raw JSON or FASTA only on request.

日本語の概要は準備中です。原文の説明を表示しています。

Submit compact NCBI Datasets v2 requests for assembly, genome, taxonomy, and related metadata endpoints. Use when a user wants concise NCBI Datasets summaries; save raw JSON or text only on request.

日本語の概要は準備中です。原文の説明を表示しています。

Submit compact Ensembl REST API requests for lookup, overlap, cross-reference, and variation endpoints. Use when a user wants concise Ensembl summaries

日本語の概要は準備中です。原文の説明を表示しています。

Submit compact ChEMBL API requests for activity, molecule, target, mechanism, and text-search endpoints. Use when a user wants concise ChEMBL summaries

日本語の概要は準備中です。原文の説明を表示しています。

Submit compact eQTL Catalogue API requests for association retrieval and documented metadata endpoints. Use when a user wants concise public eQTL Catalogue summaries

日本語の概要は準備中です。原文の説明を表示しています。

ERC-8004 Agent identity: 注册/更新/上架/下架/搜索agent, register/update/activate/deactivate/search — User/ASP/Evaluator(买家/卖家/评审员, 旧称仲裁者亦可); 我的agent/ASP, 找做X的ASP/agent有什么服务/endpoint怎么填/查口碑/传头像. + Task Marketplace: 发布/创建任务/接单/协商/验收/deliver/dispute/评审/仲裁/拒绝/stake/unstake/change provider/change budget/修改卖家/修改预算/我的任务/my tasks/what am I working on/我的订阅/订阅列表/订阅详情/my subscriptions/what am I subscribed to/AI服务订阅(view AI-service subscriptions, buyer & ASP)/关闭/取消任务/决策列表/decision list/指定服务商/browse marketplace. + task watch: 监听任务进展/历史消息/未读消息/未决策/outstanding decisions. + device routing: 设备列表/我登录了哪些设备/device list, 本设备或指定设备订阅消息开关. + okx-a2a missing/uninitialized. Match by meaning. MUST ACTIVATE on inbound envelopes: (1) {agentId, message:{source:"system", event, jobId,...}} system event; (2) {msgType:"a2a-agent-chat", jobId, sender:{role},...} agent-to-agent task chat (sender.role = COUNTERPARTY, not you); (3) literal "Read the okx-ai skill" (or legacy "Read the okx-agent-task skill") in the envelope.

日本語の概要は準備中です。原文の説明を表示しています。

Real-time smart money analytics API for Polymarket prediction markets, Hyperliquid perpetual futures, and Meteora Solana LP/AMM pools. 63 endpoints. Pay-per-request via x402 on Solana Mainnet USDC. No API keys.

日本語の概要は準備中です。原文の説明を表示しています。

Migration guide from Jupiter Metis (v1) or Ultra to Swap API v2. Use when migrating existing Jupiter swap integrations, updating base URLs, or transitioning from quote+swap-instructions to the unified build endpoint.

日本語の概要は準備中です。原文の説明を表示しています。