「dpo」の検索結果

Designs discovery, modeling, and validation workflows for prognostic biomarkers in biomedical and clinical research. Always use this skill when the user needs a prognostic biomarker study blueprint rather than a diagnostic test protocol, predictive biomarker design, treatment recommendation, or a completed manuscript. Focus on endpoint family, follow-up horizon, time scale, candidate marker strategy, model-building logic, risk stratification framework, and internal/external validation requirements. Do not invent cohort size, event rate, assay readiness, literature support, or validation access.

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。

Generates complete reference-grounded single-drug adverse-effect network-pharmacology research designs from a user-provided drug, adverse event, and desired evidence depth. Always use this skill when a user wants to design, plan, or upgrade a conventional network-pharmacology study centered on one fixed drug and one fixed adverse-effect endpoint, using drug-target prediction, adverse-event target collection, overlap analysis, PPI hub prioritization, enrichment interpretation, molecular docking, and optional orthogonal transcriptomic or literature validation. Covers five study patterns (canonical hub-first, cardiotoxicity or electrophysiology-oriented, immune-inflammatory adverse effect, organ-toxicity pathway context, translational validation) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with a recommended primary plan, dependency/evidence map, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, verified-reference pack, and self-critical risk review.

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。

Rapidly maps the evidence landscape around a medical topic by organizing major research streams, target populations, endpoints, methods, evidence density, and thin areas. Use this skill BEFORE medical-research-gap-finder — it provides the structured landscape that makes formal gap analysis more rigorous. Do not use for formal gap identification, study design, or protocol planning directly.

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。

Explains why studies on the same biomedical topic reach different or opposing conclusions by auditing differences in population, endpoint definition, sample source, assay or platform, study design, statistical model, adjustment strategy, validation chain, and bias control. It separates true contradiction from apparent contradiction caused by framing or methods. Never fabricate references, PMIDs, DOIs, trial identifiers, dataset details, platform details, study features, or conflict explanations that are not supported by the input.

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。

Guide for upgrading Stripe API versions, webhook endpoints, server-side SDKs, Stripe.js, and mobile SDKs

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。

Enforce XQUIC test coverage and local validation gates. Use when code, build, or test changes need verification; before commit or pull request; or when asked to build, test, validate, or verify XQUIC. Requires paired happy-path and abnormal-path unit tests, the complete local unit suite, and explicit endpoint coverage or gap reporting for production behavior changes.

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 share third-party HTTP API emulators with emulate. Use to emulate an external provider, add a custom service plugin, model stateful vendor endpoints, configure custom seeds, or package an emulator. For an existing built-in service, use that service's skill.

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。

Emulated AWS cloud services (S3, SQS, IAM, STS) for local development and testing. Use when the user needs to interact with AWS API endpoints locally, test S3 bucket and object operations, emulate SQS queues and messages, manage IAM users/roles/access keys, test STS assume role, or work without hitting real AWS APIs. Triggers include "AWS emulator", "emulate AWS", "mock S3", "local SQS", "test IAM", "emulate S3", "AWS locally", "STS assume role", or any task requiring local AWS service emulation.

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。

Emulated Slack API for local development and testing. Use when the user needs to interact with Slack API endpoints locally, test Slack integrations, emulate channels/messages/users/views, set up Slack OAuth flows, test incoming webhooks, or work with the Slack Web API without hitting the real Slack API. Triggers include "Slack API", "emulate Slack", "mock Slack", "test Slack OAuth", "Slack bot", "Slack views", "incoming webhook", "local Slack", or any task requiring a local Slack API.

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。

Emulated GitHub REST API for local development and testing. Use when the user needs to interact with GitHub API endpoints locally, test GitHub integrations, emulate repos/issues/PRs, set up GitHub OAuth flows, configure GitHub Apps, test webhooks, or work with actions/checks without hitting the real GitHub API. Triggers include "GitHub API", "emulate GitHub", "mock GitHub", "test GitHub OAuth", "GitHub App JWT", "local GitHub", or any task requiring a local GitHub API.

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。

Emulated Vercel REST API for local development and testing. Use when the user needs to interact with Vercel API endpoints locally, test Vercel integrations, emulate projects/deployments/domains, set up Vercel OAuth flows, manage environment variables, create API keys, configure protection bypass, emulate Vercel Blob storage, or test without hitting the real Vercel API. Triggers include "Vercel API", "emulate Vercel", "mock Vercel", "test Vercel OAuth", "Vercel integration", "Vercel Blob", "local Vercel", or any task requiring a local Vercel API.

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。

Reference for the TRL (Transformer Reinforcement Learning) library codebase. Use proactively before reading or editing any file under `trl/` so you have the intended contracts and invariants in mind, not just what the current code says. Covers trainer hierarchy (SFT, DPO, GRPO, KTO), shared utility functions (selective_log_softmax, decode_and_strip_padding, padding helpers), configuration system, model wrappers, and how data flows through any TRL trainer.

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。

Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). Use proactively when debugging a training pipeline that shows no improvement, loss anomalies, reward stagnation, NaN gradients, or other unexpected behavior during reinforcement learning fine-tuning. Work through all pipeline stages — reward, advantages, log-probs, loss, generation/decoding — before concluding the diagnosis is complete; stopping after one or two fixes is a common failure mode. Covers log-probability math, advantage estimation, numerical stability, reward processing, and generation/decoding pipeline issues.

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。

Configure HTTP/SSE transport for web-based MCP servers with proper endpoints, authentication, and CORS.

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。

WooYun business logic vulnerability methodology — 22,132 real cases across 6 domains (authentication bypass, authorization bypass, payment tampering, information disclosure, logic flaws, misconfiguration) and 33 vulnerability classes. Use for ANY security testing, auditing, or code review of web apps, APIs, or business systems — even without explicit "security" keywords. Triggers: penetration testing, security audit, vulnerability, bug bounty, payment security, IDOR, password reset, weak credentials, unauthorized access, race condition, parameter tampering, code review, 渗透测试, 安全审计, 漏洞挖掘, 支付安全, 越权, 逻辑漏洞, 业务安全, SRC, 代码审计. Also triggers on implicit intent: "test this endpoint", "find bugs", "can I bypass this", "帮我测测这个接口", "这个参数能不能改", "帮我找bug".

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。

Story structure for screenplays and stage plays (故事结构) — merged from Syd Field's paradigm and plot points, Blake Snyder's Save the Cat beat sheet and board, Robert McKee's Story (event/scene/sequence/act, inciting incident, progressive complications, crisis-climax-resolution, subplots, story triangle), Julian Hoxter's nine-beat model, Neill Hicks' three acts as attraction/anticipation/satisfaction, and Lu Jun's Chinese short-play structure (凤头猪肚豹尾, 起承转合, eight openings, eight endings, 入戏要快/脉络要清/高潮要高/转变要顺/变化要多). Use when outlining a script, placing plot points and midpoint, fixing a saggy second act, designing an opening or ending, diagnosing "nothing happens", choosing between linear and non-linear designs, or converting a premise into beats and cards.

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 the Agentlas browser hardpoint for browser-required work.

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 the Agentlas browser hardpoint for browser-required work.

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。

Architect and provision enterprise Azure infrastructure from workload descriptions. For cloud architects and platform engineers planning networking, identity, security, compliance, and multi-resource topologies with WAF alignment. Generates Bicep or Terraform directly (no azd). WHEN: 'plan Azure infrastructure', 'architect Azure landing zone', 'design hub-spoke network', 'plan multi-region DR topology', 'set up VNets firewalls and private endpoints', 'subscription-scope Bicep deployment', 'Azure Backup for VM workloads'. PREFER azure-prepare FOR app-centric workflows.

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, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, agent insights, pull agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

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。

Tech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when: user asks about tech debt, refactoring priorities, what to clean up first, or asks "why is this so hard to change?", "what should we fix first?", or "how do I justify refactoring to management?". Do NOT trigger for: server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime — "health" in those contexts is infrastructure, not code quality. Also not for single-function refactoring questions.

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。

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up the whole project", or asks for a single command that both diagnoses and remediates quality problems. Do NOT trigger for: read-only audits or health reports where the user only wants findings without code changes; single-dimension reviews (use the focused skill instead: brooks-review / brooks-audit / brooks-debt / brooks-test); server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime.

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。

Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic engineering books. Triggers when: user wants an overall quality assessment, asks "how healthy is this codebase?", "run all the checks", "I need a health score before the release", or wants to onboard a new team with a quality overview. Do NOT trigger for: server health checks, HTTP health endpoints, Kubernetes liveness/readiness probes, database health, or application uptime. Also do not trigger when the user specifically requests only one dimension — use the corresponding focused skill instead (brooks-review / brooks-audit / brooks-debt / brooks-test).

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。

This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe, reward design, or weight updates. Decision tree by reward shape, smoke-run gate, three failure diagnostics, five false-progress patterns. Provider recipes and I/O contract in references/.

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。