2,336 件 ・ 関連度順
概要と使いどころ
把生产 bad case / 失败轨迹转成训练数据时使用——从失败归因、轨迹前缀截取、DPO 偏好对构造、LoRA 训练到边界集与保留集双集验证的完整链路；也用于判断某类问题该走 SFT、DPO、RL 还是先修 Harness/工具/tokenizer，以及如何从运行轨迹中提取带证据的结构化学习信号。触发词：bad case、失败归因、DPO、偏好对、轨迹前缀、拒绝采样、过度矫正、边界集、保留集、过早结束、reward hacking、LoRA 微调、训练评估隔离。
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。
为 Agent 接入第三方能力时使用——决定走 MCP 协议还是 Skill Hub 分发、搭建或选用 MCP 服务器、设计工具/资源/提示三类原语、评估引入第三方能力的 token 成本与安全风险、审查工具描述投毒与同名工具遮蔽、锁定服务器版本与配置最小权限凭证时查阅。含 MCP 客户端-服务器架构、传输层选型与供应链缓解清单。
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 Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Applies when working with AutoModel, pipelines, tokenizers, generation configs, or TrainingArguments within Transformers.
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。
Supports Gtars for local genomic interval models and set algebra, overlaps and counts, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning across Python, Rust, and the 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。
Supports audited local Geniml genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.
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。
Implement or review authentication and authorization with explicit token, session and resource-access boundaries.
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。
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
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。
Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.
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。
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.
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。
Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging.
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。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Active Directory, Kerberos, LDAP, OAuth, enterprise messaging, Windows host forensics, credential material, and lateral-movement challenges. Use when the user asks to trace tickets or tokens, inspect mailbox rules, analyze Windows host evidence, understand an AD trust path, or explain a lateral-movement chain across sandbox-linked nodes. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
日本語の概要は準備中です。原文の説明を表示しています。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for enterprise mail abuse, OAuth consent, inbox or forwarding rules, transport rules, shared mailbox access, phishing chains, and token-to-mailbox side effects. Use when the user asks to trace mailbox rules, OAuth consent grants, forwarding or delegate abuse, shared mailbox access, message-trace evidence, or explain how mail artifacts turn into persistence, exfiltration, or privilege. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
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。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for cloud metadata services, instance identity, workload identity, link-local credential paths, role assumption, and metadata-to-privilege trust edges. Use when the user asks to inspect metadata-service access, instance credentials, pod or workload identity, link-local token paths, SSRF-to-metadata escalation, or explain how metadata-derived credentials turn into accepted cloud or control-plane privilege. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
日本語の概要は準備中です。原文の説明を表示しています。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kubernetes API analysis, service-account trust, RBAC edges, admission and controller behavior, cluster secrets, workload mutation, and namespace-scoped drift. Use when the user asks to inspect kube API permissions, service-account tokens, RoleBinding or ClusterRoleBinding edges, admission webhooks, controller-created pods, secret exposure, or why live workloads differ from manifests. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
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 for authorized assessment of federated identity systems including SAML, OIDC, OAuth2 flows, SSO misconfiguration, and token confusion 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。
Use for authorized email security review including phishing analysis, header authentication (SPF/DKIM/DMARC), BEC patterns, and mailbox token abuse research.
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。
Apply typography, color theory, spacing systems, and iconography principles to create cohesive visual designs. Use when establishing design tokens, building style guides, or improving visual hierarchy and consistency.
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 scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.
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 writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.
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 maintaining a durable Markdown knowledge store that agents compile from sources, when every number or quote in a wiki page must trace back to an immutable source, or when compiled pages need cheap drift detection against the code they describe. Teaches the raw/wiki/archive layout, per-claim provenance links, and git fingerprints for zero-token staleness checks.
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。
Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established visual direction. Skip when they have a design mockup, need a dashboard or app UI, are working at component level, building a multi-page app, or restyling with known design tokens — use frontend-design instead.
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。
CommunityToolkit.Mvvm Messenger pub/sub for decoupled communication between ViewModels (or any objects). Covers WeakReferenceMessenger vs StrongReferenceMessenger, IRecipient<TMessage>, RequestMessage<T> / AsyncRequestMessage<T> / CollectionRequestMessage<T>, ValueChangedMessage<T>, channels (tokens), and the ObservableRecipient activation lifecycle. Use across WPF, WinUI 3, .NET MAUI, Uno, and Avalonia.
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 guide for creating professional UI/UX designs in Penpot using MCP tools. Use this skill when: (1) Creating new UI/UX designs for web, mobile, or desktop applications, (2) Building design systems with components and tokens, (3) Designing dashboards, forms, navigation, or landing pages, (4) Applying accessibility standards and best practices, (5) Following platform guidelines (iOS, Android, Material Design), (6) Reviewing or improving existing Penpot designs for usability. Triggers: "design a UI", "create interface", "build layout", "design dashboard", "create form", "design landing page", "make it accessible", "design system", "component library".
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。
Manage Azure Container Registry via the az acr CLI including registries, images, cloud builds, ACR Tasks, authentication, tokens, geo-replication, and networking. Use when working with ACR, az acr commands, pushing/importing/purging container images in Azure, or when the user mentions Azure Container Registry.
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。