2,872 件 ・ 関連度順
概要と使いどころ
为 msModelSlim 创建基础 Transformers 模型适配器（Model Adapter）。 包含创建适配器、实现必需接口与注册安装流程。 适用：Decoder-only LLM、理解类 VLM（仅 LLM/text 部分）。 多模态生成（DiT/扩散，含双/多专家）见下方「多模态生成扩展」节，按需加载。 不适用：Encoder-only、非 Transformers 架构。
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。
Builds, measures, and improves an Answer Engine Optimization program across ChatGPT, Perplexity, Claude, Gemini, Google AI Overviews, and Copilot. Use for AEO, GEO, LLMO, AI search visibility, AI citations, brand mentions, answer-engine monitoring, llms.txt, AI crawler audits, or questions like 'what does AI say about us?' and 'why are competitors cited instead of us?'. Produces a durable evidence report and prioritized gameplan, not a one-shot content checklist.
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 building autonomous LLM agents operating in live environments. Protects against prompt injection, tool abuse, data exfiltration, and runaway loops. Keywords: guardrails, prompt injection, IPI, safety, sandboxing, NeMo, LLM Guard.
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。
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
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。
Agentic workflow patterns for autonomous LLM reasoning. Use when building ReAct agents, implementing reasoning loops, or creating LLMs that plan and execute multi-step tasks.
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。
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.
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。
Review owned or authorized code for security using structure-first evidence: AST/structure maps, call graphs, complexity, Source/Sink flow, and defensive findings. Use when asked for security review, vulnerability review, AST structure map review, SAST triage, Source/Sink, taint flow, parser/scanner hardening, CI/CD security, LLM/agent tool boundary review, 脆弱性レビュー, 構造マップ, セキュリティレビュー.
Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external document retrieval. Covers document injection, embedding manipulation, knowledge base poisoning, and cross-document inference attacks.
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 LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.
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。
Execute sophisticated Data Extraction and Privacy Leakage attacks explicitly against Large Language Models (LLMs) to natively force the neural network entirely into organically regurgitating exact, verbatim strings of Highly Confidential Personally Identifiable Information (PII), proprietary source code, or copyrighted material categorically memorized intrinsically during its foundational pre-training phase.
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。
Execute sophisticated Prompt Injection and Jailbreak techniques against Large Language Models (LLMs) to bypass safety filters, extract system prompts, and manipulate the AI's output to perform malicious or disallowed actions.
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 techniques for bypassing LLM safety filters, instruction tuning, and system prompt restrictions using specialized linguistic constructs, hypothetical scenarios, and persona adoption.
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。
Exploit AI assistants equipped with web-browsing capabilities or internal API plugins to perform Server-Side Request Forgery (SSRF). This skill details injecting prompts that force the LLM to request sensitive internal endpoints, such as underlying cloud metadata services or internal networks.
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。
Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.
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 building RAG or LLM applications with LlamaIndex - data loaders, node parsing, vector stores, retrievers and rerankers, query engines, agents and workflows, streaming, or evaluation
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。
Job queues, background processing, and task scheduling with BullMQ v5
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。
LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend tracking, virtual keys, and production deployment
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 LLM applications with chain-style orchestration frameworks — prompts, chains, tool-calling agents, memory, and retrieval pipelines. Use when structuring multi-step LLM programs, adding tools to a model, or composing RAG systems in code.
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。
Gate resumption of any multi-day LLM batch-scoring campaign that calls an unpinned model alias (deepseek-chat, gpt-*-latest, gemini-*-preview, any provider alias without a pinned version). Use when: (1) resuming a paused or credit-exhausted scoring run days after its last chunk, (2) topping up credits to finish a campaign, (3) extending a cached scoring pipeline with new items. Prevents silently splicing two model versions or serving revisions into one measure. Verified 2026-07-16: for $0.30 caught a serving-revision drift WITHIN DeepSeek v4-flash (same alias, same family, litigation scores systematically shifted across a 2-day gap) before an $83 resume spend.
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。
Diagnose whether an LLM classifier's validation-gate failure is GOLD-BOUND before spending on prompt revision or model changes. Use when: (1) a scoring pipeline over-predicts a label (precision low, recall high) and a prompt clarification is proposed to tighten it, (2) a pilot/validation gate fails and the fix candidates are prompt edits, (3) inter-rater agreement on the weak label was already low (κ < ~0.6). Core check: if gold POSITIVES share the exact feature the revision would exclude, no prompt can pass a gold-scored gate — recall craters while precision barely moves. Also documents the verified surgical-pilot design (single-section diff, tune/holdout split, pre-registered gate, perturbation check on untouched sections).
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 human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to rule on cases an LLM classifier or rater panel judged, (2) a labeler reports "there is no information to label from" or cells look empty in Excel, (3) excerpt columns cluster at one exact length (e.g. all 1,500 chars — a hard truncation cap). Covers: full rating-basis recovery, Excel 32,767-char cell cap, multi-line CSV mangling, ruling dropdowns, companion text files.
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 SEO analysis for any website or business type. Orchestrates 52 sub-skills (52 active): full site audits, technical SEO (CWV/INP), schema, E-E-A-T content quality, images, sitemaps, GEO for AI Overviews, llms.txt generation, AI crawler audit, plus live GSC and Ahrefs MCP data. GSC: overview, drops, opportunities, brand-vs-nonbrand, cannibalization, compare, content-decay, index-issues, new-keywords. Ahrefs: overview, backlinks, keywords, competitors, content-gap, broken-links, new-links, anchor-analysis, dr-history, top-pages. Cross-MCP: serp, content-brief, brand-radar, site-audit-pro, report. Local: log-analysis, ai-content-check, internal-links, local, migration-check, obsidian-kb. AI Readability: llms-txt, robots-ai. Performance: lighthouse-audit, core-web-vitals, page-experience. Quality & AI Search: rich-results, ai-optimization, eeat-audit, helpful-content. Triggers on: "SEO", "audit", "schema", "Core Web Vitals", "sitemap", "E-E-A-T", "AI Overviews", "GEO", "technical SEO", "content quality", "structured data", "GSC", "Ahrefs", "backlinks", "keywords", "search console", "domain rating", "local SEO", "migration", "lighthouse", "pagespeed", "LCP", "INP", "CLS", "page experience", "interstitials", "mobile friendly", "rich results", "rich snippets", "schema eligibility", "AI optimization", "AI search readiness", "EEAT", "trust signals", "helpful content", "people-first", "content quality gate".
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。
Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. GEO analysis enriched with Ahrefs Brand Radar AI visibility data when available. Includes brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "SGE", "GEO", "AI search", "LLM optimization", "Perplexity", "AI citations", "ChatGPT search", "AI visibility", or "Brand Radar".
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。
Authentication & Authorisation control plane for Yuzu — the canonical entry point for any work on RBAC, OIDC SSO, SAML, SCIM, MFA/TOTP, AD/Entra integration, API tokens, session lifecycle, enrollment, and the audit/evidence chain. Use when the user says "/auth-and-authz", "/auth", "/iam", asks to plan or implement an enterprise A&A feature, asks "what's our auth gap to enterprise readiness", asks to audit current auth state against SOC 2 CC6.x / Workstream B, or starts work that touches `auth_*`, `rbac_*`, `oidc_*`, `api_token_*`, `enrollment_*`, or `cert_store.*`. The skill bundles current-state inventory, required-features inventory, gap matrix, the canonical workflow for adding a new A&A feature, and the load order for the routed reference docs.
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。