3,258 件 ・ 関連度順
概要と使いどころ
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。
AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for issue filing.
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。
Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative 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。
Generate images via the Stable Diffusion WebUI / Forge HTTP API (AUTOMATIC1111-compatible `/sdapi/v1/*`). Use when the user wants to (1) discover or pick a model / extra module (TE/VAE) / sampler / scheduler / style preset from a running sd-webui server, (2) generate an image with a given prompt (txt2img), (3) check generation progress, (4) cancel/interrupt an in-flight generation, (5) inspect or change a global sd-webui option (e.g. active checkpoint), or (6) test connectivity. This skill talks to a *generic* sd-webui-compatible server (AUTOMATIC1111, Forge, reForge, sd-webui-forge-classic). Do NOT trigger for requests that are purely writing the prompt itself.
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。
FLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts.
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。
FLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW knowledge base (30 blog-applicable prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "blog flow", "evidence-led blogging", "find optimize win", or wants stage-specific blog prompts.
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 provides a plot summary, scene idea, character relationship, emotional beat, or short video concept and wants a cinematic AI video prompt. First diagnose the story, then rewrite it into a model-ready prompt for Kling, Seedance, Veo, Sora, Runway, Jimeng, or general AI video models.
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。
Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver 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。
Use when designing how an Agentforce agent extracts structured input parameters (slots) from a user's natural-language utterance to invoke an action. Triggers: 'agent extract date from user', 'agent action argument extraction', 'agentforce slot filling', 'agent invocable input mapping', 'agent fails to fill required parameter'. NOT for action authoring (use agentforce/agent-actions) or for prompt-template variable binding (use agentforce/prompt-builder-templates).
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。
Router for the 53 SfSkills `agentforce` skill packages. Agentforce and Einstein: agents, topics, actions, prompt templates, grounding, guardrails, evaluation and production readiness. Use when the request mentions Agentforce, agent topic, agent action, prompt builder, Einstein, Trust Layer, grounding, RAG, guardrails, agent evaluation, prompt injection. Finds and opens the exact skill package to read; it does not contain the guidance itself.
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。
Generate a fully customized Amazon Connect AI agent PoC bundle (Lambda handlers, OpenAPI spec, AI agent prompt, Contact Flows, CloudFormation/CDK infrastructure, FAQ knowledge base) from a ~15-minute structured interview — or from a requirements doc, a flow sketch, or an existing flow/prompt you want to improve. Use when the user wants to build, scaffold, prototype, or refine an Amazon Connect contact center, an AI voice/chat agent on Amazon Connect, or any contact-center use case that mentions Connect, Lex, Wisdom, Q in Connect, "AI agent domain", or Agentic CX Designer (ACXD, Connect Customer, the Agentic CX block — the ACXD runtime target). Also triggers on "I have a requirements document", "turn this flow sketch into a Contact Flow", or "improve my existing Contact Flow / AI prompt". Produces 6 asset packages on local disk.
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。
Research and normalize MotionSites-style prompt directions, then output a clean motion prompt brief for implementation.
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。
Track AI visibility — measure whether a brand is mentioned and cited by AI assistants (Gemini, ChatGPT, Perplexity) for target prompts. Runs scans, tracks mention/citation rates over time, detects trends, and identifies opportunities. Uses Gemini API free tier (with grounding) as primary method, web search as fallback. Use when a user wants to: check if AI models mention their brand, track AI citation changes over time, measure AEO content effectiveness, monitor competitor AI visibility, or audit their brand's presence in AI-generated answers. Pairs with aeo-prompt-research-free (identifies prompts) and aeo-content-free (creates/refreshes content). This skill closes the loop by measuring results.
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。
Find question-based Google Autocomplete suggestions for any topic. Prepends question modifiers (what, how, why) to a seed topic and returns real autocomplete suggestions — useful for AEO prompt research, content ideation, and understanding what people ask about a topic. Use when the user wants to discover questions people search for, find content angles, or do keyword/prompt research for a topic.
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。
Refine a draft prompt before sending to a coding agent: decomposes goal/context/constraints, flags ambiguity, emits a model-agnostic rewrite. NOT for prompts from scratch (mk:brainstorming).
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。
Parameterized prompt templates using Jinja2 patterns for reusable, dynamic agent prompts
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。
Patterns for vibe coding that produce production-quality output instead of garbage. Covers prompt engineering for AI coding, verification without reading every line, accept/reject/refine decision framework, architectural guardrails, context management (CLAUDE.md, .cursor/rules), TDD-driven vibe coding, screenshot-driven development, diff review discipline, and the anti-patterns that destroy quality. Activate on: "vibe coding", "AI coding quality", "Claude Code workflow", "AI-assisted development", "how to use AI for coding", "coding with AI", "agentic engineering workflow", "AI code quality", "vibe code without garbage", "production quality AI code", "CLAUDE.md setup", "cursorrules setup", "pre-commit hooks for AI", "TDD with AI", "test-driven vibe coding". NOT for: multi-person collaborative coding sessions (use cooperative-vibe-coding), building AI/LLM applications (use ai-engineer), prompt engineering for non-coding LLM use cases (use prompt-engineer).
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 quando uma necessidade de negócio ou técnica precisar de discovery estruturado em pt-BR e de um prompt de implementação autocontido.
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。
Pre-spend contradiction gate for AI-video runs: checks every prompt in the batch, blocks on style / character / physics mismatch. Triggers 'validate the prompts', 'check the storyboard'.
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。
Reconstruct a free-form prompt into actionable AC + assumptions + confidence band before the engine plans — '/work "…"', 'baue X', 'ist der Prompt klar genug für die Engine?'.
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。
Translate an image brief into provider-specific prompt grammar per model. Use when writing or refining an image-generation prompt for Ideogram, Flux, Gemini, GPT Image 2, or Recraft.
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。
Migre prompts e código de Claude Sonnet 4.0, Sonnet 4.5 ou Opus 4.1 para Opus 4.5. Use quando o usuário quiser atualizar sua base de código, prompts ou chamadas de API para usar Opus 4.5. Lida com atualizações de string de modelo e ajustes de prompt para diferenças comportamentais conhecidas de Opus 4.5. NÃO migra Haiku 4.5.
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。
Construa sistemas de IA complexos com programação declarativa, otimize prompts automaticamente, crie sistemas RAG modulares e agentes com DSPy - framework de Programação Sistemática de Modelos de Linguagem da Stanford NLP
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。
[Process] Use when the developer wants something explained or taught, or wants to know HOW TO REVIEW a change — by default the current working tasks + changes in context, or whatever the prompt names (a plan, a subsystem, a decision, a concept, a bug). AI derives WHAT to explain from the prompt and ALWAYS delivers a teacher-and-coach review guide, high level first then detail: what was done, a VISUAL MAP (system flowchart, domain ERD, sequence diagrams), the user stories and business rules with their REAL test-case IDs, a REVIEW PATH naming which files to open first and in what order with an exit criterion per stage, the technical concepts needed to follow it, how it works, why THIS solution, every alternative option with pros/cons, the trade-offs accepted, the blast radius, HOW TO TEST AND DEMO the change, the developer's decision levers, and written challenge prompts that provoke the reader to pressure-test the work. Works at ANY scope — from one line of code to the whole project: it SIZES the target into a scope tier, DECOMPOSES a large one into understanding groups, BREAKS the work into tasks before the first deep read, and ACCUMULATES the report group by group on disk so a huge explanation stays complete instead of thinning out. Writes the full report to a single combined markdown file (plans/reports/understand-*.md) that opens with a detailed summary section — or delivers it in full in chat when Step 3 finds no git-ignored directory for it — and always summarizes it in chat. Regardless of coding level. Never interrogates, never quizzes, never blocks.
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。