「prompt」の検索結果

Research a topic to support a decision, three ways: draft a research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), turn a finished research report into a short summary with cited sources that other skills can use directly, or run the research here with parallel web searches. Built-in research types: market, domain, technical, competitive, user-voice, academic-lit; also supports choosing between candidates, and custom types via overrides. Use when the user says "deep recon", "research this", "draft a research prompt", "process this research report", "market research", "domain research", "technical research", "competitor research", "literature review", or "help me choose between"

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-first security scanning with Medusa. 3,000+ detection patterns covering AI/ML, agents, MCP, RAG, prompt injection, and traditional SAST vulnerabilities. Wraps Medusa CLI with SARIF/JSON parsing, structured finding output, OWASP mapping, and remediation guidance.

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。

Compress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG payloads, prompt caching, expensive sessions, codebase context, chat history compaction, or wants the same answer quality with fewer tokens.

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。

Hunt vulnerabilities in LLM-powered applications — direct/indirect prompt injection, system prompt extraction, ASCII smuggling, RCE via code tools, agentic AI exploits (ASI01-ASI10), data exfiltration via response channels, IDOR in chat history, jailbreak chains, RAG poisoning. Use when target has a chatbot, AI assistant, copilot, or agentic AI features.

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。

Onboarding workflow for cross-library KB query in a consulting practice. Discovers existing user-scope library registrations, prompts for additions, validates each library, helps activate the relevant ones for the current project, runs a smoke test, and reports a clear "ready" or "issues to fix" verdict. Use --verify-only to skip prompting and just validate existing setup (sub-task 23 of

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 and edit high-quality images using Google's Nano Banana Pro (Gemini 3 Pro Image) AI model. Use this skill when working with AI image generation or editing tasks including (1) Creating images from text prompts with professional quality, (2) Editing existing images with natural language instructions, (3) Multi-turn iterative image refinement, (4) Product photography and marketing visuals, (5) Creating infographics and diagrams with text, (6) Photorealistic and artistic image generation, (7) Batch image generation workflows, (8) Testing and troubleshooting Gemini image generation API. Supports up to 4K resolution, multiple aspect ratios, reference images, and advanced prompting techniques for cinema-quality 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。

Rebalances context across Memory, Custom Instructions, knowledge files, and User Preferences in Claude Projects. Audits Memory for redundancy, staleness, and misplacement; prescribes optimization including Codification of stable Memory patterns into explicit User Preferences or Project CI rules. Use when user says "optimize my memory," "what should be in my memory," "trim my knowledge files," "reduce my context usage," "rebalance my project," "what should be in my preferences vs memory," or asks whether something belongs in Memory, a knowledge file, or User Preferences. Also trigger on symptom-phrased: "my project feels bloated," "Claude keeps forgetting things," "my context window keeps hitting limits." Activate whenever Memory-layer balance is the primary concern. Do NOT use for full Project audits (use rootnode-project-audit if available), single-prompt evaluation (use rootnode-prompt-validation if available), or global-layer audits that don't touch Project Memory (use rootnode-global-audit if available).

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。

Detects seven structural anti-patterns in Claude Projects that cause unpredictable output, ignored instructions, and degraded quality. Diagnoses Monolith, Orphan File, Echo Chamber, Phantom Conversation, Kitchen Sink, Misaligned Hierarchy, and Blurred Layers. Use when user says "what's wrong with my project," "Claude ignores my instructions," "diagnose my project," "why is output inconsistent," "review my project setup." Also trigger on symptom-phrased: "Claude doesn't follow my rules," "my instructions keep getting overridden," "my Project isn't behaving as designed." Use alongside rootnode-project-audit if available for deeper structural analysis. Activate whenever the user describes symptoms of unreliable, inconsistent, or degraded Claude Project output, even if they do not name a specific pattern. Do NOT use when the user's primary request is Memory-layer rebalancing (use rootnode-memory-optimization if available) or scoring a single prompt (use rootnode-prompt-validation if available).

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 audit of a user's entire Claude environment — combines Project audit (six-dimension Project Scorecard, seven anti-patterns) with Global audit (six-dimension Global Layer Scorecard) plus Cross-Layer Alignment Check across all nine layers and Evolutionary Recommendations across four pathways. Produces a unified action plan. Use when user says "full audit of everything," "audit my entire Claude setup," "full stack audit," "comprehensive review of my project and preferences," "check everything," or wants the complete health check of both a specific Project AND their global configuration. Also use when a project audit reveals cross-layer issues that require full-stack visibility. Do NOT use for auditing only a Project (use rootnode-project-audit if available) or only global layers (use rootnode-global-audit if available). Do NOT use for single prompt evaluation (use rootnode-prompt-validation if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy 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。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.

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 setting up a secure email inbox for any AI agent — configuring inbound email via Resend, webhooks, tunneling for local development, and implementing security measures to prevent prompt injection attacks. Also use when someone mentions 'agent email', 'bot inbox', 'receive emails for agent', 'agent webhook', 'email security for AI', 'prompt injection via email', 'inbound email for bot', or wants their AI agent to receive and respond to emails securely.

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 visual asset briefs, ad copy variants, AI image prompts, video scripts, and storyboards. Full creative production system with 5 specialized modes: product photos, product video, social graphics, talking heads, and ad creative. Make sure to use this skill whenever the user mentions any visual or creative marketing need — ad creative, image prompts, video scripts, thumbnails, banners, social graphics, product photography, storyboards, or marketing visuals of any kind. Even if they just say 'I need images for my campaign' or 'make something visual', this is the skill. Owns thumbnail and banner briefs plus the creative direction. Includes platform-specific dimensions, AI anti-slop techniques, and Remotion composition templates. For rendering the actual image file, see /image-gen; for AI-generated marketing/brand videos, see /higgsfield-generate; for stitching slides into an MP4, see /video-content.

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 professional brand-quality product images via Higgsfield's mode-specific prompt enhancement pipeline. Entry point for any product visual with a specific format or platform target. Use whenever: "product photoshoot", "lifestyle product shots", "Pinterest pin", "hero banner", "ad pack", "virtual try-on", "studio shot", "carousel images", "Meta ads creative", "model wearing product", "levitating product", "splash shot", "CGI style product", "restyle product image", Shopify image, brand campaign visual. 10 modes: product_shot, lifestyle_scene, closeup_product_with_person, moodboard_pin, hero_banner, social_carousel, ad_creative_pack, virtual_model_tryout, conceptual_product, restyle. Backend assembles the prompt — never call gpt_image_2 directly for product shots. NOT for: one-off images without a product (use image-gen), branded video with avatars (use higgsfield-generate), Soul training (use higgsfield-soul-id). Requires Higgsfield CLI and authed account.

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。

Write and improve prompts for Kling AI video generation, and pick the right Kling model for the job. Covers image-to-video, text-to-video, multi-shot storyboards, talking avatars from one photo plus audio, motion transfer, video editing of an existing clip, Element Reference for character consistency, Voice Control and voice cloning, native audio and dialogue, first/last frame control, credit and API costs, and troubleshooting failed generations.

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。

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

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。

Design effective reasoning processes for AI agents and optimize decision-making strategies. Use when designing agent prompts, improving decision quality, implementing specialized reasoning modes, creating reasoning traces, or debugging agent mistakes. Covers prompting, chain-of-thought, reasoning depth, and decision 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。

This skill should be used when the user asks to "generate tasks", "create implementation plan", "break down feature", "write agent prompts", "decompose into tasks", "create work items", or when creating agent-ready task descriptions from PRD and SDD documents.

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。

Design agent system prompts with explicit behavior rules and cognitive control. This skill should be used when users need to define agent instructions, create intent-to-tool mappings, establish confirmation policies, or prevent hallucinated actions in AI agents.

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 building AI agents using prompt-native architecture where features are defined in prompts, not code. Use it when creating autonomous agents, designing MCP servers, implementing self-modifying systems, or adopting the "trust the agent's intelligence" philosophy.

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 Claude Code plugin agent .md files: writes YAML frontmatter (name, model, color, tools, hooks, disallowedTools), crafts system prompts, and creates triggering example blocks with context and commentary. Validates agent structure against naming, length, and format constraints. Use when the user asks to create an agent, add an agent, write a subagent, configure agent frontmatter, design agent system prompts, set agent tools or colors, build an autonomous agent, or add agent hooks.

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。

Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks requiring consistent high-quality performance with deeply embedded domain knowledge.

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。

Creates Claude Code agent files (.claude/agents/*.md) with YAML frontmatter, tool permissions, and system prompts. Use when building new agents, configuring agent frontmatter, writing agent system prompts, or setting agent tool 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。

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。