5,812 件 ・ 関連度順
概要と使いどころ
Use when starting a new feature, product, or system design. Eliminates the spec-implementation gap by making specifications the primary artifact that drives code generation. Keywords: SDD, spec-driven, PRD, feature spec, user stories, implementation plan, specification, acceptance criteria, Given-When-Then.
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。
Use when designing human approval gates for high-stakes agent actions. Keywords: human-in-the-loop, HITL, approval gate, checkpoint, confirmation, risk-tiered, action 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。
High concurrent SQLite access causing lock contention and missing indexes Keywords: sqlite, wal, indexes, performance
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 monitoring, tracing, or debugging agentic workflows in production. Keywords: observability, tracing, OpenTelemetry, Langfuse, latency, token cost, loop detection, telemetry.
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。
Reasoning data lost across agent steps and missing low-confidence fallback Keywords: sqlite, triangulation, escalation, confidence
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。
Template for creating new Kilo-Kit skills. Copy this folder and customize for your skill. Keywords: template, new, create, 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。
Use when needing 100% type-safe, schema-valid data extraction from LLMs. Keywords: structured output, JSON schema, Pydantic, Zod, type-safe, constrained decoding, validation, tool use.
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 integrating or optimizing Model Context Protocol (MCP) servers and clients. Keywords: MCP, Model Context Protocol, tool discovery, lazy loading, sampling, resource subscription, MCP server.
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。
Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments
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。
Perform triangulated cognitive research combining SQLite memory, GitHub 10k+ stars patterns, and ToT DAG benchmarking before critical architectural decisions. Automatically triggers subagent research escalation when confidence is low (<0.70). Keywords: research, benchmark, github, memory, triangulation, grounding, best-practices, escalation
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 optimizing token usage, KV cache efficiency, or context window management for LLM agents. Keywords: context optimization, KV cache, prompt caching, token budget, semantic pruning, lost-in-the-middle.
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, implementing, or debugging complex agentic workflows using state machine patterns. Keywords: state machine, durable execution, agent orchestration, graph-based agents, workflow checkpoints, C4 protocol.
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。
Core Kilo-Kit skill enforcing Hard-Gate and Iron Law principles. Ensures AI agents scan the system and codebase before proposing solutions. Keywords: hard-gate, iron-law, evidence, scan, verify, system-check, codebase
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 coordinating multiple specialized agents for complex distributed tasks. Keywords: multi-agent, orchestrator, subagent, handoff, swarm, supervisor, agent topology, coordination.
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 validating, benchmarking, or monitoring LLM application performance. Keywords: RAG evaluation, LLM-as-a-judge, CI/CD gating, trajectory scoring, test suites, prompt quality.
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。
Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding micro-interactions, or creating design documentation. Includes workflows for capturing and analyzing inspiration screenshots with chrome-devtools and ai-multimodal, iterative design image generation until aesthetic standards are met, and comprehensive design system guidance covering BEAUTIFUL (aesthetic principles), RIGHT (functionality/accessibility), SATISFYING (micro-interactions), and PEAK (storytelling) stages. Integrates with chrome-devtools, ai-multimodal, media-processing, ui-styling, and web-frameworks skills.
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 code editing, bug fixing, or software engineering agents. Keywords: SWE-agent, code agent, bug localization, patch generation, AST, diff, TDD loop, repository indexing.
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 self-correcting retrieval systems for AI agents. Keywords: RAG, retrieval, Corrective RAG, Self-RAG, query decomposition, reranking, hallucination, grounding.
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 needing global or relational understanding of codebases or knowledge corpora. Keywords: GraphRAG, knowledge graph, entity extraction, community summarization, graph traversal, Microsoft GraphRAG.
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 standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native 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。
Guides agents and users to create standards-compliant agent definitions using templates in markdown frontmatter format, ensuring context gathering, clarity, and proper metadata. Forces agents to ask clarifying questions when context is insufficient. Token-efficient documentation required. All content must be in English. Trigger: When creating a new agent definition, setting up project agents, or documenting agent 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。
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
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 Maestro's Azure Boards and Repos task/PR identity and connection requirements while identifying Orchestra's currently unavailable Azure DevOps tracker operations.
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。