スキルを探す

Set up and optimize a complete local AI infrastructure — Ollama, Open WebUI, local RAG pipelines, and private model serving. Use when running models locally for privacy, compliance, offline use, or cost, or setting up GPU-accelerated local inference and RAG.

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 evaluation suites for agentic systems, choosing agent benchmarks, measuring multi-agent performance, or critiquing single-score evaluation of agents. Based on arXiv:2605.26112v1. Trigger phrases: "evaluate my agent", "benchmark agent", "measure agent reliability", "pass^k evaluation", "agent metrics beyond success rate", "trajectory quality", "memory hygiene metric", "longitudinal agent eval", "why my agent scores well on benchmarks but fails in production".

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。

Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.

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。

Runs an autonomous experiment loop on any programming task: you define the goal, metric, and eval command; the agent edits code, measures, and keeps or discards each change until interrupted. Use when optimizing a measurable target (speed, accuracy, size, score) by iteration.

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 experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo

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。

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity

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 and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response 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。

Use when diagnosing agent benchmarks or runtime failures from trajectories instead of aggregate pass rates. Builds shared action-observation decision landscapes, identifies productive cores and trap regions, profiles Access/Trap/Repair behavior, and designs conservative trap-triggered recovery experiments.

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 AI-powered trading and financial analysis agents with multi-agent LLM architectures: research pipelines, sentiment signals, portfolio optimization, backtesting, risk guardrails, and market monitoring. Use when designing or implementing an LLM-based trading or market-analysis system.

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 "design agent tools", "create tool descriptions", "reduce tool complexity", "implement MCP tools", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.

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 an autonomous agent run needs a plan before execution — decomposing the goal, setting explicit boundaries and stop conditions, and defining what the agent may decide alone versus escalate.

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 executing a previously agreed autonomous agent plan — running the steps within declared boundaries, checkpointing progress, and escalating when a stop condition is hit.

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。

Turns a structured-autonomy PR plan (plans/{feature}/plan.md) into copy-paste-ready implementation documentation with complete code for every step, saved as implementation.md. Use after a plan exists and before implementation, when each step needs fully specified changes.

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 defensive monitoring for agent systems whose risks accumulate across users, sessions, subagents, files, or tool calls. Adds online cross-context clustering with rare escalation, time-to-detect evaluation, provenance checks for control-like workspace content, and sanitized commits for persistent prompt-injection defense.

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 Hugging Face smolagents, code-executing agents, Python-action agents, Hub-shared tools, or lightweight agent prototypes that need sandboxing and provider flexibility.

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 a Python terminal UI inspired by Claude Code with Rich. Translates a detailed TypeScript/Ink-style visual reference into a staged Python architecture for logo, message stream, streaming Markdown, tools, diffs, prompt, footer, spinners, permissions, transcript mode, themes, accessibility, and tests. Separates Rich rendering from the input and widget responsibilities that require an application-owned event loop or an optional Textual layer.

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 "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

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 scalable MCP tool routing, dynamic tool retrieval, agent-tool graphs, tool inventory indexing, or routing policies for agents with many available tools.

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 "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical 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。

Use when designing or auditing an agentic AI system holistically. Activates the six-component harness framework (ℛ Reasoning, ℳ Memory, 𝒞 Context, 𝒮 Skills, 𝒪 Orchestration, 𝒢 Governance) from arXiv:2605.26112. Trigger phrases: "design an agent system", "why is my agent unreliable", "harness architecture", "system-level agent design", "beyond model scaling", "agentic infrastructure", "scale my agent system", "agent performance bottleneck".

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 turning expert materials, execution traces, repository evidence, or long-form documents into an inspectable, correctable, and empirically verified agent skill. Covers source governance, capability-vs-behavior separation, contrastive induction from successes and failures, intervention testing, versioning, rollback, and task-conditioned vs. reusable-library 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。

Use when designing retryable or crash-resilient agent workflows, especially when tools can send, charge, publish, provision, or otherwise create duplicate side effects.

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 long-horizon agents that need subagents, isolated context windows, filesystem-backed work, persistence, human approval, MCP tools, or production tracing.

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。

Scaffolds a headless agent in TypeScript using @openrouter/agent and Bun — for CLI tools, API servers, queue workers, and pipelines. No terminal UI. Use when building an OpenRouter-based agent that runs without a terminal UI, such as a CLI tool, HTTP service, or queue worker.

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。