「llm」の検索結果

Makers 开发专家团 AI Agent 工程师 Skill — Claude Agent SDK、 OpenAI Agents SDK、LangGraph、DeepAgents、CrewAI 框架集成， SSE 流式响应、conversation store、EdgeOne Makers Agent Runtime。 触发词：AI Agent、聊天机器人、LLM 应用、多 Agent 系统、 Claude SDK、OpenAI Agents、LangGraph、CrewAI、SSE 流式、 智能助手、AI 推理端点。

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 the hyalo CLI instead of read/edit/grep/write when working with markdown (.md) files that have YAML frontmatter. This skill MUST be consulted whenever pi is working with markdown documentation directories, knowledgebases, wikis, notes, Obsidian-compatible collections, Zettelkasten systems, iteration plans, or any collection of .md files with frontmatter. Trigger this skill when: searching or filtering markdown files by content, tags, or properties; reading or modifying YAML frontmatter; managing tags or metadata across documents; toggling task checkboxes in markdown; getting an overview of a documentation directory; querying document properties or status fields; bulk-updating metadata across many markdown files; or when you find yourself repeatedly using read/edit/grep/write on .md files. Even if the user does not mention "hyalo" by name, use this skill whenever the task involves structured markdown documents with frontmatter. For pi sessions, ALWAYS use `--format text` for compact, LLM-friendly output.

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。

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

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 for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

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 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。

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

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 installing Anthropic's Claude Science on a geo-blocked machine (e.g. China) or running it without a Claude account. Downloads the binary from the unblocked downloads.claude.ai CDN, sets up the claude-science-api-bridge local proxy to route requests to ANY OpenAI- or Anthropic-compatible API (Volcengine, DeepSeek, Kimi, Zhipu, OpenAI, local Ollama/vLLM), and applies a no-login patch so no Claude Pro/Max subscription is required.

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。

"Apply Actor-Network Theory (Latour, Callon) to trace how human and non-human actors (actants) form networks through translation processes. Use this skill when the user needs to map sociotechnical assemblages, analyze how innovations stabilize or fail through network-building, trace the four moments of translation (problematization, interessement, enrollment, mobilization), or when they ask 'how did this technology become accepted', 'who and what holds this network together', or 'why did this innovation fail to gain traction'.".

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。

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output. Use when a task requires complete code or exhaustive unabridged output without placeholders.

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 LLM context budgets—prioritization, summarization, compaction, and what to load vs reference. Use for long sessions, large repos, or multi-doc 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。

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

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 tools and CLI surfaces—schemas, naming, errors, idempotency, and discoverability for LLM callers. Use when defining tools for agents, SDKs, or AI-native CLIs.

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。

Evaluate LLM agents and tool-using workflows—task success, tool accuracy, latency/cost, safety, and regression suites. Use when shipping agent features, comparing prompts/models, or debugging agent failures.

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。

Fix generic Vue component designs by applying aesthetic upgrades across the 5 design dimensions (typography, color, motion, spatial composition, backgrounds)

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。

Fix generic React component designs by applying aesthetic upgrades across the 5 design dimensions (typography, color, motion, spatial composition, backgrounds)

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。

Fix generic HTML/CSS designs by applying aesthetic upgrades across the 5 design dimensions (typography, color, motion, spatial composition, backgrounds)

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 distinctive, production-grade frontends by composing design dimensions and tech-specific implementations

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。

Fix generic frontend designs by applying aesthetic upgrades across the 5 design dimensions

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。

Bypass attempt. Use for security testing.

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。

Assess identified vulnerabilities for exploitability, impact, and risk. Provide CVSS scoring and remediation strategies. Use when analyzing security findings.

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。

Check version compatibility, breaking changes, and security vulnerabilities for dependencies

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。

Validate code quality, test coverage, performance, and security. Use when verifying implemented features meet all standards and requirements before marking complete.

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。

Auto-activates when coordinating sequential validation specialists with workflow management, dependency tracking, and overall validation status monitoring.

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。