发现 部署与运维 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Analyze context management, memory systems, and state continuity in agent frameworks. Use when (1) understanding how prompts are assembled, (2) evaluating eviction policies for context overflow, (3) mapping mem...
Master protocol for deconstructing agent frameworks to inform derivative system architecture. Use when (1) analyzing an agent framework's codebase comprehensively, (2) comparing multiple frameworks to select be...
Analyze tool registration, schema generation, and error feedback mechanisms in agent frameworks. Use when (1) understanding how tools are defined and registered, (2) evaluating schema generation approaches (int...
Extract and analyze agent reasoning loops, step functions, and termination conditions. Use when needing to (1) understand how an agent framework implements reasoning (ReAct, Plan-and-Solve, Reflection, etc.), (...
Multi-agent orchestration system that persists until all tasks are complete. Delegates to specialized subagents and coordinates parallel execution.
TNF Context Frontloading System - Inspired by Ralph Wiggum Technique. Ensures EVERY AI session starts with full ecosystem awareness. Implements "Fresh Context Is Reliability" principle. Auto-injects TNF system...
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...
將提示詞和程式碼從 Claude Sonnet 4.0、Sonnet 4.5 或 Opus 4.1 遷移至 Opus 4.5。當使用者想要更新其程式碼庫、提示詞或 API 呼叫以使用 Opus 4.5 時使用。處理模型字串更新和針對已知 Opus 4.5 行為差異的提示詞調整。不會...
Smart compaction suggestions at logical session intervals. ACTIVATE when: context getting full, transitioning between phases, user mentions "running out of context", "conversation too long". 50 tool calls re...
Master the art of converting source material into authentic, human-written content. Transform transcripts, notes, and research into polished prose that avoids AI tells while maintaining distinctive voice. Incor...
Provides expertise on Chroma vector database integration for semantic search applications. Use when the user asks about vector search, embeddings, Chroma, semantic search, RAG systems, nearest neighbor search,...
Iterative drafting system with 5-judge quality gates. This skill should be used for any writing project requiring multiple drafts and systematic quality control - profiles, deep dives, guides, articles. Include...
Generate AI images using Nano Banana Pro (Gemini). Use this skill when the user needs images - thumbnails, social posts, blog headers, or creative visuals. Follows an iterative workflow - brainstorm concepts, s...
Transform source content (podcast clips, blog posts, newsletters) into LinkedIn posts using framework-fitting method. Matches concepts to proven format categories, then adapts templates based on animating princ...
Provides expertise on Chroma vector database integration for semantic search applications. Use when the user asks about vector search, embeddings, Chroma, semantic search, RAG systems, nearest neighbor search,...
Extract compelling story structures from source material (transcripts, interviews, raw notes) using universal narrative arcs. Use this skill when transforming podcast transcripts into blog posts, creating cold...
Patterns that make writing sound AI-generated. Invoke this skill for ANY writing task - newsletters, social media, blog posts, emails. Apply these constraints automatically.
Use when designing ClickHouse table schemas, choosing MergeTree engines, optimizing slow queries (execution time > 1 second), or implementing batch INSERT patterns. Does NOT cover real-time streaming from messa...
Waypoint plans methodology and session survival patterns for Claude Code. Use when working on long-running features, need to resume after context reset, want to document task progress, or need to survive sessio...
実装計画を立案する為のスキル。Plan Subagent を実行する際に併せて使用する。
List and get Linear issues via CLI (read-only operations)
List and get Linear projects via CLI (read-only operations)
Draft brief, professional responses to GitHub PR review comments. Use /pr-respond with a PR number to fetch unresolved comments and craft replies.
Reference material for Athena when writing requirements. NOT a template - Athena writes requirements freely based on the domain. This skill provides guidance patterns that may be useful, not constraints to foll...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。