Loading...
Loading...
Found 112 Skills
Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context infrastructure to an existing repo, user asks to set up AGENTS.md, add intent layer, make agents understand the codebase, or scaffolding AI-friendly project documentation.
Strategies for managing LLM context windows effectively in AI agents. Use when building agents that handle long conversations, multi-step tasks, tool orchestration, or need to maintain coherence across extended interactions.
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, constructing context from retrieved documents, adding citations, or implementing hybrid search.
Recursive Language Model context management for processing documents exceeding context window limits. Enables Claude to match Gemini's 2M token context capability through chunking, sub-LLM delegation, and synthesis.
Working memory management, context prioritization, and knowledge retention patterns for AI agents. Use when you need to maintain relevant context and avoid information loss during long tasks.
原始人スタイル subagent への委譲判断ガイド。`genshijin-investigator` (コード位置特定)、 `genshijin-builder` (1-2ファイル編集)、`genshijin-reviewer` (diff レビュー) を inline作業 or vanilla `Explore` の代わりにスポーンするタイミングを示す。subagent 出力は原始人圧縮 → 主コンテキストに戻る tool-result が約60%縮小 → 長セッション持続。 Trigger: 「subagent 委譲」「genshijin-crew 使用」「investigator/builder/reviewer 起動」「コンテキスト節約」「圧縮 agent 出力」。
Set up and manage a Memory Bank system for cross-session context continuity across AI coding agents. Use when the user mentions 'memory bank' with any action intent — setup, install, initialize, init, update, refresh, sync, status, check, read, show, review, display, or equivalents in any language (e.g. Turkish: kur, kurulum, güncelle, durumu, oku; German: einrichten, aktualisieren; Spanish: configurar, actualizar; French: installer, mettre à jour). Supports Claude Code, Cursor, Windsurf, Cline, GitHub Copilot, Roo Code, Aider, Antigravity, and OpenAI Codex.
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.
Best practices for Claude Code performance optimization, context management, storage cleanup, and troubleshooting slowdowns
Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. Activates automatically after plan-interview and intent-framed-agent. Stays active through execution and hands off cleanly to simplify-and-harden and self-improvement when the wave completes naturally or exits via handoff. Use this skill whenever a multi-step agent task is underway and session continuity or context drift is a concern. Especially important for long-running tasks, complex refactors, or any work where degraded context would silently corrupt the output. Trigger even if the user doesn't say "context surfing" — if an agent task is running across multiple steps with intent and a plan already established, this skill is live.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Write, audit, and improve agent context files (AGENTS.md, CLAUDE.md) for AI coding agents. Use when creating or improving agent context for a codebase.