Claude Skills by majiayu000

Validate CLAUDE.md structure, formatting, and quality. Use when checking context files for compliance, ensuring proper structure, or verifying before commits.

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...

Create or update continuity ledger for state preservation across clears

Create or update continuity ledger for state preservation across clears

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

Stateless conversation management with database-backed history, message persistence, and scalable architecture. Use when handling chat state, loading history, or building stateless APIs.

Use Copilot Spaces to provide project-specific context to conversations. Use this skill when users mention a "Copilot space", want to load context from a shared knowledge base, discover available spaces, or ask questions grounded in curated project documentation, code, and instructions.

Transform Claude Code into your personal Jarvis - an AI operating system that knows your projects, preferences, and workflows across sessions. Use this skill when setting up personal AI systems, building context-aware assistants, or creating persistent memory across projects.

Guidance for maintaining memory quality through curation. Covers updating outdated memories, marking obsolete content, and linking related knowledge. Use when memories need modification, when new information supersedes old, or when building knowledge graph connections.

Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents. Stores entities (modules, functions), their dependencies (imports), public API (shared/exports), and reasons for every connection. Use when: (1) project has a .dsp/ directory, (2) user asks to set up DSP or bootstrap project structure, (3) creating/modifying/deleting code files in a DSP-tracked project, (4) navigating project structure, understanding dependencies, or finding...

End-of-session reflection. Extracts memories, suggests updates to about-taylor.md and CLAUDE.md. Run before ending a long session or when context is getting full. Triggers on "debrief", "extract memories", "session summary".

Analyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown. Use when the user asks about session size, context usage, or when you notice the context window is getting full.

Resolves framework reference IDs to their content. Use when you need to look up a document, decision, observation, task, or ADR by its ID. Triggers on "resolve reference", "look up THY-001", "find DEC-...", "get content of", "what is ADR-001".

Load minimal relevant context for the current task

Writes comprehensive handoff note at session end. Captures work done, files changed, remaining tasks, and next steps. Use before ending any work session or switching contexts.

Hierarchical memory architecture combining short-term, long-term, and episodic memory layers. Based on Mem0 research showing 26% accuracy improvement. Use for persistent knowledge, context management, and RAG optimization.

実装開始時のコンテキストセットアップ。関連ナレッジを検索し、効率的な実装開始を支援。新規実装タスク開始時に自動トリガーまたは明示的に呼び出し可能。

Extract reusable knowledge from the current session into a persistent skill. Use when you discover something non-obvious, create a workaround, or develop a multi-step workflow that future sessions would benefit from.

Load architecture principles and core conventions for grounding work against project standards - simple context loading for all workflow stages

Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, claude-mem, past decisions, record this, or cursor-mem integration. Do NOT load for: implementation work, reviews, ad-hoc notes, or in-session logging.

Execute extract and use project memories from previous sessions for context-aware assistance. Use when recalling past decisions, checking project conventions, or understanding user preferences. Trigger with phrases like "remember when", "like before", or "what was our decision about".

Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.

Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation.

This skill should be used when the user asks to "remember project context", "save SEO data", "track campaign progress", "store keyword data", "manage project memory", "remember this for next time", "save my keyword data", or "keep track of this campaign". Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with intelligent promotion/demotion.

Spatial organization of knowledge in navigable directories

Searches conversation history and semantic memory to find previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting new work to recall prior decisions and avoid repeating past discussions.

Persist and recall context between sessions

Automatic documentation memory system for AI agents. Ensures context is loaded at session start and documentation is updated after changes.

Enterprise Claude Code context window optimization with 2025 best practices: aggressive clearing, memory file management, MCP optimization, strategic chunking, and quality-over-quantity principles for 200K token context windows.

Claude Code memory management, context persistence, and knowledge retention.

Enterprise context and session management with token budget optimization and state persistence

Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use when dealing with token budget management, context window limits, session handoff, state persistence across agents, or /clear strategies. Do NOT use for agent orchestration patterns (use moai-foundation-core instead).

Load session context from handoff files

Recall the reasoning behind a past change by locating the Claude Code transcript that produced it. Use when the user asks to \"recall reasoning\", \"find reasoning\", \"look up reasoning\", \"recall implementation reasoning\", \"find the rationale\", \"why did I do X\", \"recall from transcripts\", or \"find the transcript for this commit\".

Based on the Recursive Language Models (RLM) research by Zhang, Kraska, and Khattab (2025), this skill provides strategies for handling tasks that exceed comfortable context limits through programmatic decomposition and recursive self-invocation. Triggers on phrases like "analyze all files", "process this large document", "aggregate information from", "search across the codebase", or tasks involving 10+ files or 50k+ tokens.

Apply R&D framework to optimize prompts and context. Use when optimizing context window usage, reducing prompt size, delegating to specialized agents, or applying systematic context management.

Use when loading, saving, or reflecting on session context - provides structured workflows for session lifecycle management and reflection outputs.

Use when a prompt or corpus is long/dense (multi-docs, logs, codebases) and you want a reproducible map/reduce pipeline. Trigger this skill to slice inputs, run per-slice codex/gemini subcalls, and aggregate results with manifests/logs via the slice runner (preferred default), falling back to manual REPL slicing only if needed.

策略性压缩 — 在逻辑边界手动压缩上下文，而非任意自动压缩。保留关键决策和约束，丢弃中间探索过程。

Search and analyze Claude Code transcripts for past decisions, solutions, and discussions. Use when recalling past context, finding solutions to previously-solved problems, understanding session history, or restoring context after compact/clear.

Outbox Pattern knowledge base. Provides patterns, antipatterns, and PHP-specific guidelines for transactional outbox, polling publisher, and reliable messaging audits.

Design RBAC/ABAC policies and permission boundaries.

Implement Role-Based Access Control (RBAC), permissions management, and authorization policies. Use when building secure access control systems with fine-grained permissions.

Build comprehensive chromatin accessibility maps by aggregating ATAC-seq and DNase-seq narrowPeak data across multiple ENCODE experiments, donors, and labs. Use when the user wants to answer "where is chromatin accessible in my tissue?" by combining peak calls into a union peak set. Handles cross-lab variation, ATAC vs DNase platform differences, and ENCODE blocklist filtering.

セマンティックHTML/JSXとWAI-ARIAを「最小で正しく」適用し、キーボード操作・スクリーンリーダ・コントラスト等を満たす実装を作るための判断軸。ネイティブ要素優先、ARIAの過剰使用を避ける。

Plan accessibility compliance - WCAG 2.2, Section 508, EN 301 549, inclusive design principles, audit planning, and remediation strategies.

Reviews UI for accessibility issues against WCAG 2.1/2.2 AA. Triggers on "is this accessible?", "check accessibility", or contrast/a11y review requests.

Use when defining ABM tiers, scoring logic, and coverage rules.

AWS Controllers for Kubernetes (ACK) for Kubernetes-native AWS resource management. Use when managing AWS resources via kubectl, implementing GitOps for infrastructure, creating self-service developer platforms, integrating AWS services with EKS workloads, or adopting existing AWS resources into Kubernetes.

Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization.