Claude Skills by majiayu000

Show the current project context. Summarizes active increment, spec root, commands, and suggests the next safe action.

RLM-style recursive memory exploration - dynamically navigate the memory graph

Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.

Guidance for deep knowledge graph traversal across memories, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.

Manage offline reference material in the `extra/` directory. Use when needing external documentation, library source code, screenshots, PDFs, or API specs. ALWAYS check `extra/` before web searches. HALT and ask the human when required material is missing - do NOT fall back to WebFetch/WebSearch.

Manage offline reference material in the `extra/` directory. Use when needing external documentation, library source code, screenshots, PDFs, or API specs. ALWAYS check `extra/` before web searches. HALT and ask the human when required material is missing - do NOT fall back to WebFetch/WebSearch.

Extract decisions and learnings from Claude session transcripts. Triggers: "extract learnings", "process pending", SessionStart hook.

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

The terminal step of /feature and /sprint. Routed to once commit-gate has cleared, to decide the branch's fate — merge via PR, open a PR, or discard. Direct merge to the default branch is forbidden; every change lands through a PR. Under /sprint the skill auto-selects "open PR" and surfaces the merge decision to the user.

The terminal step of /feature and /sprint. Routed to once commit-gate has cleared, to decide the branch's fate — merge via PR, open a PR, or discard. Direct merge to the default branch is forbidden; every change lands through a PR. Under /sprint the skill auto-selects "open PR" and surfaces the merge decision to the user.

Mine transcripts into learnings.

Orient to project structure and load context. Use at the start of each new session or after context reset to understand the project state.

Use when starting a new session, the project has changed significantly, or you need a fresh context summary.

Load user profile and AI personality directives. Returns structured context for personalizing skill behavior and communication style.

Cross-project knowledge search, pattern recognition, and insight management — the long-term memory across all projects

Cross-project knowledge search, pattern recognition, and insight management — the long-term memory across all projects

Build or update a CONTEXT.md domain glossary for the current project. Establishes shared vocabulary with term definitions, avoid-aliases, and relationships so agents use consistent, concise language. This skill should be used when starting a new project, when domain terminology is inconsistent across sessions, when the user says "build a glossary", "define our terms", "shared vocabulary", or "domain language", or when an existing CONTEXT.md needs updating after new domain concepts emerge.

This skill should be used when the user asks to "/gobby-memory", "remember", "recall", "forget memory". Manage persistent memories across sessions - store, search, delete, update, and list memories.

Manage persistent context threads for cross-session work

Set up and maintain Hierarchical Agent Memory (HAM) for Codex using scoped local memory files. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "HAM audit".

Set up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "ham sync".

Use when ongoing work must continue in a new conversation, session, or agent with no shared history. Triggers: 'handoff', 'prepare context for next chat', 'summarize for a new session', 'continue this in another conversation'. Not for same-chat status updates or repository documentation.

Write compact session handoffs.

Write compact session handoffs.

Session handoff — compress current context into a structured prompt for seamless continuation in a new session. Use when: switching sessions, running low on context, or needing to hand off work.

Hand off to a fresh Claude session. Use when context is full, you've finished a logical chunk of work, or need a fresh perspective. Work continues from hook.

Prepare for context handoff when running low on context. Syncs docs and commits so a fresh agent can continue.

Use handoff tools for session continuity. Create handoffs at end of session, read handoffs at start, search past handoffs for context. Trigger words - "handoff", "end session", "wrap up", "continue from", "where we left off", "context high", "running low", "before I forget".

Generate a session handoff note for context resets or multi-day work.

Generate a comprehensive markdown summary of our conversation for seamless handoff to another AI agent. Use when ending a session or transferring work.

Generate a comprehensive markdown summary of our conversation for seamless handoff to another AI agent. Use when ending a session or transferring work.

Background memory organ for AI agents. Runs separately from the main agent—encoding, decaying, and reinforcing memories automatically. Just like the real hippocampus in your brain. Based on Stanford Generative Agents (Park et al., 2023).

Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.

Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".

Automatically capture implicit technical decisions and uncertainties encountered by AI agents during coding work. This skill logs decision points where the agent chose an approach without explicit user guidance, enabling later review and context enrichment. Use this proactively during any coding task to track "what choices I made and why."

Analyzes conversation history to improve CLAUDE.md files. Use when you notice patterns in how Claude misunderstands requests, want to consolidate repeated guidance, or improve instruction clarity based on actual usage.

Create searchable knowledge base from existing documentation and code for fast context lookup in brownfield projects. Indexes .md files with sections/keywords, maps code exports to documentation, generates search.json, quick-ref.md, and glossary.md in .claude/index/. Use when onboarding to brownfield projects or when documentation needs better discoverability.

Index a folder's contents into the context system for fast retrieval

初始化和增量更新 AI 记忆文件（CLAUDE.md、AGENTS.md、GEMINI.md）。通过交互式选择和差异对比，智能补全记忆项内容。触发条件：当用户提及初始化记忆文件、更新 CLAUDE.md、同步 AI 记忆、init-ai-md 等关键词时主动调用。

Generate $HOME/.claude/CLAUDE.md with AI-driven environment detection and advanced configuration options

Generates hierarchical context files (CLAUDE.md) throughout a project directory tree, providing AI agents with directory-specific knowledge for better code understanding. Use when setting up a new project for AI-assisted development.

Analyze project structure and update AGENTS.md with detected tech stack, commands, and configurations.

Analyze a codebase and create or improve an AGENTS.md file for future agent instances. Use when onboarding to a repository and capturing hard-to-rediscover conventions, constraints, and rationale.

Initialize or update CLAUDE.md coding standards for any project by auto-detecting tech stack and assembling rules from the claude-rules template library. Use when user says "init rules", "初始化规范", "生成 CLAUDE.md", or wants to set up coding standards.

Initialize Contextium session state and verify environment

Use to set up Obsidian vault and populate it with existing codebase knowledge. Enables context memory for AI development.

Load relevant .agents context.

Load relevant .agents context.

Load relevant .agents context.

Instar's identity system gives agents a continuous self that survives