Claude Skills by majiayu000

File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running w...

Save Parzival session handoff document to Qdrant for cross-session memory

Save Parzival session handoff document to Qdrant for cross-session memory

Save a Parzival insight or learning to Qdrant for cross-session memory

Save a Parzival insight or learning to Qdrant for cross-session memory

Use this skill when creating a context handoff file, pausing work mid-phase, stopping work temporarily, or creating a checkpoint for session resumption. Triggers include "pause work", "stop work", "create handoff", "save progress", and "pause session".

Write stable learnings, decisions, and patterns to durable storage like CLAUDE.md or knowledge files. Use when saving project decisions, recording patterns, or updating long-term memory.

Persistent memory storage private to the agent session.

View an existing person's profile or create a new one when meeting someone.

Saves complete session state to STATUS.json for seamless continuation across conversations. Captures git context, in-progress tasks, service status, focus area, and next actions. Use at the end of work sessions, before context limits, or when switching to a different task. Do NOT use mid-task or for quick questions - the overhead is only worthwhile when you actually need to resume later.

Use at start of new session to restore context from STATUS.json - loads previous state, displays session type, shows what to continue working on. Calculates session type (Continuation/Resume/Fresh Start) based on time gap. Do NOT use mid-session or when starting fresh work unrelated to previous session - just begin the new task directly.

Captures working state before it is lost. Use before context compaction, when switching between unrelated tasks, after completing a logical phase of multi-step work, or when work will resume in a new session. Triggers on long tasks, multi-file changes, context warnings, or "continue later" scenarios.

This skill should be used when the user asks to "load feature context", "resume feature work", "prime feature N", "continue feature N", or wants to load all planning artifacts for a specific feature number.

Get a general understanding of the codebase (stack, key files, structure, etc) and/or specific feature

This skill should be used when the user asks to "prime the project", "load context", "get oriented", "what is this project", or wants to understand the codebase structure before starting work.

Orient to current project by reading CLAUDE.md and architecture docs. Auto-invokes when Claude detects a new or unfamiliar repository. Can also be triggered by "orient me", "what is this project", or "prime session".

Template and guide for restructuring large documentation files into token-efficient directory structures. Reduces context bloat by 40-60% while maintaining accessibility.

Comprehensive project context detection and state awareness. Use when

<ONBOARD> Use on first session in a project, or when user asks for codebase overview. Creates persistent glossary, architecture maps, and decision records to solve agent amnesia.

<ONBOARD> Use on first session in a project, or when user asks for codebase overview. Creates persistent glossary, architecture maps, and decision records to solve agent amnesia.

Captures project-specific patterns and anti-patterns into the project's configuration file. Loaded by other skills (bug-killer, feature-dev, etc.) when they discover project-specific knowledge worth encoding for future sessions.

Internal metacognitive skill for episodic memory retrieval cues — surfaces relevant workflows when needed

Capture each prompt into Graphiti memory (episodes) for this repo/user.

Memory Infrastructure for Autonomous Agents

起居注——会话事件记录，tuichao 时写入，morning-court 时读取，追踪跨会话历史

Show memory buffer status including pending, synced, and failed entry counts. Quick health check without syncing.

Sync buffered memories to Cognee. Use when agent-memory reconnects or to force sync pending entries.

Resume from saved session state after interruption or compaction. Recovers context from checkpoints and agent-memory.

Meta-skill that wraps reasoning skills to capture notes in real-time, protecting against context compression. Creates checkpoint files during reasoning sessions.

Meta-skill that wraps reasoning skills to capture notes in real-time, protecting against context compression. Creates checkpoint files during reasoning sessions.

Search Origin's local memory by query. Targeted lookup, not orientation. Invoked as `/recall <query>`. Use when the user asks "do you remember", "what do you know about", "look up".

Recall the reasoning behind a past change from Codex session history when available, falling back to commit diff and surrounding code. 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\".

Query the memory system for relevant learnings from past sessions using semantic search.

Use Recent Data to find and apply recently accessed topics and resources.

Guide for using Recent Data (topics, resources, pages). Use when working with recently accessed items, implementing recent lists, or accessing session store recent data. Triggers on recent data usage or implementation tasks.

Guide for using Recent Data (topics, resources, pages). Use when working with recently accessed items, implementing recent lists, or accessing session store recent data. Triggers on recent data usage or implementation tasks.

Guide for using Recent Data (topics, resources, pages). Use when working with recently accessed items, implementing recent lists, or accessing session store recent data. Triggers on recent data usage or implementation tasks.

This skill should be used when facing long-context tasks, processing large documents, handling multi-file analysis, aggregating information across many sources, answering questions requiring hierarchical reasoning, or when context length would cause "context rot" degradation. 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 of input.

Summarise current status, completed work, and remaining tasks when context is running low. Use when you need to hand off work or document progress before context limit.

Store a learning, pattern, or decision in the memory system for future recall.

Caches research findings to avoid redundant web searches. Stores best practices by topic with sources and dates. Use before researching to check existing knowledge.

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.

Captures and retrieves PR-review findings in memory palaces. Use after PR review to store architectural decisions, patterns, and standards for future reference.

Capture and retrieve PR review knowledge in project memory palaces

会話やログからメモリ候補を抽出し、結果を workspace に保存する

Repo Prompt CLI - proxy MCP client for AI agents to access Repo Prompt's context engineering tools via bash. Build prompts, search code, manage file selections, chat with AI, and export context without MCP configuration.

Manage RVF (Ruflo Vector Format) files for portable agent memory and cross-platform transfer

Working memory for thinking out loud.

Working memory for thinking out loud.

Search past Claude Code conversations. Use when user says "search conversations", "find that chat", "what did we discuss", "where did we talk about", "look up past session", "find conversation about X", "search history", "what did I ask about", "remember when we", "that discussion about". Also triggers on past-tense questions referencing prior work or possessives without context.