Claude Skills by majiayu000

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.

Cold-start resume — load all memory and project state to continue any interrupted project

Automatic session tracking and memory system for Claude Code. Activates when working in git repositories to track file changes, commits, and session context. Creates .cortex_log.md (session history), .cortex_status.json (current state), and .cortex_handoff.md (next steps) for session continuity across conversations. Use when needing persistent memory, session handoffs, or work history tracking.

This skill should be used when the user asks to "check my preferences", "show memory", "run /buff:counterfeit", "what does buff remember", "update my preferences", "reset memory", "show session history", "what did I work on", "show graph", "show corrections", or when buff needs to read or write persistent user/project memory. Intelligence engine with 3-tier memory — preferences, patterns, corrections, and project graph. Auto-activates at session start and end.

Generate comprehensive CONTEXT.md files for agent handoff. Ensures another

Create unified artifact document for checkpoint, handoff, or finalize

Create handoff documentation for work-in-progress sessions. Use when handing off work to another agent to supplement history compaction and and progress summarization.

Create a structured handoff document to transfer context to another agent session. Captures task status, key learnings, critical files, and prioritized next steps.

Generate context documents for session continuity

Create a structured handoff document to transfer context to another agent session. Captures task status, key learnings, critical files, and prioritized next steps.

Save session state for later resumption. Use when: - User says "done for today", "ending session", "save state" - Context is getting full (80%+) - User is taking a break - Before context compaction - User mentions "handoff", "pause work", "wrapping up"

Generate a handoff document after implementation work is complete — summarizes changes, risks, and review focus areas for the review pipeline. Use when done coding and ready to hand off for review.

Create a handoff document to preserve context before clearing. Use when user says 'create handoff', context is low, or before '/clear'.

Write a handoff file at .turbo/handoff/<YYYY-MM-DD>-<slug>.md capturing current session state — task, status, open decisions, in-flight changes, next step — so a fresh session can continue without re-deriving context. Use when the user asks to \"create a handoff\", \"create handoff\", \"save handoff\", \"handoff before compact\", \"save session state\", \"handoff for next session\", or \"capture session state\".

Write a handoff file at .turbo/handoff/<YYYY-MM-DD>-<slug>.md capturing current session state — task, status, open decisions, in-flight changes, next step — so a fresh session can continue without re-deriving context. Use when the user asks to \"create a handoff\", \"create handoff\", \"save handoff\", \"handoff before compact\", \"save session state\", \"handoff for next session\", or \"capture session state\".

Create handoff document for transferring work to another session

Create handoff document for transferring work to another session

Create complete user-context instruction files using a structured discovery workflow and repository format rules.

<!-- Copyright (c) 2026 defconxt. All rights reserved. -->

Read, search and analyze Claude Code session transcripts (the .jsonl under ~/.claude/projects). Use this INSTEAD of grep/ripgrep/cat/jq/python: the format has documented traps that return plausible wrong answers, no error (a user-role filter overcounts human turns 3x; a sixth of human turns hide inside tool_result payloads; an AUQ answer can read (notes only) with the words in annotations). Reach for it when you would hand-scan a session jsonl or shadow session facts in your own state file - ...

Use when starting a session on a project, returning after time away, or before making significant changes. Essential for building comprehensive understanding of project state through total recall and deep exploration.

Use when starting a session on a project, returning after time away, or before making significant changes. Essential for building comprehensive understanding of project state through total recall and oracle-driven exploration.

Load PRD, FRD, Tech Spec, or RFC into context

Mine agent work into durable knowledge.

Mine transcripts, .agents, bd, and git for skill diffs, bd updates, or

Full curator pipeline for autonomous learning from quality repositories. Executes: discovery → scoring → ranking → ingest → learn → inject. Use for: populating procedural memory with domain patterns, first-time domain learning, comprehensive knowledge building. Triggers: /curator full, 'learn patterns from repos', 'build knowledge base'.

Accesses the claude-mem MCP server from Cursor to search session history and record observations. Triggers: memory search, claude-mem, past decisions, record this. Do NOT load for: normal coding, temporary notes, or implementation work.

Accesses the claude-mem MCP server from Cursor to search session history and record observations. Triggers: memory search, claude-mem, past decisions, record this. Do NOT load for: normal coding, temporary notes, or implementation work.

(ePost) Use when an agent needs to persist or retrieve project-level data across sessions via .epost-data/

Give agents persistent structural memory of a codebase — navigate dependencies, track public APIs, and understand why connections exist without re-reading the whole repo.

Reconstruct context and present next steps when a user returns to a conversation after a break. Synthesizes status into scannable summaries with actionable options.

DeepAgent-style memory folding for VCO sessions: compress long context into structured working/tool memory without using episodic-memory.

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

Log an observation (measurement, state, or event). Use when recording factual observations during work execution. Triggers on "log observation", "record observation", "note finding", "capture state".

Log an observation (measurement, state, or event). Use when recording factual observations during work execution. Triggers on "log observation", "record observation", "note finding", "capture state".

Save session context for continuity across sessions. Creates a per-user session memo capturing active focus, recent work, and open questions. Triggers on "save session", "end session", "session memo", "remember context".

Save session context for continuity across sessions. Creates a per-user session memo capturing active focus, recent work, and open questions. Triggers on "save session", "end session", "session memo", "remember context".

Distill PDF, URL, or text into Q&A pairs stored in memory. Use --context for domain-focused extraction.

Advanced long-term memory with semantic search and recall.

Ultimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again. For Clawdbot, Moltbot, Claude, GPT agents.

Recall past work from Claude Code history before starting new tasks. Use when: (1) starting work on a codebase, (2) asked about previous decisions, (3) need context about why code exists.

Summarize coding sessions into structured learnings using LLM extraction. Use when: (1) distilling lessons from recent work, (2) creating reusable knowledge, (3) building a project knowledge base, (4) onboarding others to a codebase.

Augmented cognition layer that makes users smarter by connecting conversations to their persistent knowledge tree. Use proactively when topics arise that might have prior knowledge, and when users ask to remember, recall, search, or organize. Triggers on technical discussions, decision-making, project work, "remember this", "recall", "what do I know about", or any knowledge request.

Log execution steps during episode execution for detailed tracking and learning. Use when recording tool usage, decision points, errors, or milestones during task execution.

Log execution steps during episode execution for detailed tracking and learning. Use when recording tool usage, decision points, errors, or milestones during task execution.

Start a new learning episode in the self-learning memory system with proper context. Use this skill when beginning a new task that should be tracked for learning from execution patterns.

Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Tracks UNRESOLVED sessions for reflection with structured failure episodes (trigger/diagnosis/action/outcome), K~4 similar failure retrieval, user behavioral profiling, and federated taxonomy classification.

Episodic Memory Archiver. Stores full conversation transcripts with embeddings and analysis into ArangoDB. Use this to save the "User Story" or "Chain of Thought".

Convert verbose memories to SSL v0.2 format - I am encoder AND decoder

Remembers errors you have hit and how you fixed them. When the same or similar error appears again, it suggests the fix before you have to re-discover it. Like habit-formation but specifically for error/fix pairs. State persists between sessions.