Memory and context skills

memodb-io/skill-memory

Skill Claude CodeCodex

Use skill-memory to download, view and edit agent skills in memory. TRIGGER by 'skill', 'memory', 'learn'.

legoambarish/portable-handoff

Skill Claude CodeCodex

Create, validate, list, and load local Portable Handoff capsules for context transfer, continuing work in a new chat, compacting current work, or loading prior work. Use whenever the user asks for a handoff, context transfer, continuation briefing, or portable work-state summary.

AllenMaxi/ContextGraph

Skill Claude CodeCodex

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress or "compress memory…

microhustlestack/cerebro-skill

Skill Claude CodeCodex

Strategic intelligence engine for markdown vaults. Use this skill whenever the user asks to analyze a vault, scan notes for connections, surface relationships between entities, find hidden links, map a knowledge base, audit what a set of notes is missing, or generate an intelligence report from a folder of markdown…

JohnnyFiv3r/Core-Memory

Skill Claude CodeCodex

Use when working with Core Memory from OpenClaw, including finalized-turn writes, memory retrieval, bridge behavior, semantic bead fields, promotion, claims, associations, or integration debugging.

sebbsssss/clude

Skill Claude CodeCodex

MCP server for Clude's cognitive memory system — store, recall, search, and dream. Supports hosted (zero-setup), self-hosted (Supabase + pgvector), and local (offline) modes.

Malaiac/claude

Skill Claude CodeCodex

Maintain working context via current-context.md - read before and update after every response with timestamp YYYYMMDD-HHMMSS.

jzOcb/ai-agent-memory

Skill Claude Code

Guidelines for managing AI agent memory. Use when deciding what to write to MEMORY.md, how to organize memory files, or when reviewing memory health. Includes Q1/Q2/Q3 decision framework and common mistakes to avoid.

szw321127/repowise

Skill Claude CodeCodex

Build and maintain a project-serving knowledge base inside the current project's .project-knowledge/ directory. Use when Codex should initialize a project knowledge base, inspect current project knowledge status, rebuild the project knowledge graph, or crystallize stable knowledge from the current task into…

AnisurRahmann/llm-wiki-kit

Skill Claude CodeCodex

Maintain a personal LLM-generated wiki/knowledge base in Obsidian. Use this skill whenever the user wants to: ingest a new source (AI tool, GitHub repo, article, social post, project doc) into their wiki, query or search their wiki, lint/health-check the wiki, create or update wiki pages, manage the wiki index or log…

microsoft/ShadowFrog

Skill Claude CodeCodex ✓ vendor

Clean and consolidate the shadow knowledge base. Scans all shadow files for duplicate discoveries (same claim, different wording), near-duplicates (one extends another), and conflicting entries (contradicting claims). Merges duplicates, resolves conflicts by investigating the code, and asks the user only when…

cclank/lanshu-wiki-skill

Skill Claude CodeCodex

A persistent Markdown knowledge base maintained by an AI agent. Markdown is a plain-text format for structured notes; the knowledge base can hold personal research or documentation about an open-source project's design.

sleeplesshan/dual-brain

Skill Claude Code

Two complementary reusable sub-agents collaborate to remember, grill, verify, document, and maintain weighted project memory. A Right Brain (context / pattern / grill) interrogates assumptions against Hot/Warm memory; a Left Brain (logic / verification / code) cross-checks memory, code, and docs; the orchestrator…

julymetodiev/post-cortex

Skill Claude CodeCodex

Multi-agent orchestration system for Post-Cortex MCP memory infrastructure. Use when working with persistent memory, knowledge graphs, semantic search, session management, or context building.

pbeens/obsidian-agents.md

Skill Claude CodeCodex

After vault-ingest or history-ingest, consolidate detected people, projects, and open tasks into alias-friendly vault pages in the dedicated people/ and projects/ folders and roll up tasks into overview views.

H1an1/openclaw-evolution

Skill Claude CodeCodex

Interactive guide for new OpenClaw users to set up and grow their agent. Two paths - Tool Path (automation, efficiency, getting things done) or Awakening Path (memory, personality, relationship, growth). Use when a user is new to OpenClaw, asks how to get started, wants to set up their agent, or asks about agent…

hyungchulc/memory-forest

Skill Codex

Build, validate, index, and query a private local Memory Forest with provenance-aware layers, pointer-first search, and validated root-first retrieval. Use when creating a new forest, checking an existing forest's structure, building its local SQLite index, or retrieving bounded memory trails without exposing full…

melodykoh/learning-loop-skill

Skill Claude Code needs its repo

Two-mode learning system — raw signal scanning before compaction, quality-gated consolidation at session end. Invoke with /learning-loop.

shibing624/skills

Skill Claude CodeCodex

Learn from experience: self-reflection + self-criticism + self-learning + self-organizing memory + cross-session sync. Agent evaluates its own work, catches mistakes, and improves permanently. Compiles confirmed learnings to global config for automatic cross-session persistence. Use when (1) a command, tool, API, or…

redhat-ai-americas/memory-hub

Skill Claude CodeCodex

Resume and hand off work across agent sessions using the work-item pool.

PUSHINGSQUARES/ARI-OS

Skill Claude CodeCodex

Use when something worth keeping is decided or learned — a decision, a fact, an open thread — so the next session has it.

ResearAI/MeOS

Skill Claude CodeCodex

Read the owner's local history, assets, and person-graph evidence; extract stable workflows, preferences, and personality-level claims; keep them updated; and align future tasks to the owner's style. Use when explicitly asked to initialize, refresh, or apply MeOS.

sordi-ai/skill-everything

Skill Claude CodeCodex

Apply when learning from a mistake. Central memory of past errors and derived rules; consult before logging a new error to avoid duplicates.

D4kooo/Openclaw-Token-memory-optimizer

Skill Claude CodeCodex

Optimization suite for OpenClaw agents to prevent token leaks and context bloat. Use when an agent needs to implement background task isolation (Cron) or a Reset & Summarize workflow (RAG).