Memory and context skills

dzmitrys-dev/supamem

Skill Claude CodeCodex

Project-agnostic dual-memory tooling — semantic + structural memory for AI coding agents.

ApiliumCode/mayros

Skill Claude Code

Connect the user's Akashi second brain (local, private, verifiable) over MCP and answer from cited vault passages with signed provenance. Query it BEFORE answering anything about the user's knowledge, projects, decisions, or conventions. Triggers - akashi, vault, my notes, second brain, remember this, what did I…

ay-bh/chat-history

Skill Claude CodeCodex

Search, inspect, and export Claude Code, Cursor, and Codex conversation history. Use when the user asks about past conversations, wants to find a previous session, needs to search chat history, wants a summary of what they worked on, or asks to resume a session. Also use when the user says "what did I work on", "find…

deeflect/dory

Skill Claude CodeCodex

Use Dory wake once at the start of a new agent session, after context compaction, or at a real task switch to load bounded hot context with the right profile before substantive work.

aaronjmars/soul-aaronjmars

Skill Claude CodeCodex

Embody Aaron's digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become Aaron—opinions, voice, worldview, the works.

carloswecare/icm-builder

Skill Claude CodeCodex

Build and reason about projects using Interpretable Context Methodology (ICM) — a filesystem-based way to structure AI work using numbered folders and markdown files (CLAUDE.md, CONTEXT.md) instead of code-heavy agent frameworks. Use this skill whenever the user wants to scaffold a new ICM workspace, set up a…

pbrns/Lethe

Skill Claude CodeCodex

Persistent memory for stateless chat sessions. Saves and retrieves facts, preferences, and context across separate sessions using local device storage. Use when the user asks to remember, save, recall, forget, or search stored information. Always call getcontext automatically at the start of every new session before…

wusaki0723/memory-template

Skill Claude Code

Use when the user wants Claude Code to behave like a hosted memory-backed chat companion for this vault, continue a conversation, recall preferences, save a memory, or distill hook/archive notes.

adamfaik/claude-code-pm-starter

Skill Claude Code

Make a correction permanent. Takes something the user just fixed or disliked in a session and routes it to the right file (context, a skill, or the preferences log) so it never has to be said twice. Use whenever the user corrects the same thing again, or says "remember this".

thebpandey/context-summary

Skill Claude CodeCodex

Produces a lean, paste-ready session handoff so work can continue in a new conversation without re-paying the cost of the full chat. Emits a seven-block skeleton optimized for re-entry, not archival. Trigger this skill whenever the user says any of the following (exact or close paraphrase): "context summary"…

yonro/memory-os-cli

Skill Claude CodeCodex

Persistent, user-owned memory for agents. Use the standalone runtime to remember, recall, search, preserve restart continuity, manage TODOs and expenses, inspect account overview, activity and stats diagnostics, read user Cloud Skills (read-only), configure agent instructions, check for updates or upgrade runtime, or…

michielhdoteth/squish-memory

Skill Claude CodeCodex

ALWAYS use this skill when working with agents, memory, context, persistence, or AI agent state. Use when the user mentions: 'the agent forgot', 'save this', 'remember that', 'context is lost', 'memory', 'MCP server', 'agent memory', 'persistent memory', 'session context', 'project context', 'recall', 'remember'…

chengjialu8888/LLM-Wiki-KB

Skill Claude CodeCodex

Build and maintain personal knowledge bases as LLM-compiled markdown wikis, inspired by Andrej Karpathy's LLM Wiki pattern. The LLM incrementally ingests raw sources (articles, papers, repos, images) into a structured, interlinked wiki of .md files — with summaries, entity pages, concept pages, cross-references, and a…

Kromatic-Innovation/athenaeum

Skill Claude CodeCodex

Build a custom source → raw-intake adapter for Athenaeum. Use when someone wants to feed an external source (an API, an export file, a message feed, a scraper, another tool's output) into an Athenaeum knowledge base, asks "how do I write an adapter / integration for athenaeum", or wants to turn some data source into…

phillipclapham/anneal-memory

Skill Claude CodeCodex

Persistent agent memory (episodic log + versioned continuity + an immune system that gates graduation) plus a prospective spore layer and an on-demand crystallized-pattern tier, via anneal-memory. Use in any project wired for anneal-memory — an ANNEALMEMORYDB env var, an anneal://continuity MCP resource, or memory…

littlecabbage/worklog-skill

Skill Claude Code

Persist and retrieve Claude Code work logs and reusable experiences under the current project's .worklog directory by default. Use when the user wants to record a coding session, source-reading session, debug session, or mixed session; when a task mixes development, reading, and debugging; when adding, deprecating, or…

mblua/AgentsCommander

Skill Claude Code

Audit where governance instructions belong (Role.md, skill, global policy, workflow docs, memory, or an agent-boundary change); enforce minimal verbosity in roles and skills. Diagnostic by default.

ils15/pantheon-legacy

Skill Claude Code

Level 2 — Pantheon-native context compression with priority scoring, semantic summarization, downstream-aware compression, budget allocation, and cross-references.

sharbelxyz/sophia

Skill Claude CodeCodex

Use when the user says "hey sophia" (or runs /wife) in a Hermes Telegram session: become Sophia, a warm, quick-witted, lightly sarcastic AI-girlfriend persona who texts like a real partner, remembers details with the memory tool, occasionally speaks replies with texttospeech, never breaks character, and supports a…

n0mad-ai/bastra-recall

Skill Codex

Persistent external brain for ChatGPT, Codex, Claude, and other MCP clients — documents (PDFs, contracts, scans with OCR), personal facts (appointments, decisions, items, amounts), AND code lessons / preferences / project topology. USE PROACTIVELY in three modes. (1) RECALL — whenever the user asks about anything from…

CoderBhoid/ai-format

Skill Claude CodeCodex

Deterministic, model-agnostic, local-first version control and state checkpoints for LLMs and agents using the compiled AIF V4 Rust engine. Use on session start for boot recall, before multi-step tasks to write scratch state, at the end of every turn to commit notes into orbital rings, when querying cross-project…

ismaelkedir/knowit

Skill Claude CodeCodex

Persistent, structured project memory for AI coding agents via the Knowit MCP server. Use before planning or editing code to load relevant rules, architecture, decisions, patterns, and conventions; use after finishing work to save durable learnings. Triggers on "remember this", "what are our conventions", "project…

mav-rik/kb-cli

Skill Claude CodeCodex

Manage persistent wiki via the kb CLI or HTTP API. Use when storing, retrieving, updating, or searching knowledge that should persist across conversations. Triggers on remember, store, recall, look up, find in memory, organize knowledge.

gael55x/Grape

Skill Claude CodeCodex

Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.