compound-refresh
961Skill Claude Code
Refresh stale or drifting learnings and pattern docs in docs/solutions/ against the current codebase.
not rated 2 3mo ago A 22 tokens
original MIT
Nyrest/capacities-mcp-enhanced
Skill Codex
Operate Capacities safely and precisely through the Capacities MCP server. Use whenever a user asks to inspect, search, read, create, update, append to, delete, or upload Capacities objects, pages, tasks, tags, web links, media files, blocks, properties, collections, or Daily Notes; when choosing structured blocks…
not rated 2 25d ago A 97 tokens
original MIT
hicortex-memory
963Skill Claude Code
Long-term memory tools for searching past knowledge, decisions, and lessons. Use when the user references past work, asks about previous decisions, or when you need context from earlier sessions.
not rated 2 2d ago A 40 tokens
agentmemory
964Skill Claude CodeCodex
Persistent project memory via AgentMemory MCP. Use when the user asks you to remember something, recall a project convention, search past context, or forget a memory. Always search before answering project-specific questions.
not rated 2 3mo ago A 43 tokens
original MIT
Skill Claude CodeCodex
Use when connected to a Cortex memory MCP server (tools named memorize, recall, recallabout, recalltimeline, listmemories, forget) — at session start, before asking the user for facts they may have shared before, after learning durable facts/preferences/decisions, when the user says "remember/recall/forget", or when…
not rated 2 9d ago A 82 tokens
original Apache-2.0
midmem-dev
966Skill Claude CodeCodex needs its repo
Develop/iterate on the MidMem middleware core (this repo's packages/core — the shared "LLM Wiki" knowledge layer). Use when adding or changing MidMem capability — retrieval lanes, tiers/lifecycle, work-memory events, concept routing, claims, grounding, the MCP/CLI/hook surfaces, or its tests. Encodes the…
not rated 2
changed 2d ago A 136 tokens
original Apache-2.0
17557295964-ops/project-brain-bridge
Skill Claude CodeCodex
Use when creating, deploying, diagnosing, or operating a reusable ChatGPT-as-project-brain bridge for any local Codex project: initialize .ai-bridge state, expose read-only project evidence, expose a narrow stage-plan write connector, avoid stale/freeform connector schemas, and run the ChatGPT plan -> Codex execution…
not rated 2 2mo ago A 85 tokens
original MIT
phenomenoner/Chatgpt-Codex-App-Plus
Skill Claude CodeCodex
Maintain an optional session task map and explicit retrievable references in Context Canvas Codex. Use when navigation or long-context offload would materially help with goals, decisions, progress, dependencies, blockers, next steps, exploration summaries, large textual tool results, or selective historical…
not rated 2 18d ago A 88 tokens
original MIT
memory-bank
969Skill Claude CodeCodex
Token-efficient persistent memory system for Claude Code that saves 67% tokens on session warm-up (verified with tiktoken). Layered architecture with progressive loading, compact encoding, branch-aware context, smart compression, session diffing, conflict detection, session continuation protocol, and recovery mode.…
not rated 2 2d ago A 199 tokens
original Apache-2.0
archive
970Skill Claude CodeCodex
Persistent knowledge wiki and memory system that compounds across conversations using an Obsidian-compatible vault. Consult at the START of any non-trivial task to recall project context, preferences, and past discoveries. Ingest sources and build wiki pages when accumulating knowledge on a topic. Save at the END when…
not rated 2 5mo ago A 178 tokens
session-logs
971Skill Claude CodeCodex
Search and analyze your own session logs (older/parent conversations) using jq.
not rated 2 2mo ago A 20 tokens
copy · 81% MIT
mneno-memory
972Skill Claude CodeCodex
Use when working in a repository that uses Mneno for local project memory through the CLI, including task-start context recovery, narrow memory search, and storing durable project facts before stopping work.
not rated 2 2mo ago A 43 tokens
original Apache-2.0
klayer-skill
973Skill Claude CodeCodex
Automatically use klayer for grounding, codebase indexing, session memory, and episode logging during software development tasks unless the user explicitly opts out.
not rated 2 28d ago A 33 tokens
neilshermes-project/hermes-memory-hybrid
Skill Claude CodeCodex
One-command hybrid memory upgrade for Hermes (FTS5 + sqlite-vec embeddings + relational pre-filtering). Snapshot-safe and fully reproducible.
not rated 2 3mo ago C 35 tokens
original MIT
Yingqi-Han/learning-retrospective-skill
Skill Codex
A skill for saving verified lessons from difficult coding tasks so future agents can use them. It covers both learning after a task succeeds and recalling an existing lesson when the same problem appears again.
not rated 2
changed 6d ago A 64 tokens
original MIT
obsidian-memory
976Skill Claude Code
Explicit-only Obsidian memory workflow. Use when the user explicitly asks to work with an Obsidian vault, LLM wiki, agent memory, RAW/source ingest, provenance, QUERY, LINT, or release safety for a markdown knowledge system. Do not auto-route ordinary coding sessions into external vault workflows.
not rated 2 3mo ago A 66 tokens
original MIT
Skill Claude CodeCodex
MUST be used when editing code that carries a hard-won lesson, a deliberate decision, or a correctness invariant. Enforces inline @agent: notes recorded next to the code, so the next agent reads the reason for free and does not repeat the mistake. Load whenever writing or modifying non-trivial logic. Paired with…
not rated 2 1mo ago A 82 tokens
original MIT
manifold
978Skill Codex
Work with any network-reachable Manifold knowledge and memory service through its REST API. Use proactively before non-trivial work to retrieve prior decisions, procedures, incidents, and evidence; use after verified material work to preserve durable cross-agent knowledge, project knowledge, or task-scoped notes…
not rated 2 2d ago A 100 tokens
phenomenoner/hermes-agent-harness-plus
Skill Claude CodeCodex
Use for compaction, coordination, or two complexity cues.
not rated 2 2d ago A 17 tokens
original MIT
memgentic
980Skill Claude Code
Universal AI memory — recall past decisions, learnings, and context from all your AI conversations (Claude Code, Gemini CLI, ChatGPT, Aider, etc.).
not rated 2 1mo ago A 37 tokens
original Apache-2.0
agent-memory
981Skill Claude CodeCodex
Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the…
not rated 2 5mo ago A 78 tokens
original MIT
claw-init
982Skill Claude CodeCodex
An interactive setup skill that turns an empty Claude Code folder into an OpenClaw-style personal assistant. It asks about the assistant's identity, tone, communication channels, permissions, and memory, then creates the related instruction and memory files.
not rated 2 2mo ago B 233 tokens
original MIT
llm-wiki
983Skill Claude CodeCodex
Generates a complete AI-native service wiki from repository analysis for human onboarding and AI-agent long-term memory. Use when the user asks to generate a wiki, service documentation, repository documentation, ai-context.md, repository-map.md, onboarding docs, or LLM-native documentation for a codebase. Trigger on…
not rated 2 15d ago A 104 tokens
capture
984Skill Claude Code
Review session work and propose knowledge captures for human review. Scans git commits, changed files, and patterns used across repos to generate structured knowledge items. Includes review workflow to approve/reject/edit pending captures before persisting to the knowledge base.
not rated 2 2mo ago A 50 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: