llm-wiki
193Skill Claude CodeCodex
A connector for querying the user’s LLM Wiki, a desktop knowledge-base application running on the local computer.
not rated 135
+4 3mo ago B 218 tokens
synapse-usage
194Skill Claude CodeCodex
Use the th0th Synapse cognitive modulation layer to get focused, low-noise retrieval during multi-step coding tasks. Open a session, prime the buffer with known-relevant memories, pass synapseSessionId on every search, and prefetch when opening a file. Triggers on tasks involving repeated searches in the same context…
not rated 135 2mo ago A 92 tokens
original MIT
memory-engine
195HelloRuru/claude-memory-engine
Skill Claude Code
Memory management system for Claude Code — Student Loop, Smart Context, Auto Learn, Session Handoff, Correction Cycle. Triggered by memory commands (/save, /reflect, /handoff, /check) or memory-related questions. Not for general programming tasks.
not rated 133 3mo ago B 55 tokens
original MIT
memory
196Skill Claude CodeCodex
Always-on prompt memory for stable facts and preferences.
not rated 133
+1 3mo ago A 12 tokens
original MIT
GODGOD126/self-improving-for-codex
Skill Codex
Build or maintain a Codex-native self-improving memory loop using global AGENTS.md, a persistent memories directory, and optional nightly refinement automation. Use when Codex needs to adapt OpenClaw-style self-improvement ideas to Codex, set up long-term user/profile memory, create PROFILE.md / ACTIVE.md /…
not rated 130
+1 26d ago A 117 tokens
original MIT
qiushi-dev/openclaw-memory-knowledge-management
Skill Claude CodeCodex
A system for reorganizing and continuously adding memory and knowledge data in OpenClaw, an AI-agent platform.
not rated 130 17d ago A 88 tokens
alive-save
199Skill Claude CodeCodex
Checkpoint -- route stash items, write log entry, update bundle, trigger projection, reset stash.
not rated 127 12d ago A 21 tokens
original MIT
learn
200Skill Codex
A skill for recording verified observations as evidence and deciding whether they should become lasting project context, stable rules, or an ADR, a document that records an architectural decision.
not rated 126
changed 2d ago A 63 tokens
original MIT
remind
201Skill Claude CodeCodex
Mechanism-level read path for a remindb MCP server — MemoryTree (orient), MemorySearch/MemoryFetch/MemoryFetchBatch (look up), MemoryDelta/MemoryDiff (resync), MemoryRelated (traverse), MemoryStats/MemoryHistory (inspect), passive remindb:// resources. Use when already driving remindb read tools and need…
not rated 125 1mo ago A 113 tokens
original MIT
my-wiki
202Skill Codex
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…
not rated 123 7d ago A 78 tokens
original MIT
docmancer
203Skill Claude CodeCodex
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.
not rated 123 24d ago A 62 tokens
original MIT
ingest_raw
204Skill Claude CodeCodex
Process the next ingest unit in inspool-wiki-en/raw/unprocessed, update the wiki, and mark the raw files as pendingreview.
not rated 121 4mo ago A 32 tokens
original MIT
trajex
205Skill Claude Code
A tool for searching past Claude Code, Codex, and Pi work sessions. It finds earlier conversations and solutions from session history.
not rated 118
+1
changed 3d ago A 159 tokens
AGPL-3.0
mycelium
206Skill Claude CodeCodex
Multi-agent coordination layer with persistent memory. Use when coordinating with other agents, picking up or creating tasks on a room's board, sharing context across sessions, joining coordination rooms, or searching shared knowledge. Triggers on "coordinate", "negotiate", "share memory", "mycelium", "the board"…
not rated 117 2d ago B 80 tokens
harness-24h
207Skill Claude CodeCodex
A production-grade framework for long-running, autonomous agents based on Harness Engineering principles. Features three-layer self-healing memory, circuit breaker protection, KAIROS dream-mode consolidation, and multi-agent coordination. When a user describes a task idea, Agent automatically initializes the…
not rated 116 5mo ago A 76 tokens
ogham-research
208Skill Claude CodeCodex
Structured memory capture for Ogham shared memory. Use when the user wants to store findings, remember something, save what was learned, or capture a decision. Triggers on "remember this", "store this", "save this finding", "save what we learned", "capture this decision", "log this", or any request to persist…
not rated 115
+1 12d ago A 113 tokens
original MIT
Forlives/21-day-self-interview
Skill Claude CodeCodex
A 21-night guided self-reflection routine in which an agent asks three questions each night, remembers the answers, and reflects on them at key points.
not rated 112
+19 3mo ago A 68 tokens
original MIT
memory
210lokikill123/codex-token-skills
Skill Codex
Persistent global memory across conversations. Read memory file at start of every conversation, write important context during conversation so it survives context compression. Use ALWAYS. Triggered automatically.
not rated 111
+1 2mo ago A 35 tokens
original MIT
karpathy-wiki
211Skill Claude CodeCodex
Use when building or maintaining a personal knowledge base with LLM assistance. Triggers on ingesting sources, compiling wiki articles, querying knowledge, running health checks, deep research, or initializing a new wiki vault. Based on Karpathy's LLM Wiki pattern with Obsidian integration.
not rated 109 4mo ago A 62 tokens
original MIT
braindb
212Skill Claude Code
Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.
not rated 109
+2 4d ago A 36 tokens
original Apache-2.0
session-pack
213Skill Claude Code
A session-ending skill that automatically organises memory and handoff notes. A handoff is a summary for continuing work in a later session.
not rated 108 2mo ago A 18 tokens
setup-open-index
214Skill Claude CodeCodex
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
not rated 106
+1 26d ago A 48 tokens
original MIT
Skill Codex
Maintain durable, evidence-based repository context whenever an agent initializes a repository, changes behavior, checkpoints or resumes work, switches AI tools or windows, collaborates through Git, prepares a pull request, or completes a coding task. Use the deterministic runtime to route bounded context, isolate…
not rated 105 10d ago A 103 tokens
original MIT
jiaojie
216Skill Claude CodeCodex
A human-first method for handing ongoing work from one chat, AI model, device, or language to another. It creates or reads a small handoff document, or a package with files when the receiver needs them.
not rated 105
+1 17d ago A 186 tokens
original MIT
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: