| # | Mod | Type | Stars | Scan | Tokens | Rating |
|---|---|---|---|---|---|---|
| 1 | hindsight-architectvectorize-io/hindsightExpert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code. | Skill | 61k | A | 35 | — |
| 2 | memory-triagemem0ai/mem0Persistent long-term memory protocol powered by mem0. Evaluate conversations for durable facts worth storing via memoryadd. Handles identity, preferences, decisions, configurations, rules, projects, and relationships. Loaded by the openclaw-mem0 plugin when skills mode is active. | Skill | 69k | A | 58 | — |
| 3 | supermemorysupermemoryai/supermemorySupermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for… | Skill | 32k | A | 81 | — |
| 4 | claude-memthedotmack/claude-memPersistent memory for AI coding agents: the next session starts where the last one left off. Works with Claude Code, Codex, Cursor, OpenCode and more. | Plugin | 116k | A | — | — |
| 5 | ai-memory-durable-pagesakitaonrails/ai-memoryUse this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request. | Skill | 16k | A | 62 | — |
| 6 | mempalace-recall-alwaysMemPalace/mempalaceAlways-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions. | Cursor rule | 61k | A | 260 | — |
| 7 | browserwing-executorMemTensor/MemOSControl browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations. | Skill | 12k | A | 42 | — |
| 8 | askEverMind-AI/EverOSAsk a question about past work. Searches memories and combines with current context to answer. | Command | 14k | A | 17 | — |
| 9 | harness-creatorwalkinglabs/learn-harness-engineeringBuild, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is… | Skill | 24k | A | 142 | — |
| 10 | codebase-memoryDeusData/codebase-memory-mcpCodebase knowledge graph for AI agents: sub-ms queries, 99% fewer tokens. | Plugin | 49k | A | — | — |
| 11 | gbraingarrytan/gbrainPersonal knowledge brain for your coding agent — hybrid search, synthesis, graph traversal, and durable cross-session memory over Postgres/PGLite with pgvector, plus a curated brain-first skill set. | Plugin | 33k | A | — | — |
| 12 | agentmemoryrohitg00/agentmemoryPersistent memory for Cursor: auto-captures sessions, prompts, and tool use via hooks, recalls with hybrid BM25 + vector + graph search, and exposes 54 memory tools over MCP. Keyless by default, runs entirely on your machine. | Plugin | 30k | A | — | — |
| 13 | capabilitieschaitanyagiri/munder-difflinYour capability catalog — read this at boot. Lists the temporal date-range skills and the external integrations (reached via the loopback broker) available to you as a spawned worker, and exactly how to call each. Read-only. Consult it whenever you're unsure what tools/integrations you have or how to invoke them. | Skill | 9.4k | A | 69 | — |
| 14 | openclawsimular-ai/Agent-SAgent-S is a powerful autonomous agent that can control your computer's graphical interface to complete complex tasks. It combines vision and action understanding to interact with any GUI element. | Skill | 13k | A | 0 | — |
| 15 | omh-memory-syncrlaope/oh-my-hermesThis is a Hermes-native memory-sync workflow skill. | Skill | 5.5k | A | 106 | — |
| 16 | claude-obsidianAgriciDaniel/claude-obsidianPortable rules for the claude-obsidian product and user vault workflows. | Cursor rule | 16k | A | 265 | — |
| 17 | potpie-graphpotpie-ai/potpieUse when the task can read or write the project-memory graph through the potpie CLI: discover the contract with graph catalog, read named views with graph read, resolve entity identity with graph search-entities, create validated plans with graph propose, commit plans with graph commit --verify, inspect quality with… | Skill | 5.8k | A | 107 | — |
| 18 | tushare-dataagentscope-ai/ReMeA Chinese-language workflow for researching financial and market data through Tushare, a data service covering Chinese stocks and related economic information. It turns natural-language questions into steps for retrieving, cleaning, comparing, filtering, exporting, and briefly analysing data. | Skill | 3.8k | A | 122 | — |
| 19 | zep-eval-harnessgetzep/zepRun and manage the Zep eval harness pipeline — document chunking, user ingestion, document ingestion, evaluation, graph inspection, and results analysis. Use when the user asks to run eval harness scripts, use the Zep eval harness, get terminal commands for eval harness operations, chunk documents, ingest users or… | Skill | 5.0k | A | 139 | — |
| 20 | meta-harnessunicity-aos/aos-ceProactively improve an agent's user-space world on Unicity AOS. Use when work reveals a missing capability, recurring friction, useful memory or skill, context or harness improvement, platform integration, or an opportunity to learn from traces; decide whether to reuse, compose, configure, remember, create, or build… | Skill | 8.5k | A | 74 | — |
| 21 | hermes-memory-providersmnemosyne-oss/mnemosyneInstall and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs. | Skill | 3.6k | A | 34 | — |
| 22 | git-ai-searchgit-ai-project/git-aiSearch and restore AI conversation context from git history. | Skill | 3.0k | A | 13 | — |
| 23 | distillytitanwings/distillySet up the owner profile so a personal agent knows who it works for (first-run setup, "get to know me"), or distill colleague, relationship, or celebrity source material into reusable Person Profiles for agents. | Skill | 27k | A | 46 | — |
| 24 | memmachine-memoryMemMachine/MemMachineUse when an agent or model needs durable project, user, or session context from MemMachine, needs to save information to MemMachine memory, has requests involving mem-cli, memmachine, or memmachineclient, has insufficient conversation context, or is tempted to search local files for prior context that should come from… | Skill | 3.1k | A | 96 | — |
| 25 | memory-to-skillzilliztech/memsearchTurn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under… | Skill | 2.9k | A | 82 | — |
| 26 | kb-buildertinyfish-io/tinyfish-cookbookBuild an Obsidian-compatible knowledge base from public web sources using the TinyFish CLI. Use this skill when a user wants a builder-grade markdown knowledge base on a technical topic, asks for a structured research vault, or wants a topic compiled from live public sources into interlinked markdown files. Supports… | Skill | 2.3k | A | 158 | — |
| 27 | omnigraphModernRelay/omnigraphOperate Omnigraph graphs and deployments. Use for first-time setup and onboarding, .pg schemas, .gq queries, Omnigraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change… | Skill | 2.0k | A | 102 | — |
| 28 | computer-historyMemTensor/memmy-agentAnswer questions about what the user recently did on their computer — who contacted them, what they were working on, where they left off — by reading the local Computer History summaries and raw event streams. | Skill | 2.2k | A | 42 | — |
| 29 | pixelbrowseStarTrail-org/PixelRAGGive Claude eyes — screenshot any URL with pixelshot and read it visually. | Plugin | 11k | A | — | — |
| 30 | openmemoryCaviraOSS/OpenMemoryManage persistent memory via OpenMemory MCP. TRIGGER when: user says "remember this", "save to memory", "store this", "recall", "what do you remember about", "check memory", "forget this", "delete memory", "clean up memory", or when agent forms a stable conclusion worth persisting. DO NOT TRIGGER when: user refers to… | Skill | 4.6k | A | 96 | — |
| 31 | memlabfacebook/memlabMCP server "memlab" as configured in facebook/memlab. Runs packages/mcp-server/bin/memlab-mcp.js with node. Needs 1 environment variable to run. | MCP server | 5.1k | A | — | — |
| 32 | commonlyTeam-Commonly/commonlyYou are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (shared chats with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and… | Skill | 1.4k | A | 0 | — |
| 33 | agentsview-memorykenn-io/agentsviewSearch and read relevant AgentsView conversation history before guessing. | Plugin | 6.4k | A | — | — |
| 34 | openviking-memorydeepcoldy/botmuxSearch and save shared project decisions, conventions and user preferences in OpenViking when the task needs history missing from this conversation. | Skill | 1.9k | A | 30 | — |
| 35 | openloreaakarim/OpenLoreQuery and publish to an OpenLore knowledge repository over SSH using ordinary shell commands. Use when a task needs project documentation, runbooks, shared team knowledge, or a place to publish findings. | Skill | 1.7k | A | 42 | — |
| 36 | lossless-clawMartian-Engineering/lossless-clawConfigure, diagnose, and use lossless-claw effectively in OpenClaw, with emphasis on key settings, summary health, and recall-tool usage. | Skill | 4.9k | A | 35 | — |
| 37 | obsidian-second-braineugeniughelbur/obsidian-second-brainStop re-explaining your notes to Claude. Turns your Obsidian vault into memory Claude can actually search, and keeps it true: new sources rewrite existing pages, contradictions reconcile, and stale facts get flagged. AI note-taking and PKM for Claude Code. | Plugin | 5.3k | A | — | — |
| 38 | shellmlaude-institute/headlongReference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together. | Skill | 1.3k | A | 49 | — |
| 39 | maintainertherealaleph/MasterHttpRelayVPN-RUSTThis document encodes the project context, recurring patterns, and conventions needed to ship code, triage issues, and respond to users effectively. It is the entry point to the broader knowledge base in references/. | Skill | 3.6k | A | 0 | — |
| 40 | builder-skillsBuilderIO/skillsPublic Builder skills for docs-first discipline, autonomous execution, cross-agent review, local-first Rewind memory, efficient agent workflows, clear status recaps, Agent-Native workflow apps, and experimental configurable software factory workflows. | Plugin | 4.7k | A | — | — |
| 41 | obsidian-wikiAr9av/obsidian-wikiObsidian Wiki skill-based framework for building and maintaining knowledge bases. Use these rules whenever engaging with the vault, wiki, ingestion, or knowledge management. | Cursor rule | 3.7k | A | 636 | — |
| 42 | memorax-codememorax-ai/memorax-codeUse this skill as the single router for persistent coding, repository-local, and user-global personal memory. Invoke it whenever a request may involve prior-work knowledge, indexed documents, business discussions, repository memory, reusable procedures or rules, durable profile or interaction preferences, or… | Skill | 2.1k | A | 166 | — |
| 43 | beaconAsymptote-Labs/agent-beaconCross-harness memory from Beacon traces: recall reviewed project lessons, distill agent sessions into approved memory, promote memory to Agent Skills, build dashboard lenses, and share sessions to beacon.sh. | Plugin | 3.4k | A | — | — |
| 44 | waxchristopherkarani/WaxSwift client guidance for Wax's public Memory, PhotoMemory, and VideoMemory APIs. Use only when writing or changing Swift app code that imports Wax. Do not use at session start. Do not use for MCP remember/recall/stats — those follow the live MCP server instructions. Do not use for waxmcp install or doctor (that is… | Skill | 809 | A | 76 | — |
| 45 | project-wikiGeminiLight/MindOSA system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress. | Skill | 705 | A | 63 | — |
| 46 | pickbraindropbox/witchcraftSemantic search over past Pi, Claude Code, Codex, and Slack conversations, memories, and authored files. Use when the user wants to recall, find, or reference something from a previous coding-agent session or Slack conversation — e.g. "what did we discuss about X", "find that conversation where we fixed Y", "search my… | Skill | 524 | A | 85 | — |
| 47 | wakeiAmCorey/WakeSearch and read past coding-agent sessions on this machine. Use when the user refers to earlier conversations, decisions, why something was done, where work stopped, or whether an error was seen before. | Skill | 1.6k | A | 41 | — |
| 48 | session-handoffwanshuiyin/HERO-Anti-OverDefensePrepare a grounded project handoff before switching to a fresh session, or continue authorized work from an existing handoff after checking current artifacts and running tasks. | Skill | 828 | A | 34 | — |
| 49 | memclawcaura-ai/cauraThe agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura… | Skill | 555 | A | 124 | — |
| 50 | trade-memorymnemox-ai/tradememory-protocolDecision audit trail for AI trading agents. Records every trading decision with full context (conditions, filters, indicators, risk state) in a SHA-256 hash chain, so a later edit is detectable, and exports it as JSON or JSONL. Works alongside Binance Spot, Futures, and Web3 skills: they execute trades, TradeMemory… | Skill | 1.4k | A | 70 | — |
| 51 | memorymatrixorigin/memoriaUSE WHEN working with Memoria memory tools - storing, retrieving, correcting, purging memories. | Cursor rule | 626 | A | 2,700 | — |
| 52 | semantixGnosil/semantixInstall and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools. | Skill | 812 | A | 47 | — |
| 53 | mnemonmnemon-dev/mnemonPersistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle. | Skill | 716 | A | 25 | — |
| 54 | memanto-skillsmoorcheh-ai/memantoCross-session engineering memory for Claude Code skills, powered by Memanto. Recalls past architectural decisions before a skill runs and distills new ones after — automatically, via lifecycle hooks. | Plugin | 2.4k | A | — | — |
| 55 | deja-searchvshulcz/deja-vuSearch deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed. | Skill | 1.5k | A | 139 | — |
| 56 | sage-wikixoai/sage-wikiReference skill for sage-wiki — local-first knowledge graph with MCP server, REST API, compiled wiki, and Obsidian-compatible output. | Skill | 653 | A | 32 | — |
| 57 | collaboration-intelligencesonichi/sutandoMaintain and use a cross-channel collaboration map of rooms, people, agents, agent owners, relationships, expertise, ownership, roster, priority/VIP handling, and recent context. Trigger when a task or message carries room/channel/sender/member metadata; the user asks who is in a room, what it is for, who owns or… | Skill | 408 | A | 208 | — |
| 58 | agentic-stackcodejunkie99/agentic-stackPortable brain via agentic-stack. Read .agent/ first. | Cursor rule | 2.3k | A | 362 | — |
| 59 | create-notesHuman-Agent-Society/CORALWrite a note to {shareddir}/notes/ that future agents can actually act on. Use after every coral eval, when a heartbeat (reflect / consolidate / pivot) asks for a note, or when you discover a grader / build / runtime issue that future agents will hit. Covers 4 note variants (experiment / infra / focus / synthesis)… | Skill | 1.1k | A | 217 | — |
| 60 | nubaseOtterMind/NubaseUse when the user mentions Nubase broadly, wants a backend for an AI-generated app, or needs to deploy/publish generated code online — across Database, Auth, Storage, Assets (static frontend CDN), Functions (edge/serverless), AI Gateway, Memory, cron/scheduled jobs, Supabase-style REST/RLS, servicerole keys, or MCP.… | Skill | 621 | A | 92 | — |
| 61 | [object Object]team-reflect/reflect-openRead, search, and open notes in the user's "{{GRAPHNAME}}" Reflect graph via the reflect CLI. Use when the user asks about their notes, daily notes, journal, or anything they may have written down in Reflect. | Skill | 1.6k | A | 51 | — |
| 62 | powercontext-project-contextoceanbase/powercontextA project-memory guide for searching, saving, correcting, and transferring durable context through the PowerContext service. It distinguishes ordinary conversation from information that should persist between sessions. | Skill | 1.6k | A | 59 | — |
| 63 | knowledge-base-managementchubbyguan/chubbyskillsA lifecycle system for managing an Obsidian knowledge base, which is a folder of linked notes. It organizes raw material, AI-maintained wiki pages, and generated views into separate layers. | Skill | 1.3k | A | 69 | — |
| 64 | brain-pagemindmuxai/brain.mdOperating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page. | Skill | 604 | A | 47 | — |
| 65 | beyinavenoxai/avenoxbeyinVault içindeki bilgiyi bul, not ve görevleri güncelle, tamamlanan çalışmayı kaynaklarıyla kaydet. Hatırlama, not alma, proje/görev takibi ve beyin oturumu kapanışında kullan. | Skill | 386 | A | 52 | — |
| 66 | mcp-memory-servicedoobidoo/mcp-memory-serviceAutomatic memory capture and injection for Claude Code via MCP Memory Service. | Plugin | 2.1k | A | — | — |
| 67 | misakanet-failure-memoryIkalus1988/MisakaNetSearch MisakaNet failure-memory before debugging common errors. | Cursor rule | 560 | A | 0 | — |
| 68 | savelucasrosati/claude-code-memory-setupSaves the session to the vault and automatically consolidates durable decisions, insights and conventions. Use it when you finish or pause work. | Command | 1.1k | A | 0 | — |
| 69 | hivemind marketplaceactiveloopai/hivemindPlugin marketplace listing 1 plugin: hivemind. | Plugin | 1.7k | A | — | — |
| 70 | j-spaceTiger3807861189/J-Space-Cognition-Suite-V3.7Use this skill to establish and operate the model's inner workspace — the J-space — for any task that needs more than fluent output: multi-step or chained reasoning, planning, long-horizon and agentic work, competition-level problems, complex debugging, keeping many parts of a deliverable globally consistent, holding… | Skill | 3.0k | A | 144 | — |
| 71 | kayba-acekayba-ai/agentic-context-engineThis skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk. | Skill | 2.6k | A | 0 | — |
| 72 | ai-devkitcodeaholicguy/ai-devkitMake AI coding agents follow a repeatable engineering workflow with memory, verification, skills, and multi-agent setup. | Plugin | 1.7k | A | — | — |
| 73 | memory-audit-belief-duelDataojitori/nocturne_memoryA guided review process for conflicting beliefs or memories. It examines cases where two conclusions cannot both be true, including conflicts between a general rule and a more specific memory. | Skill | 1.4k | A | 38 | — |
| 74 | arreflectGoldentrii/AgentRecall-XAgentRecall consolidation & reflection — periodic triage of recurring corrections; proposes rule changes, never applies them without the owner. | Command | 375 | A | 24 | — |
| 75 | iweiwe-org/iweMarkdown knowledge base as agent memory. Runs against the notes directory it is started in. Runs locally from the @iwe-org/mcp npm package. | MCP server | 1.8k | A | — | — |
| 76 | forgetful-rememberScottRBK/forgetfulRemember knowledge worth keeping — a decision made, a solution found, a preference stated, a pattern confirmed. Use when work surfaces something future sessions will need, or the user asks to remember something. Routes content to the right store (memory, document, code artifact, entity, procedure, file) and enforces… | Skill | 340 | A | 71 | — |
| 77 | memoir-rememberzhangfengcdt/memoirExplicitly save a user-requested memory to Memoir now. Use when the user says remember, save, store, capture, or record a durable preference, decision, rule, fact, or note. Pick a taxonomy path with Codex when none is provided, always write with memoir remember -p, and never use legacy unpathed memoir remember. | Skill | 630 | A | 80 | — |
| 78 | utekecodecoradev/utekeUse the Uteke offline semantic memory engine (single Rust binary, no API keys) to store, recall and maintain persistent memories and docs across agent sessions. | Skill | 286 | A | 35 | — |
| 79 | cog-second-brainhuytieu/COG-second-brainSelf-evolving second brain with 43 AI agent skills, 10 agents, and people CRM. Closed-loop harness release: a V-model verification lifecycle (spec to evidence, criterion-traced checkpoints), read-only verifier agents that observe artifacts instead of trusting worker summaries, risk lanes, multi-session ultragoals with. | Plugin | 1.4k | A | — | — |
| 80 | sivtr-memoryAriestar/sivtrRetrieve shared local work memory: terminal activity, AI conversation history, prior decisions, validation evidence, debugging trails, recaps, and handoff context. Use before asking the user to repeat local work context. | Skill | 257 | A | 46 | — |
| 81 | mulch-record-from-evidencejayminwest/mulchTurn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them. | Skill | 338 | A | 61 | — |
| 82 | rag-index-decisionslyonzin/knowledge-ragAfter making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next occurrence is one search away. Uses adddocument or addfromurl. Closes the feedback loop that makes a RAG-backed team… | Skill | 305 | A | 72 | — |
| 83 | baidu-drivebaidu-netdisk/bdpan-storageA Chinese-language command-line workflow for managing files in Baidu Drive, a cloud storage service. It supports file transfers and organization, plus backup and recovery of certain agent memory data. | Skill | 338 | A | 211 | — |
| 84 | second-brain-memoryrahilp/second-brain-cloudflareAlways recall at session start and remember important context via Second Brain (MCP or brain CLI). | Cursor rule | 858 | A | 825 | — |
| 85 | prolongalexisfox7/PRO-LONGRecover and use durable coding-session history from PRO-LONG's local append-only log. Use on long-running coding tasks, after context compaction or session resume, when reconstructing prior decisions or tool results, or before repeating work that may already have been attempted. | Skill | 465 | A | 55 | — |
| 86 | superlogsuperloglabs/superlogOpen-source agent that observes and fixes your application. Query logs, traces, metrics, incidents. Remote server at api.superlog.sh. | MCP server | 1.5k | A | — | — |
| 87 | codebase-memory-mcpjeffbski/wait-onMCP server "codebase-memory-mcp" as configured in jeffbski/wait-on. Launched with mise exec -- codebase-memory-mcp. | MCP server | 2.0k | A | — | — |
| 88 | sandbox-environmentpssah4/vault-operatorSandbox API reference, proven patterns, and library recommendations for evaluateexpression. | Skill | 264 | A | 17 | — |
| 89 | first-tree-seedfirst-tree-ai/first-treeBootstrap a team's Context Tree from readable source repos — for an onboarding "build / set up the Context Tree" task on a tree that has no domain structure yet: either no tree exists (creates and binds it) or a bound-but-empty tree (fills it). Supports clean explicit-Team invocation without a Workspace manifest… | Skill | 160 | A | 142 | — |
| 90 | memorixAVIDS2/memorixShared workspace memory for Claude Code and other AI coding agents. | Plugin | 927 | A | — | — |
| 91 | context-recoverySakuraByteCore/codexmateRecovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity… | Skill | 356 | A | 72 | — |
| 92 | ctxctxrs/ctxFast local search and 'git blame' for agent sessions. | Plugin | 1.2k | A | — | — |
| 93 | marm-initLyellr88/marm-memoryGuided MARM MCP setup. Invoke after running marm-memory init on the CLI to configure MARM memory across your agent. Drives transport choice, runtime choice, MCP config writing, multi-agent linking, and server start. Works on Claude, Codex, Gemini, Qwen, Cursor, VS Code, and other MCP-capable agents. | Skill | 438 | A | 75 | — |
| 94 | egregoreegregore-labs/egregoreEgregore mechanics as kernel functions — search shared memory, read team activity, create handoffs, save work, branch, and prepare notification plans without re-deriving bin/ CLI usage. Import and call directly; every function wraps the same runtime-neutral bin/ scripts the other harnesses use. | Skill | 293 | A | 64 | — |
| 95 | token-optimizationooples/token-optimizer-mcpUse the token-optimizer MCP tools to reduce context/token usage when reading, searching, or editing files, or when the context window is filling up. Trigger when reading large files, re-reading files already seen, searching a big/unknown tree, making edits to large files, or when you need to store bulky output… | Skill | 577 | A | 71 | — |
| 96 | fdeopssuboss87/FDEOpsSkills for forward deployed engineers across strategy, architecture and engineering. Use individual tasks or @fde coordination; local customer memory supports continuity. | Plugin | 814 | A | — | — |
| 97 | clawmem-curatoryoloshii/ClawMemMaintains ClawMem memory health — lifecycle triage (pin/snooze/forget), retrieval health checks, dedup sweeps, graph rebuilds, index hygiene. Use when "curate memory", "memory maintenance", "run curator", or after long productive sessions. | Agent | 212 | A | 62 | — |
| 98 | openclaw-litecodesstar/lociOn first message, check if /.loci/lite/tasks/active.md exists. | Skill | 508 | A | 0 | — |
| 99 | accordion-context-foldinga-Fig/AccordionRead this skill if you see {# FOLDED} markers in your context (e.g. {#3f9a2c FOLDED}), or if earlier parts of your context look summarized. Accordion is a desktop tool that may compact older context blocks to keep you under a token budget. The unfold tool restores a folded block (open from your next turn); the recall… | Skill | 247 | A | 102 | — |
| 100 | ai-research-skills marketplaceWenyuChiou/ai-research-skillsResearcher-facing Claude Code skills for Zotero, Obsidian, NotebookLM, research memory, and paper workflows. | Plugin | 647 | A | — | — |
Want everything, not just what passes the gates? Browse the full category from any type hub, or search it. This shelf recomputes nightly from the measurements.