AI & ML

agentshield-ai Bundle

AI Agent Detection & Response — real-time security monitoring with Sigma rules and LLM-powered triage

reshashi Bundle

Spawn and manage parallel Claude workers for software development. Use for parallel feature development, multi-agent coordination, or autonomous project execution.

fasuizu-br Bundle

Transcribe an explicitly authorized local Brazilian Portuguese or Spanish audio or video file with the metered BRAINIALL API, speaker diarization, word timestamps, and JSON, SRT, and WebVTT outputs. Use when an agent needs speaker-labelled transcripts or caption files from .mp3, .wav, .m4a, .mp4, .mpeg, .mpga, .webm, or .ogg media.

darrryz Bundle

企业微信 (WeCom) Channel 插件 — 让 OpenClaw AI Agent 通过企业微信收发消息。支持消息加解密、Token 自动管理、访问控制策略。

leoyeai-openclaw-master-skills Bundle

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

leoyeai-openclaw-master-skills Bundle

This skill provides comprehensive guidance and tools for conducting pharmacoeconomic evaluations including cost-effectiveness analysis (CEA), cost-utility analysis (CUA), cost-benefit analysis (CBA), budget impact analysis (BIA), sensitivity analysis, and decision-analytic model construction (Markov, decision tree, DES, PSM). Follows ISPOR Good Practices for Outcomes Research Reports. Use this skill for HTA projects, drug pricing, reimbursement decisions, and health economic research.

leoyeai-openclaw-master-skills Bundle

Generate images from text with multi-provider routing — supports Nanobanana 2, Seedream 5.0, GPT Image, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.

portkey-wallet Bundle

Portkey EOA wallet lifecycle and asset operations for creating, importing, listing, backing up, selecting, and deleting wallets; querying tokens, NFTs, prices, balances, and history; and performing transfers, approvals, bridge, view, send, and fee estimation operations on AElf. Use by default for direct EOA wallets; use the Portkey CA skill for guardian, recovery, CA hash, or Contract Account workflows.

cortexreach-memory-lancedb-pro-skill Bundle

This skill should be used when working with memory-lancedb-pro, a production-grade long-term memory MCP plugin for OpenClaw AI agents. Use when installing, configuring, or using any feature of memory-lancedb-pro including Smart Extraction, hybrid retrieval, memory lifecycle management, multi-scope isolation, self-improvement governance, or any MCP memory tools (memory_recall, memory_store, memory_forget, memory_update, memory_stats, memory_list, self_improvement_log, self_improvement_extract_skill, self_improvement_review).

fausto-404 Bundle

通过 chrome-devtools-mcp 连接真实浏览器，自动定位前端加密入口，生成 JSRPC 注入代码、Flask 代理和 Burp autoDecoder 对接文档。

leoyeai-openclaw-master-skills Bundle

Top-tier GEO (Generative Engine Optimization) expert agent for managing daily AI visibility operations. Use this skill whenever someone wants to optimize brand visibility in AI search engines (ChatGPT, Perplexity, 豆包, Kimi, DeepSeek, 文心一言, Claude), run AIEO diagnostics, create AI-optimized content, monitor AI mention rates, build question libraries, or execute any GEO/AEO/AIEO workflow. Also trigger when users mention GEO-claw, AI搜索优化, 生成引擎优化, AI可见性, brand AI visibility, AI recommendation optimization, AI平台测试, FAQ optimization for AI, Schema markup for AI, or any work related to how brands appear in AI-generated answers — even if they don't say "GEO" or "agent" explicitly. Any AI visibility or generative search optimization work qualifies.

5dive-ai Skill

Send progress, completion, and option-prompt messages to the paired user via this agent's Telegram bot. Use whenever work takes more than a few seconds, when blocking on a user decision, or when presenting choices. Never go silent for more than ~30s on a long-running task.

yaklang Bundle

IRify SAST — AI-powered static application security testing. Compile source code into SSA IR, then use SyntaxFlow DSL to trace data flow across function boundaries, detect vulnerabilities (SQLi, RCE, XXE), and answer questions like "where does user input go?". Supports 7 languages (Java, PHP, JS, Go, Python, C, Yak) and incremental compilation via ProgramOverLay. Requires yaklang MCP server: yak mcp -t ssa

draeden79 Bundle

Microsoft 365 Graph for OpenClaw with webhook-based wake signals. Reduce recurring LLM cost from inbox polling while managing Outlook mail, calendar, OneDrive, and contacts via Microsoft Graph.

zhaobudaoyuema Bundle

Count tokens and estimate costs for 300+ LLM models. Primary use: audit OpenClaw workspace token consumption (memory, persona, skills).

gaoryan86 Bundle

Audit and optimize OpenClaw workspace documents (AGENTS.md, SOUL.md, USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, memory/) for redundancy, dead content, format compliance, cross-file conflicts, and token efficiency. Use when user asks to audit workspace files, check document health, reduce token usage, clean up memory, or optimize agent configuration. Triggers on "audit workspace", "check my docs", "optimize tokens", "clean up memory", "workspace health", "文档审计", "精简文档", "token优化".

xrds76354 Bundle

Model Context Protocol integration for SUMO. Use when a task needs automated multi-step SUMO workflows, programmatic tool execution, live TraCI control, or RL training via MCP tools. Avoid for simple command hints or static config edits.

pytorch Skill

Verify forward and backward numerical correctness of a handwritten low-precision GPU kernel against a high-precision oracle and an eager same-dtype baseline. Use for Triton or CUDA kernel correctness; use numerics_debugging to locate an unknown whole-model divergence.

pytorch Skill

Profiler-driven hill-climbing to close the inference throughput gap between TorchTitan's unified model (running inside vLLM) and vLLM's native model. Benchmark with generate.py --benchmark, climb optimization rungs (compile / cudagraph / fused kernels), profile torchtitan vs the native target, then patch the single biggest gap at a time and re-measure. Use when the user wants to benchmark or optimize RL inference generation speed, reproduce previous hill climbing study, or invokes /inference_perf_hillclimb.

pytorch Bundle

Add a new HF MoE model to the transformers_modeling_backend experiment. Use when the user provides a HuggingFace model ID and wants to integrate it with Titan's MoE, or invokes /add_moe_model.

camronh Bundle

Write and analyze evaluations for AI agents and LLM applications. Use when building evals, testing agents, measuring AI quality, or debugging agent failures. Use this skill when you need to test the performance of an LLM or Agent, or if the user mentions EZVals.

ishnoor-singh Bundle

A virtual world where AI agents live, chat, and socialize. Join as an external agent via HTTP API.

6551team Bundle

Twitter/X data via the 6551 API. Supports user profiles, tweet search, user tweets, follower events, deleted tweets, and KOL followers.

yu-iskw Skill

Synchronizes Subagents with available Agent Skills, suggesting bindings and removing broken links.

yu-iskw Skill

Verifies and updates the commands within existing Agent Skills to ensure they match the current codebase state.

nvidia Skill

Maintain the NeMo Curator Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation changes.

dbt-labs Skill

Use in a reviewer agent in agent loops or when reviewing your own code.

e-x-o-entertainment-studios-inc-hopeids Bundle

Inference-based intrusion detection for AI agents. Pattern matching + LLM analysis for jailbreaks, prompt injection, credential theft, social engineering. 108 detection patterns, OpenClaw plugin, auto-scan, quarantine. Commands: hopeid scan, hopeid test, hopeid setup, hopeid stats, hopeid doctor.

jinn-network Skill

Bootstrap a jinn-node installation — prereqs, clone, and dependency install. Use when user says "set up jinn-node", "run a jinn node", "install jinn", "earn with my agent", or "jinn setup".

goodeye-labs Skill

Orchestrator for Truesight MCP skills. Use this when the user needs help choosing the right Truesight workflow or when intent is ambiguous across LLM evaluate, error analysis, review, templates, or evaluation creation.

goodeye-labs Skill

Generate synthetic test data for LLM evaluations using dimension-based tuple expansion. Use when the user needs synthetic traces, test cases, eval datasets, or when create-evaluation needs synthetic fallback data.

davebream Skill

Use only when the user explicitly asks for an interactive three-perspective review of a completed deep-study report and Claude Code agent teams are already enabled in in-process mode.

davebream Bundle

Use when producing a passage reader with a deduplicated lemma glossary. Use when user asks for a vocabulary list, glossary, lemmas in a passage, deduplicated glossary for a text, or a graded-reader study artifact. Combines passage text with an ordered, MCP-grounded glossary of every distinct headword. Always English output.

drbarq Bundle

Play Pokemon Red autonomously via PyBoy emulator. The OpenClaw agent IS the player — starts the emulator server, sees screenshots, reads game state from RAM, and makes decisions via HTTP API. Use when an agent wants to play Pokemon Red, battle, explore, grind levels, or compete with other agents. Requires Python 3.10+, pyboy, and a legally obtained Pokemon Red ROM.

claw-silhouette Bundle

Get a free bot email address instantly — no steps other than installing needed. Just say "get me a bot email" and the agent creates your address in seconds. Supports inbox monitoring, attachment downloads, and heartbeat auto-notifications.

ramsbaby-openclaw-memorybox Bundle

Memory health CLI that diagnoses bloated MEMORY.md files, splits oversized sections into domain files, archives stale daily logs, and runs continuous health monitoring. Use when MEMORY.md exceeds 10KB, context windows overflow from memory bloat, or agent sessions slow down from loading large memory files. Pure bash, zero dependencies.