Agent Memory
Dennis · Source needs review
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
D · Limited evidence · Execution Low
Narrow the list first, then review author, source, risk, and alternatives to pick faster.
Start simple, then layer advanced filters
Showing the first 24 of 601 indexed skills.
Applied filters
Dennis · Source needs review
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
D · Limited evidence · Execution Low
You get source-backed evidence and hints here; installation decisions always stay with you.
Nukewire · Source needs review
Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing
D · Limited evidence · Execution High
Wscats · Source needs review
A comprehensive Bilibili toolkit that integrates hot trending monitoring, video downloading, video watching/playback, subtitle downloading, and video publish...
C · Review first · Execution Low
TheSethRose · Source needs review
Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.
D · Limited evidence · Execution High
mxfeinberg · Source needs review
Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable.
C · Review first · Execution Low
liuxy951129-cpu · Source needs review
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本,使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式:夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
C · Review first · Execution Low
guogang1024 · Source needs review
Search and analyze your own session logs (older/parent conversations) using jq. The skill's requirements and instructions are coherent with its stated purpose (searching local session JSONL logs with jq and ripgrep) and
D · Limited evidence · Execution High
Iván · Source needs review
Anticipates needs, keeps work moving, and improves through use so the agent gets more proactive over time.
C · Review first · Execution Low
Iván · Source needs review
Docker containers, images, Compose stacks, networking, volumes, debugging, production hardening, and the commands that keep real environments stable. Use whe...
D · Limited evidence · Execution High
byungkyu · Source needs review
Google Workspace Admin SDK integration with managed OAuth. Manage users, groups, organizational units, and domain settings. Use this skill when users want to administer Google Workspace. For other third party apps, use t
D · Limited evidence · Execution Low
bert-builder · Source needs review
AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with
D · Limited evidence · Execution High
GeekCraft · Source needs review
Perform deep SEO competitor analysis, including keyword research, backlink checking, and content strategy mapping. Use when the user wants to analyze a website's competitors or improve their own SEO ranking by studying t
C · Review first · Execution Low
officialpm · Source needs review
Control Tesla vehicles from macOS via the Tesla Owner API using teslapy (auth, list cars, status, lock/unlock, climate, charging, location, and extras). Use when you want to check your car state or run safe remote comman
D · Limited evidence · Execution High
Nimrod Gutman · Source needs review
Generate SRT subtitles from video/audio with translation support. Transcribes Hebrew (ivrit.ai) and English (whisper), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or
D · Limited evidence · Execution High
codedao12 · Source needs review
OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
D · Limited evidence · Execution High
IPedrax · Source needs review
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
D · Limited evidence · Execution Low
Wesley Armando · Source needs review
Detect prompt injection, jailbreak, role-hijack, and system extraction attempts. Applies multi-layer defense with semantic analysis and penalty scoring.
C · Review first · Execution Low
byungkyu · Source needs review
Google Calendar API integration with managed OAuth. Create events, list calendars, check availability, and manage schedules. Use this skill when users want to interact with Google Calendar. For other third party apps, us
D · Limited evidence · Execution Low
nitishgargiitd · Source needs review
#1 on DeepResearch Bench (Apr 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. R...
C · Review first · Execution Low
billyutw · Source needs review
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, for
D · Limited evidence · Execution High
BENZEMA216 · Source needs review
🏆 AI交易复盘教练 — 把你的券商CSV变成可执行的改进洞察! 自动FIFO配对持仓,8维度质量评分(入场/出场/趋势/风险...),10维度AI洞察。 支持富途(中/英)、老虎、中信、华泰等主流券商。 触发条件: 用户提供交易CSV、要求分析交易表现、评估交易质量、生成复盘报告、 计算盈亏统计、识别交易模式问题、"帮我复盘"、"分析我的交易"。
C · Review first · Execution Low
jotamed · Source needs review
Read, search, and manage Outlook emails and calendar via Microsoft Graph API. Use when the user asks about emails, inbox, Outlook, Microsoft mail, calendar events, or scheduling.
D · Limited evidence · Execution Low
kesslerio · Source needs review
Market news briefings with AI summaries. Use when asked about stock news, market updates, portfolio performance, morning/evening briefings, financial headlines, or price alerts. Supports US/Europe/Japan markets, WhatsApp
C · Review first · Execution Low
TXMERLXN · Source needs review
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
D · Limited evidence · Execution High