Best OpenClaw Skills (2026)
The best OpenClaw skills, chosen from what developers and reviewers who run the agent say they keep installed, then checked against each skill's source and its ClawHub security audit.
Gog
One skill covers Gmail, Calendar, Drive, Docs, Sheets and Contacts through the gog command-line tool, and it turns up on nearly every list, from Travis Media to KDnuggets' Abid Ali Awan. It ships with OpenClaw, so you only add the CLI and a Google OAuth client. The catch is how much it can do: Faberlens testers found it teaches the agent to bulk-delete mail without teaching it when to stop, so require confirmation before it sends or deletes.
- Install
- Bundled; add the CLI: brew install openclaw/tap/gogcli
- Maintainer
- OpenClaw (published by Peter Steinberger, steipete)
- Popularity
- 196,584 ClawHub downloads; 953 stars
- License
- MIT (OpenClaw repository)
- Needs
- gog CLI and a Google OAuth client (client_secret.json)
- ClawHub audit
- Pass (ClawHub copy, September 10, 2026)
GitHub
Wraps the gh command-line tool so the agent can triage issues, review pull requests and read CI logs from chat. Rost Glukhov, who installed 18 skills to compare them, calls it the kind the ecosystem needs more of: boring, direct and tied to a tool developers already know. It is bundled with OpenClaw. It acts through your signed-in gh session, so look at any command that changes a repository before you let it run.
self-improving agent
The most downloaded skill on ClawHub. It writes failures and your corrections to a .learnings folder and reads them back before similar work; Monica's agent stopped reaching for a deprecated Python library after one correction. Since it took off, OpenClaw has added self-learning of its own, switched on by default, so see whether that is enough before adding this. The optional hook scans each finished session's transcript for errors.
- Install
- openclaw skills install @pskoett/self-improving-agent
- Maintainer
- pskoett
- Popularity
- 484,149 ClawHub downloads; 3,997 stars
- License
- MIT-0
- Needs
- Nothing extra; the session-end error hook is optional
- ClawHub audit
- Pass (October 4, 2026)
Summarize
Give it a URL, a PDF, a podcast or a YouTube link and it returns the gist, working from captions or a transcript when one exists. Travis Media uses it for research and for deciding whether a video is worth watching. It is bundled with OpenClaw and its maintainer has not published it on ClawHub, so the registry entries called Summarize come from other people. The CLI needs a model API key of its own.
wacli
Lets the agent message other people on WhatsApp and sync or search your chat history. It is not for talking to your own agent on WhatsApp; OpenClaw's WhatsApp channel already does that. Dubibubi notes that many people only let it send messages to themselves. The skill now ships inside OpenClaw's WhatsApp plugin, so clawhub install wacli from older guides no longer finds it. It speaks the WhatsApp Web protocol and is not affiliated with Meta.
- Install
- In the WhatsApp plugin; brew install openclaw/tap/wacli
- Maintainer
- OpenClaw
- Popularity
- 2,797 GitHub stars
- License
- MIT
- Needs
- wacli CLI linked to your WhatsApp account
Obsidian
Reads, searches and writes notes in an Obsidian vault, which several long-term users treat as the agent's memory. Tom Pounders keeps it in a setup that allows no community skills at all. WenHao Yu's warning applies: a skill only teaches the method, and nothing gets written unless the write tool is enabled. The bundled version drives Obsidian's official CLI, while the ClawHub copy dates from January and installs a third-party one.
Agent Browser
A command-line browser made for agents. It reads a page as an accessibility snapshot and clicks elements by reference, so it can fill forms and scrape pages without a visible window. Rost Glukhov rates it powerful and adds that saved logins and cookies need care. Install Vercel Labs' own skill, because the name is crowded: Composio's guide points to a ClawHub copy that is gone, and the most downloaded copy is frozen at version 0.1.0.
- Install
- npx skills add vercel-labs/agent-browser
- Maintainer
- Vercel Labs
- Popularity
- 43,835 GitHub stars
- License
- Apache-2.0
- Needs
- agent-browser CLI: npm install -g agent-browser
- ClawHub audit
- Review for MaTriXy's ClawHub copy (September 10, 2026)
ontology
Keeps what the agent learns as a typed graph of people, projects, tasks and documents instead of a growing pile of notes. Three reviewers single it out, and Rost Glukhov calls structure the stronger long-term direction for agent memory. Its publisher, Palash Oswal, is easy to identify. ClawHub's audit marks it for review, not as malicious: it can write and delete shared memory records with fewer safeguards than its documentation claims.
- Install
- openclaw skills install @oswalpalash/ontology
- Maintainer
- Palash Oswal (oswalpalash)
- Popularity
- 199,865 ClawHub downloads; 660 stars
- License
- MIT-0
- Needs
- No API key; stores its graph in your workspace
- ClawHub audit
- Review (September 10, 2026)
Humanizer
Rewrites text to remove the tells listed in Wikipedia's Signs of AI writing guide. Travis Media runs it as a last pass on blog posts, and Christopher Kvamme installed it first for a content pipeline. Take it from Siqi Chen's repository: the ClawHub copy with 132,134 downloads was republished by an account with an empty GitHub profile and has stayed at version 1.0.0. The README says AI detectors still flag most of its output.
- Install
- npx skills add blader/humanizer --global --agent '*'
- Maintainer
- Siqi Chen (blader)
- Popularity
- 55,879 GitHub stars
- License
- MIT
- Needs
- Nothing; instructions only, no code
- ClawHub audit
- Review for the ClawHub republish (September 10, 2026)
Notion
Creates and updates Notion pages and databases. It is bundled, and worth turning on if your work already lives in Notion; Dan Cleary connected it early and later moved his agent's output to a dashboard he built, because he never liked Notion on his phone. Share the integration only with the pages the agent should touch. Rost Glukhov liked the workflow and distrusted the packaging in May; the ClawHub copy's audit passes today.
Weather
Current conditions and forecasts from wttr.in, with no API key. It is the simplest skill here and a good first check that skills work at all on your install. Travis Media has it in a scheduled job that runs at 8 AM and tells him whether to take a jacket. It is bundled with OpenClaw. The place you ask about goes to a public weather service, which is the one thing the audit asks you to be comfortable with.
- Install
- Bundled; nothing to install
- Maintainer
- OpenClaw (published by Peter Steinberger, steipete)
- Popularity
- 171,380 ClawHub downloads; 429 stars
- License
- MIT (OpenClaw repository)
- Needs
- No API key; uses wttr.in
- ClawHub audit
- Pass (ClawHub copy, September 10, 2026)
OpenAI Whisper
Transcribes audio on your own machine with the Whisper command-line tool, so recordings stay local and no API key is needed. Rost Glukhov calls it limited, local and refreshingly straightforward. Do not confuse it with openai-whisper-api, a separate bundled skill that sends audio to OpenAI and does need a key; Composio's guide says this one needs a key, and it does not. Models download to your disk on the first run.
- Install
- Bundled; add the CLI: brew install openai-whisper
- Maintainer
- OpenClaw (published by Peter Steinberger, steipete)
- Popularity
- 89,200 ClawHub downloads; 341 stars
- License
- MIT (OpenClaw repository)
- Needs
- whisper CLI; models download on first run; no API key
- ClawHub audit
- Pass (ClawHub copy, September 10, 2026)
How to choose
For email and calendar, start with Gog. For code, GitHub. For long articles, videos and podcasts, Summarize. For notes, Obsidian or Notion. To stop the agent repeating a mistake, self-improving agent. For cleaner prose, Humanizer.
Safety first. ClawHub, the registry, lets anyone with a GitHub account publish, and a skill acts with whatever access your agent has. Security firms have counted more than a thousand malicious skills there since January 2026, and in June Unit 42 and Trail of Bits each showed skills getting past its scanners. OpenClaw's own June data labelled 25,504 of 67,453 skill versions suspicious and 206 malicious. Every skill page now has a security audit with an outcome such as Pass or Review. Read it, and the SKILL.md, before you install.
Older guides are out of date in three ways. Most of the skills they tell you to install now ship with OpenClaw and switch on when their command-line tool is present. Web search, self-learning and memory search are built in, and Tavily has a first-party plugin, so the Tavily and QMD skills are no longer needed. And names are copied: at least five publishers use the slug gog, so install with the owner, as in @steipete/gog.
Skill Vetter and Capability Evolver are on most lists and left out here. Skill Vetter's publisher links to a GitHub profile that no longer exists. ClawHub's audit marks Capability Evolver for review because it can run jobs handed to it by a remote server.
Skills are ordered by how many independent reviewers and users recommend them, then by downloads or stars. All are free.
Numbers checked October 11, 2026.
More guides like this
OpenClaw Alternatives (2026): Safer and Easier to Run
The best OpenClaw alternatives are other personal AI agents you message from a chat app, self-hosted or hosted. These picks rest on write-ups by people who switched and on what developers on Hacker News say they run now. People leave OpenClaw for four reasons: updates that break things, token bills, the work of running it, and security. If it kept breaking, most switchers land on Hermes Agent, which imports your OpenClaw memory and skills. If you want code you can read and agents locked in containers, pick NanoClaw. For a small VPS, a Raspberry Pi or a $10 board, look at ZeroClaw or PicoClaw. If you never want to run a server again, Claude Cowork, Grok Bot and Manus do the hosting for a monthly fee. A few things the makers' pages won't tell you. None of the open-source agents is free to run: you still pay a model provider, and switchers report $10 to $20 a month on cheap models and far more on top ones. People who moved to Claude's own tools say Anthropic stopped Claude subscriptions from covering OpenClaw in April 2026. NemoClaw is a sandbox that runs OpenClaw or Hermes inside it, not a replacement. QwenPaw was called CoPaw until April 2026. Perplexity's Computer and Personal Computer are different products. Hosted agents bill in credits or weekly allowances that are hard to predict. And a smaller codebase is easier to audit, but any agent holding your logins can still be tricked by a hostile web page or message. Ordered by how many independent users and reviewers recommend each one, then by GitHub stars, then by price. Prices checked October 11, 2026.
Best Claude Skills (2026)
The best Claude skills are the SKILL.md packages that Hacker News users and independent reviewers keep recommending. This list ranks collections and single skills you can install today, with what each adds and its catch. If you want Claude to plan and test before it codes, get Superpowers. If you want it to question you before it starts, get grill-me from Matt Pocock's skills. For better-looking pages, start with frontend-design and add Impeccable to review the result. To build your own skills, or to make real Word, Excel, PowerPoint and PDF files, use Anthropic's repository. For marketing work, use Corey Haines's pack. Skills install in three ways. In Claude Code, run /plugin install from a marketplace, or copy a folder into ~/.claude/skills. For most coding agents, npx skills add owner/repo does the copying. In the Claude apps, upload a ZIP under Customize > Skills. Skills follow the open Agent Skills format, so most of these also run in Codex, Cursor and Gemini CLI. Older guides are now wrong in places. Claude Code has merged custom commands into skills. Superpowers and Matt Pocock's skills are in Anthropic's official marketplace, so adding a separate marketplace is no longer needed. The Karpathy repository moved to a new owner. Star counts are huge and say little, and a link list such as awesome-claude-skills installs nothing. A skill is instructions plus scripts that run with your agent's permissions. Snyk scanned 3,984 skills from ClawHub and skills.sh and found a critical security issue in 13.4% of them. Read a skill before you install it, and install a few, not all. Items are ordered by how many independent people recommend each one, then by GitHub stars. Everything here is free. Numbers checked October 11, 2026.
Claude Code Plugins (2026): What Developers Install
The best Claude Code plugins, picked from the setups developers publish after pruning their own installs and from Hacker News threads where people say what they kept, not from install counts alone. A plugin is a bundle. One install can carry skills, slash commands, subagents, hooks and MCP servers. A skill is a single instruction file Claude loads when it judges it relevant, and an MCP server is a connection to an outside tool, so a plugin can contain both. Type /plugin inside Claude Code to browse Anthropic's official marketplace, which is connected from the start, or run /plugin install name@claude-plugins-official. For anything else, add the maker's marketplace first with /plugin marketplace add owner/repo. If you install one thing, make it Superpowers, plus the LSP plugin for your language. Add Security Guidance if you ship code you don't read line by line, Plannotator if you want to mark up plans in a browser, and Claude HUD to see how full the context is. Every enabled plugin adds to the context on every turn, and several of the writers quoted here deleted more than they kept. Plugins run code on your machine with your permissions, and community marketplaces are not reviewed, so read what a plugin will install before you say yes. Two names trip people up. Claude Code has a built-in review command alongside the Code Review plugin. And Anthropic keeps a second, smaller marketplace in the anthropics/claude-code repo, where the loop plugin still goes by ralph-wiggum and not ralph-loop. The list is ordered by how many independent people recommend each plugin, then by installs and GitHub stars. Prices checked October 11, 2026.
OpenCode Plugins (2026): Which Still Work on OpenCode 2
The best OpenCode plugins, and which ones work on OpenCode 2, ranked by how many developers outside each project say they use them, in blog posts, hands-on reviews and Hacker News threads. If your sessions run out of context, start with Dynamic Context Pruning. If you want the agent to plan before it codes, get Superpowers, or Plannotator to review plans in a browser. For a team of subagents, oh-my-opencode-slim is the one that runs on the current version. For memory that stays on your machine, opencode-mem. The thing no plugin page says loudly: OpenCode 2.0 came out in September 2026 with a new plugin system, and plugins written for OpenCode 1 do not load on it. Older guides tell you to add a package name to the "plugin" list in opencode.json, which OpenCode 1 then installs at startup. On OpenCode 2 the list is called "plugins" and there is a command for it, opencode plugin add <package>. Check the Works with line on each pick before you upgrade. OpenCode 1 still gets releases. Two names to keep straight. The OpenCode here is the one at opencode.ai, now in the anomalyco/opencode repository on GitHub. An earlier Go project with the same name, opencode-ai/opencode, is archived and continues as Crush. And oh-my-opencode was renamed oh-my-openagent. Plugins that sign you in with a Claude or Gemini subscription are left out. Google and Anthropic treat that as against their terms, the popular Antigravity one is archived, and accounts have been flagged. A plugin runs with your full permissions, so read what you install. Ordered by how many independent recommendations each plugin has, then by downloads and stars. A plugin that does not load on the current OpenCode ranks below the ones that do. Numbers checked October 17, 2026.
Best Pi Coding Agent Extensions (2026)
The best extensions for the Pi coding agent (some people call them plugins), picked from the setups developers publish and the write-ups that tested them, not from download counts alone. Pi is deliberately bare: no sub-agents, no plan mode, no permission prompts. You add what you miss with one command, pi install npm:<package>. If you are starting out, three cover most of the gap with Claude Code: pi-subagents for delegation, pi-web-access for search, and rpiv-ask-user-question so the model asks before it guesses. Add Plannotator if you want plan mode, and pi-permission-system if you don't want the agent free to run anything. Two things have changed that older guides miss. Pi has had MCP support built in since version 0.99, so pi-mcp-adapter is now an upgrade and no longer a requirement. And several popular names have lookalikes: npm has at least four other packages named pi-mcp-adapter under other people's scopes, and more than one /btw extension, so install by the exact name shown here. Extensions run with the same access to your machine that Pi has. Pi's catalog lists more than 5,000 packages, so read the source of anything that touches your shell or credentials, and pin versions you depend on. Ordered by how many independent users and reviewers recommend each one (Kay Rhodes's setup guide, Composio's tested top ten, developers on Hacker News and Pi's own GitHub discussions), then by npm downloads and GitHub stars. Downloads count automated installs too, so treat them as a rough signal. Numbers checked October 10, 2026.