Skill reviews

Google Indexing API tool. Use when user wants to submit URLs for Google indexing. Supports two modes: "auto-index" (fetch sitemap, diff against cache, submit new URLs) and "index-n

• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill
• Linear process with no failure handling

Security auditing for git commits, repos, and skills before publishing. Run automatically before any `git commit`, `git push`, or `clawhub publish`. Detects hardcoded secrets, API

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed s

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (21 tags): a typed call is more reliable

Manage feature requests, votes, roadmaps, and changelogs with VoteShip.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Tamper-Proof Audit Trails for Trading Bots. EU AI Act, MiFID II, and SEC 17a-4 compliance audit trail implementation for autonomous trading bots. Includes detailed Python code exam

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

A distributed task collaboration platform designed specifically for AI agents. Supports task creation, assignment, status synchronization, progress tracking, and real-time collabor

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Route user tasks to the most relevant skills using a layered taxonomy, risk model, and minimum-necessary-loading strategy. Use when deciding which skill to load, when multiple skil

• References files that are not bundled: references/routing-decisions.jsonl
• 20 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Async Agent Commerce: Event-Driven Patterns for Autonomous Transactions. Build event-driven agent commerce systems using saga patterns, compensating transactions, dead letter handl

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Benchmark and rank AI providers/models against a user-specific prompt suite derived from the user's purpose, domain, and usage frequency. Use when users ask which model is smarter,

• References files that are not bundled: examples/*.yaml
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model

Visualize gene structure with exon-intron diagrams, domain annotations, and mutation position markers. Produces SVG, PNG, or PDF figures suitable for publication from a gene symbol

• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• No condition that starts the skill

AgentGuard security engine — intercept dangerous operations, audit all actions, protect sensitive data. All commands/file/network operations go through ag_* tools for rule engine r

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Create, read, unlock, update, and delete temporary Markdown shares through the MDShare service. Use when an agent needs to publish Markdown as a short-lived share link, fetch share

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Install: clawhub install skill-creator

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Memorist Agent — helps you capture your parents' and family members' life stories through adaptive interviews via WhatsApp, WeChat, or direct conversation. Organizes stories into m

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 16 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Lobster Brew helps your OpenClaw discover coffee roasters, compare coffees, build personalized carts, and hand off a secure Shopify checkout link for you to complete the purchase.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Comprehensive Blender automation via Python bpy API. Procedural modeling, material nodes, lighting, rendering, and asset generation. Includes verified gear/mechanical parts demo.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Linear process with no failure handling

Agent-Ready Commerce: Retrofit Your APIs for AI Buyers. Build agent-discoverable storefronts and API-first product feeds so AI shopping agents choose your products over competitors

• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Automatically fetch multi-dimensional on-chain data using Nansen CLI, compile a comprehensive and beautifully formatted daily report, and publish it to Binance Square. Auto-run on

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 10 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Convert any webpage to a clean, high-quality PDF file and send it directly. Use when the user asks to view a website, screenshot a webpage, or see a page's content. Exports the web

• References files that are not bundled: scripts/batch-export.sh
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: scripts/batch-export.sh

Operate DefiLlama Pro analytics APIs through UXC with a curated OpenAPI schema, path-templated API-key auth, and read-first guardrails.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

Prepare and publish a local skill to ClawHub and GitHub using a workflow that keeps the local publish directory clean. Use this skill when the user wants to update an already publ

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Alibaba Cloud OSS scheduled local-folder sync skill using aliyun CLI, including integrated ossutil commands for incremental upload. Use when the user wants to schedule recurring lo

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 12 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

The Agent Production Hardening Guide. Step-by-step playbook to take AI agent systems from pilot to production with SLOs, circuit breakers, cost guardrails, and EU AI Act compliance

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 13 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Diagnose GPU issues on Alibaba Cloud ECS GPU instances: GPU device status, driver issues, and GPU hardware failures. Use when users ask to check the GPU status of their GPU instanc

• References files that are not bundled: references/how-to-implement-by-common-sdk.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval