Skill reviews

Persistent agent memory and versioned markdown documents over the Mark Protocol (mark://). Use when asked to remember something across sessions, fetch or publish mark:// documents,

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Execute DeFi transactions on BSC via SHLL AgentNFA. The AI handles all commands and users only need to chat.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 19 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (26 tags): a typed call is more reliable

A multi-chain wallet skill for AI agents, with local sandbox signing, secure PIN handling, and configurable risk controls.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The response is described with custom markup (18 tags): a typed call is more reliable

Orchestrate policy-bounded DeFi sessions, OODA plans, intent state, circuit breakers, and recovery; execution stays status-gated and separately authorized.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• 13 mutating operations with no state check

Control and query Home Assistant via natural language. Covers lights, switches, climate, temperature sensors, cameras, automations, energy monitoring, EV chargers, presence detecti

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Send and receive compliant B2B payments via the Ra Pay CLI, and onboard a counterparty agent so both sides can transact.

• 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
• Does not say what the result is

AI UGC video production from the terminal using the `agent-media` CLI.

• 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 response is described with custom markup (16 tags): a typed call is more reliable

Use when an agent needs to turn evidence-backed behavior into a validated self-intro submission, a share-card JSON payload, and a final screenshot-friendly HTML selfie card with a

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Query Claude API usage and cost reports from the command line. Secure macOS Keychain storage for Admin API key. Table/JSON output.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The response is described with custom markup (10 tags): a typed call is more reliable
• Does not say what the result is

Stake $CLAWMEGLE tokens to earn dual rewards (ETH + CLAWMEGLE) from Clanker LP fees. Use when an agent wants to stake tokens, check staking rewards, claim earnings, or manage their

• 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
• Does not say what the result is

A Meeting Execution Operator. Not an automated bot, but a strategic orchestrator for preparation, capture, and commitment tracking. Operates on a "Draft-First" and "Manual Confirma

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Does not say what the process needs to start

Better Every Run: capture explicit /ber corrections, review them, and promote only the lessons that deserve durable memory, skill rules, or evals.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• No condition that starts the skill
• Does not say what the process needs to start

Communicate with other OpenClaw agents on your local network. Use when you need to ask another agent a question (sync), delegate a task (async), or check if a peer agent is reachab

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Manage Alibaba Cloud Security Center (Sas) via OpenAPI/SDK. Use whenever the user needs Security Center resource operations, configuration updates, status queries, and troubleshoot

• 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
• 1 mutating operations with no state check

Run and grow a Whop business with better offers, checkout flows, promo strategy, affiliates, ads, tracking, analytics, support operations, and advanced API workflows when needed

• 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
• Does not say what the result is

Send and receive messages between AI agents via the ClawTell network. Use when sending inter-agent messages, handling ClawTell deliveries, or setting up ClawTell for the first time

• 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
• Does not say what the result is

TuleBank — check wallet balance, send ARS to any CVU/ALIAS, swap USDC/wARS, manage beneficiaries, and move funds with ARS off-ramp/on-ramp flows.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• 58 mutating operations with no state check

Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 17 top-level sections: this looks like several domains in one skill
• Does not say what the result is

Natural language task and project management. Use when the user talks about things they need to do, projects they're working on, tasks, deadlines, or asks for a project overview /

• References files that are not bundled: {rel_path}, templates/dashboard/*.html, scripts/*.py
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 15 top-level sections: this looks like several domains in one skill

Security partner for Inner Warden — validates commands before execution, monitors server health, diagnoses and fixes issues. Requires Inner Warden installed.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Digital legacy agent — dead man's switch, final message executor, and ghost mode responder that preserves your digital presence. Use when the user wants to set up a dead man's swit

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• Does not say what the process needs to start

Track competitors with pricing alerts, feature changes, positioning analysis, and strategic dossiers.

• 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
• Does not say what the result is

Automate Brevo (Sendinblue) tasks via Rube MCP (Composio): manage email campaigns, create/edit templates, track senders, and monitor campaign performance. Always search tools first

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• Does not say what the result is
• No condition that starts the skill

Generate children's drawings and coloring pages with modular prompts, style packs, and print-ready constraints across image models.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• Does not say what the result is