Skill reviews

Generate secure SQL queries with validation, pagination helpers, risk analysis, and audit-focused safeguards.

• 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
• No condition that starts the skill

Local SiYuan API integration for notebook, document, block, asset, database/attribute view, and limited SQL operations. Restricted to local HTTP endpoints and environment-based tok

• 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

Shared Meta Ads skill for OpenClaw agents. Analyze Meta (Facebook and Instagram) ad accounts, campaigns, ad sets, ads, insights, and lead-form data with a production-safe read-firs

• 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

• 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
• Does not say what the result is

DeepSeek models on your local fleet — DeepSeek-V3, DeepSeek-V3.2, DeepSeek-R1, DeepSeek-Coder routed across multiple devices via Ollama Herd. 7-signal scoring picks the best machin

• 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

When your human faces a decision that keeps them up at night — "Should I leave this relationship?" "Is now the right time to quit?" "Can I trust this person?" — consult Qronos. Unl

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

Turns your weekly repetitive tasks into automated bots. Identifies high-value automation opportunities, picks the right tool (Dify / Coze / n8n workflow, or zero-Token RPA scripts)

• 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
• 13 mutating operations with no state check

Evidence-based, approval-gated self-improvement workflow for OpenClaw. Use when the user asks to make OpenClaw or any project more reliable, faster, cheaper, safer, or higher quali

• 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
• 5 mutating operations with no state check

Produce polished, production-ready daily news briefings, morning reports, market snapshots, executive digests, and founder updates with verified sourcing, clear prioritization, and

• 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

Nano Banana 2 — AI image generation powered by Google Gemini 3.1 Flash. Fast, versatile text-to-image and image editing via Evolink API. One API key.

• 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

Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust across MCP discovery, CVEs, SBOMs, CIS benchmarks (AWS, Azure, GCP, Snowf

• References files that are not bundled: discover/SKILL.md, scan/SKILL.md, scan-infra/SKILL.md
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 8 referenced file(s) missing: discover/SKILL.md, scan/SKILL.md, scan-infra/SKILL.md

• 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
• Does not say what the result is

AI PPT creation skill with structured 5-stage generation, machine-readable QA gates, checkpoint recovery, and experience accumulation. 20 layout methods, native charts, visual QA p

• 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

Deploy Jarvis, your Chief of AI Staff, on OpenClaw. Optimized for Dell Pro Max GB10 (NVIDIA DGX Spark) edge devices. Use when setting up Jarvis, configuring an AI executive agent,

• 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

Workspace wellness break reminder with configurable work interval, cooldown, idle reset, quiet hours, and per-day caps. Use when users want OpenClaw to remind them to take regular

• 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

Lightweight markdown editor with optional OpenClaw gateway chat. Filesystem-based, no database required.

• 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

Track, calculate, and optimize key performance metrics for startups from seed through Series A. Covers unit economics, growth efficiency, and business models.

• 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

Analyze read-only multichain EVM portfolios, wallet balances, idle stablecoins, capital efficiency, allocation drift, and rebalance proposals.

• 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
• Does not say what the process needs to start

Manage ATX on BSC with wallet creation, price and balance queries, PancakeSwap V3 swaps, liquidity operations, LP positions and holdings, and BNB/ERC20 transfers. Use when the user

• 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 (5 tags): a typed call is more reliable

United States federal income tax filing assistant for US citizens, resident aliens, and nonresident aliens. Guides users through the entire IRS filing workflow: determining filer t

• 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
• Does not say what the result is
• No condition that starts the skill

Structured extraction and cleanup for public, user-authorized web pages. Use when the user wants to collect, clean, summarize, or transform content from accessible pages into reusa

• 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

Generate social media content and publish to all major platforms from one command.

• 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
• Does not say what the result is

Structural parity skeleton for queue-driven orchestration in a workflow context.

• 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
• 10 top-level sections: this looks like several domains in one skill
• Does not say what the result is