Skill reviews

Generate images, videos, and audio/music via Lovart AI. Also manages Lovart projects, threads (conversation history), and user settings. Trigger on: (1) any visual or audio creatio

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 top-level sections: this looks like several domains in one skill
• Frontmatter name (lovart-api) differs from the folder (lovart-skill)

Buy, sell, and launch tokens on Pump.fun using the PumpPortal API

• 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 (5 tags): a typed call is more reliable
• Does not say what the result is

Triages symptoms, reads lab results and medication risks, and says how urgent something is: emergency now, seen today, or safe to watch. Use when someone describes chest pain, a he

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

Agent-controlled memory plugin for OpenClaw with confidence scoring, decay, and semantic search. The agent decides WHEN to store/retrieve memories — no auto-capture noise. v2 uses

• 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

Be the COO with process design, organizational scaling, cross-functional execution, and operational excellence.

• 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

Create, list, update, and record Fulcra annotations through the Fulcra Life API. Use when a user asks to log an annotation, create an annotation button/definition, record a moment/

• 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 response is described with custom markup (5 tags): a typed call is more reliable

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use for solution decks, presales/sales pitches, client proposals, pitch decks, te

• References files that are not bundled: reference/viewport-and-base.css, assets/logo_round.png
• 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

Smart auto-updater with AI-powered impact assessment. Checks updates, analyzes changes, evaluates system impact, and decides whether to auto-update or just report. Perfect for hand

• 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

What should we do? Smart activity discovery with live weather, local movie showtimes, streaming recommendations, game library matching, group profiles, routines & traditions, favor

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 23 top-level sections: this looks like several domains in one skill
• No condition that starts the skill

Self-sovereign EVM wallet for AI agents. Use when the user wants to create a crypto wallet, check balances, send ETH or ERC20 tokens, swap tokens, or interact with smart contracts.

• 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

Acts as a chief technology officer: architecture calls, build vs buy, hiring and team scaling, tech debt, engineering metrics. Use when making technical strategy decisions or advis

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 14 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

Save notes to Flomo via the Flomo inbox webhook. Use when the user says "save to flomo", "记录到 flomo", "flomo note", or asks to store a note in flomo.

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

Writes, debugs, and refactors Terraform — HCL and modules, plan and apply failures, state surgery, drift, and provider pinning. Use when writing or reviewing HCL, when terraform pl

• 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 process needs to start

Microsoft SharePoint and OneDrive integration with managed OAuth. Manage sites, lists, libraries, files, folders, permissions, content types, and SharePoint operations via Microsof

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

Audit-ready decision artifacts for LLM outputs — assumptions, risks, recommendation, and review gating (schema-valid JSON).

• References files that are not bundled: examples/*.md
• 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

• 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

Track agent session costs, file changes, and git commits with CostHQ. Enforces budget limits, tracks local models, and provides Enterprise SOC2 audit trails via a web dashboard. v3

• 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

Portfolio risk management and analytics. Use when user asks to calculate VaR, run Monte Carlo, stress test, optimize with Risk Parity / Calmar / Black-Litterman, run pre-trade chec

• 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

This skill should be used when the user wants to read, analyze, or work with CAD DWG/DXF drawing files. Trigger phrases include: DWG, DXF, CAD drawing, drawing analysis, layer, blo

• References files that are not bundled: assets/.setup_done
• 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

Semrush SEO integration with API key authentication. Analyze backlinks, keyword rankings, competitor domains, traffic metrics, and SEO data across organic and paid search channels.

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

Bambu Lab 3D printer control and automation. Activate when user mentions: printer status, 3D printing, slice, analyze model, generate 3D, AMS filament, print monitor, Bambu Lab, or

• 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 response is described with custom markup (3 tags): a typed call is more reliable

Remember-this trigger: memory updates + recall for preferences, goals, boundaries, prior work, decisions, dates, and todos. Use whenever user asks to remember, continue previous co

• References files that are not bundled: references/promotion-checklist.md, references/profile-schema.md
• 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

Draft, publish, and manage posts on X (Twitter), inspect timelines, manage profiles, and automate social media workflows via the X API. Use this skill when users want to post tweet

• 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

Design better OpenClaw HEARTBEAT.md files with adaptive cadence, safe checks, and cron handoffs for precise schedules.

• 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