AI Agent Workflow Collection

Zero-knowledge secrets management via PassBox — store, retrieve, rotate, and inject credentials securely.

Assist with Aave lending, borrowing, liquidations, and risk management across chains.

View, create, cancel, bid, and claim Aavegotchi GBM auctions on Base mainnet (8453). Subgraph-first discovery (Goldsky), with onchain verification + execution via Foundry cast. Safety-first: DRYRUN defaults to 1 (simulate with cast call; only broadcast with cast send when DRYRUN=0 and explicitly instructed).

Simple time display for Abby. Use when you need to know the current time or count down to a specific time.

Add abstracts to .bib file entries by searching academic databases (arXiv, Semantic Scholar, CrossRef) with browser fallback.

AI accounting helper. Bookkeeping, tax preparation, financial analysis. No API keys needed. $2 FREE credits to start. Pay-as-you-go via SkillBoss.

Generate and edit images using the AceData Nano Banana API. Supports models like nano-banana-2, custom aspect ratios (default 16:9), and resolutions (default 2K). Handles batch generation and image-to-image (edit) tasks with local files. Use when the user wants to generate or edit high-quality images via Nano Banana.

Generate diverse, engaging ad prompts for any product or brand across 20+ creative styles and 10 categories. Use when user needs advertisement concepts, marketing prompts, or creative marketing content generation.

Routes LLM requests to a local model first (Ollama, LM Studio, llamafile), validates the response quality, and escalates to cloud only when the local result fails. Tracks local vs escalated vs cloud outcomes in a persistent dashboard. Use when: (1) user asks to run a task with a local model first, (2) user wants to reduce cloud API costs or keep requests private, (3) user wants post-outcome quality validation before committing to a local result, (4) user asks to see token savings or the routing dashboard, (5) any request where local-vs-cloud routing should be decided automatically with a quality gate. Supports Ollama, LM Studio, and llamafile as local providers.

Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.

Strict semantic firewall with Human-in-the-Loop execution authorization. Airgaps external data and enforces zero-trust environment.

Complete community building, engagement, and monetization system. From zero to thriving community — launch strategy, member engagement loops, content programming, moderation frameworks, growth tactics, monetization models, and health metrics. Works for Discord, Slack, Telegram, Circle, forums, or any platform.

Design, build, optimize, and scale sales funnels for any business model. Use when mapping customer journeys, diagnosing conversion leaks, building landing pages, designing email sequences, setting up attribution, A/B testing funnel stages, or scaling paid acquisition. Covers B2B, B2C, SaaS, services, ecommerce, and hybrid funnels. Trigger on: sales funnel, conversion funnel, funnel optimization, lead funnel, why aren't people buying, funnel audit, landing page, email sequence, conversion rate, customer journey, pipeline conversion, funnel metrics.

Complete strategic thinking & mental models toolkit. 50+ decision frameworks organized by situation type — business strategy, investing, hiring, pricing, risk, negotiations, product, and personal life. Use when facing any important decision, analyzing a situation, or building a decision culture. Includes scoring rubrics, templates, anti-patterns, and real-world application guides.

Inter-agent communication via shared JSON file. Use when two or more OpenClaw instances need to exchange messages, coordinate, or pass information. Works across different machines via SSH or shared storage.

Multi-agent UX for OpenClaw Control UI — agent selector, per-agent sessions, session history viewer with search, agent-filtered Sessions tab with friendly names, Create…

Deploy a new isolated OpenClaw agent with its own Telegram bot, workspace, and session storage. Use when user asks to create a new agent, add a new bot, or set up multi-agent routing. Uses openclaw config set for safe config updates with doctor validation and auto-rollback.

Advanced repository analysis and refactoring guide. Identifies technical debt and architectural anti-patterns using AI reasoning.

Invisible privacy guardian for agent workspaces. Automatically intercepts outbound actions (git push, skill publish, file sharing) and checks for sensitive data leaks. Users don't need to know commands — the agent handles everything silently. Activate on: ANY outbound action (push, publish, share, sync, send files), or when user asks \"检查隐私\", \"有没有敏感信息\", \"privacy check\", \"scan for secrets\".

Agents can sign plugins, rotate credentials without losing identity, and publicly attest to behavior.

Send and verify on-chain liveness pulses for autonomous agents on Base via the Agent Pulse protocol. Use when you need to: (1) prove an agent is alive by sending a pulse, (2) check any agent's liveness status or streak, (3) monitor multiple agents, (4) view the global pulse feed, (5) auto-configure wallet and PULSE balance, (6) run scheduled heartbeat pulses, or (7) read protocol health and config. Supports both API and direct on-chain (cast) modes.

Security audit and validation tools for the Agent Skills ecosystem. Scan skill packages for common vulnerabilities like credential leaks, unauthorized file access, and Git history secrets. Use when you need to audit skills for security before installation, validate skill packages against Agent Skills standards, or ensure your skills follow best practices.

Design compelling AI agent personalities with structured SOUL.md templates — tone, rules, expertise, and response…

Enable and configure Agent Synthesizer for OpenClaw to improve autonomy and execution throughput. Use when a user asks to install, set up, troubleshoot, or optimize Agent Synthesizer using https://github.com/rylena/agent-synth, or when they want their OpenClaw agent to work faster/better via that repository.