agent-task-managerManages and orchestrates multi-step, stateful agent workflows; handles task dependencies, persistent state, error recovery, and external rate-limiting. Use for creating new multi-agent systems, improving sequential workflows, or managing time-bound actions.
Install via ClawdBot CLI:
clawdbot install dobbybud/agent-task-managerThis skill provides the structure and primitives for building resilient, complex, and professional multi-agent systems within the OpenClaw environment. It transforms simple scripts into production-ready workflows.
molt_task.py to manage state in task_state.json.scripts/cooldown.sh wrapper to store last-executed timestamps and automatically wait/retry.ContractAuditor, FinancialAnalyst).FinancialAuditContractAuditor (Input: Contract Address, Output: Contract Safety Score)FinancialAnalyst (Input: Contract Address + Safety Score, Output: Trust Score)MoltbookPost (Dependent on final Trust Score; subject to Rate Limit).molt_task.py: Python class for task state management.cooldown.sh: Shell wrapper for managing rate-limited executions.workflow_schema.md: JSON schema for defining complex task dependencies.rate_limit_patterns.md: Guide to handling common API rate limits (e.g., Moltbook, Helius).Generated Mar 1, 2026
A multi-agent system sequentially audits smart contract code, analyzes financial tokenomics, and publishes risk assessment reports to community platforms. The task manager ensures the audit completes even if sessions reset and respects API rate limits when posting findings.
Orchestrates data collection from multiple APIs, analysis by specialized agents (e.g., for market trends, company fundamentals), and compilation into a formatted report. Handles dependencies where raw data must be fetched before analysis can begin.
Manages a sequence of checks across legal documents, transaction records, and identity verification systems. Different agent roles handle specific compliance rules, with the task manager ensuring all steps complete in order and state is saved for audit trails.
Coordinates web scraping, API queries, and database lookups across various sources to compile research on a topic. Manages rate limits for external sites and sequences tasks so data is cleaned and cross-referenced before final synthesis.
Orchestrates identity verification, credit checks, document signing, and account setup in a defined workflow. Uses persistent state to resume onboarding if interrupted and manages API call limits to external services like credit bureaus.
Sell subscription access to pre-built multi-agent workflows (e.g., for audits, compliance) or custom workflow development. Clients use the platform to automate complex, stateful business processes without building from scratch.
Offer consulting and development services to design, build, and maintain bespoke multi-agent systems for enterprises. Use the skill as a foundation to deliver resilient, production-ready workflows tailored to client needs.
Create a platform where developers can sell modular agent roles (e.g., ContractAuditor, FinancialAnalyst) that plug into the task manager. Users assemble workflows from pre-built, vetted components.
💬 Integration Tip
Start by defining your workflow as a DAG in the provided schema, then implement each node as a modular agent; use the cooldown wrapper for any external API calls to avoid rate limit issues.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection