longrunning-agentEnables AI agents to work on long-running projects across multiple sessions. Use when starting complex projects, resuming work on existing projects, managing...
Install via ClawdBot CLI:
clawdbot install YonghaoZhao722/longrunning-agentThis skill enables AI agents to work on long-running projects across multiple sessions.
The longrunning-agent skill provides a structured workflow for:
# Create project directory
mkdir my-project && cd my-project
# Initialize workflow files
claude -p "Initialize this project using the longrunning-agent workflow"
The skill expects these files in the project directory:
CLAUDE.md - Project instructions and workflow guidetask.json - Task list with priorities and dependenciesprogress.txt - Log of work completedinit.sh - Environment setup script (optional){
"tasks": [
{
"id": "task-1",
"description": "Set up project structure",
"priority": 1,
"dependencies": [],
"passes": false
},
{
"id": "task-2",
"description": "Implement core features",
"priority": 2,
"dependencies": ["task-1"],
"passes": false
}
]
}
[2024-01-15 10:30:00] Started session
[2024-01-15 10:35:00] Completed task: Set up project structure
[2024-01-15 10:40:00] Milestone: Core features implemented
progress.txt for recent workpasses: false task with met dependenciesinit.sh if neededprogress.txtpasses: true in task.jsonThis skill integrates with the Agent Workflow Web App:
Templates for workflow files are in the templates/ directory:
CLAUDE.md.tpl - Project templatetask.json.tpl - Task list templateGenerated Mar 1, 2026
A development team uses the skill to manage a multi-month software project, breaking it into atomic tasks with dependencies. It ensures continuity across developer sessions, tracks progress incrementally, and integrates with version control for atomic commits.
A researcher employs the skill to structure the writing of a complex paper over weeks, with tasks for literature review, data analysis, drafting sections, and revisions. It helps maintain focus, track milestones, and resume work seamlessly after breaks.
A marketing team utilizes the skill to plan and execute a long-running campaign, with tasks for content creation, social media scheduling, and performance analysis. It enables progress tracking across team sessions and ensures dependencies like approvals are met.
An event planner uses the skill to organize a large conference over several months, managing tasks for venue booking, speaker coordination, and logistics. It facilitates incremental progress, dependency management, and session-based updates for team collaboration.
A product manager applies the skill to oversee a product launch, with tasks for market research, prototype development, and go-to-market planning. It supports atomic task completion, progress logging, and integration with web tools for real-time updates.
Offer the skill as part of a subscription-based platform for teams, providing cloud sync, collaboration features, and analytics. Revenue comes from monthly or annual fees per user, with tiers for small to enterprise teams.
Provide a free basic version of the skill for individual users, with paid upgrades for advanced features like AI-assisted task generation, integration with third-party tools, and priority support. Revenue is generated from one-time purchases or in-app upgrades.
Sell enterprise licenses to large organizations, including customization, on-premise deployment, and dedicated support. Revenue is derived from upfront licensing fees, annual maintenance contracts, and consulting services for workflow integration.
💬 Integration Tip
Integrate the skill with existing project management tools via APIs to sync tasks and progress, ensuring seamless adoption without disrupting current workflows.
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