Planning With Files Manus Workflow
Skill by adisinghstudent
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/adisinghstudent/planning-with-files-manus-workflowWhat This Skill Does
The Planning With Files Manus Workflow skill transforms your AI agent into a highly persistent coding partner by implementing the industry-standard 'three-file' architectural pattern. Originally popularized by the Manus AI agent, this skill moves critical project context out of the volatile AI context window and onto your persistent local storage. By automating the creation and management of task_plan.md, findings.md, and progress.md, the skill ensures your agent never forgets its objectives, research findings, or current state, even across massive context resets or long-running development sessions.
Installation
You can install this skill via the OpenClaw ecosystem or directly through your terminal using the following command:
clawhub install openclaw/skills/skills/adisinghstudent/planning-with-files-manus-workflow
Once installed, the agent will have the necessary directives to maintain the three-file pattern in your project root, ensuring that every task is documented from conceptualization to execution.
Use Cases
This skill is ideal for:
- Complex refactoring projects that span multiple days.
- Large-scale feature development requiring deep research before writing code.
- Maintaining continuity in long-context coding sessions where session timeout is a risk.
- Technical debugging tasks where you need to track findings across multiple experimental runs.
Example Prompts
- "I'm starting a new feature to integrate Stripe payments. Set up the Manus-style planning files for me."
- "I've hit a wall with the current debugging task. Please update findings.md with what we've discovered so far and revise the task_plan.md."
- "Summarize the current project state based on progress.md so I can pick up where we left off yesterday."
Tips & Limitations
- Persistence: Always allow the agent to update the three files; do not manually overwrite them while the agent is running as this can lead to synchronization conflicts.
- Scope: This skill works best in projects with a clear root directory. Avoid using it in temporary scratchpad folders.
- Limitation: The effectiveness relies on your agent's ability to maintain these files consistently. If you notice a file is out of sync, explicitly ask the agent to 'resync project status' using the command
/planning-with-files:statusto re-parse the files and regain alignment.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-adisinghstudent-planning-with-files-manus-workflow": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write
Related Skills
Oh My Openagent Omo
Skill by adisinghstudent
mirofish-offline-simulation
Fully local multi-agent swarm intelligence simulation engine using Neo4j + Ollama for public opinion, market sentiment, and social dynamics prediction.
ghostling-libghostty-terminal
Build minimal terminal emulators using the libghostty-vt C API with Raylib for windowing and rendering
Obra Superpowers Agentic Workflow
Skill by adisinghstudent
fabro-workflow-factory
Skill for using Fabro, the open source AI coding workflow orchestrator that lets you define agent pipelines as Graphviz DOT graphs with human gates, multi-model routing, and cloud sandboxes.