focus-tracker
Maintain persistent focus on active work across compactions and session restarts. Use when starting a multi-step project, when resuming after compaction, when the user says "we're working on X", or when you notice you've lost track of what was being done. Also use proactively at session start to check if there's unfinished work. Prevents the agent from forgetting mid-project context, drifting between topics, or asking "what were we doing?" after a compaction.
Why use this skill?
Maintain persistent project state across AI sessions with the focus-tracker skill. Prevent context loss and track multi-step projects automatically.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/crewhaus/focus-trackerWhat This Skill Does
The focus-tracker skill is a robust state-persistence mechanism designed to maintain continuity across session restarts and context compactions. By maintaining a structured FOCUS.md file in the workspace root, this skill acts as a living document of the agent's current project, progress, and immediate next steps. It eliminates the "amnesia" common in long-running AI sessions by providing a standardized roadmap that the agent updates in real-time, ensuring that work is never lost, even if memory buffers are cleared or sessions expire.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/crewhaus/focus-tracker
Use Cases
- Project Continuity: Ideal for multi-day coding projects where you need the agent to resume exactly where it left off after an overnight break.
- Complex Task Management: When breaking down a large task into smaller steps, the focus-tracker keeps the agent from drifting off-topic or losing sight of the primary objective.
- Compaction Management: Serves as a vital "anchor" when system memory is reset, providing an immediate context retrieval point for the agent.
- Proactive Status Check: Use this when you need to confirm what is currently blocked or what the last completed milestone was in a long development cycle.
Example Prompts
- "We're going to build a new authentication module. Can you initialize a focus tracker for this and break it down into steps?"
- "I'm coming back to this project after a few days off. Can you read the FOCUS.md and tell me what the next step is?"
- "That task is finished. Please update our progress, mark it as done in the focus tracker, and let me know what the next blocker is."
Tips & Limitations
- Keep it Succinct: The
FOCUS.mdis meant to be a high-speed resume point. Avoid pasting logs or full code snippets inside it; keep it under 50 lines to ensure the agent reads it efficiently. - Sacred State: Always treat the "Active State" section with care. If the agent fails to update this section before a session ends, the continuity benefits are lost.
- Archive Regularly: Remember to clear out old
FOCUS.mdfiles by appending them toFOCUS-LOG.md. This prevents stale data from cluttering the workspace and confusing the agent during future tasks. - One Task Only: The skill is designed for a single primary focus. If you attempt to track multiple unrelated projects simultaneously, the agent's ability to maintain a clear "next action" will diminish.
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-crewhaus-focus-tracker": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read
Related Skills
crewhaus
Quick startup idea evaluation from your terminal. Score ideas on 3 dimensions, run deeper scans with real competitor data and risk assessment. A structured thinking tool for founders — not an oracle.
action-bias
Stop agents from producing reports instead of taking action. Restructure prompts, cron jobs, and agent shifts so they DO things — send emails, post content, make API calls, push code — instead of writing plans about doing things. Use when: agents keep outputting strategy docs instead of executing, sub-agent sessions produce reports nobody reads, you notice your crew is busy but nothing external is happening, heartbeat/shift results are all 'here's what we should do' with no proof of doing it, or you want to audit whether your agents are actually shipping.
workspace-trash
Soft-delete protection for workspace files. Intercept file deletions and move them to a recoverable trash instead of permanent removal. Use when deleting, removing, or cleaning up files in the workspace. Triggers on /trash, /trash:view, /trash:empty, /trash:restore, or any file deletion request. Also use when the agent needs to rm/delete/remove any file — always trash instead of permanently deleting.
crew-school
Structured learning system for AI agent crews. Design curricula, run research sessions, track progress, and prevent common failure modes (lazy output, planning-without-executing). Use when setting up agent learning, running training sessions, auditing knowledge gaps, or building a curriculum for specialized agents. Works for single agents or multi-agent crews.
recall
Teaches agents to check before they guess. Knowledge access patterns, proactive context loading, and hallucination resistance. Install before taking the Knowledge-Driven Agent certification.