context-resume
Reconstructs your full working context when you return to a task after an interruption — meeting, lunch, sleep, weekend, or three-week vacation. Not session restore. Mental state restore. Answers the question every developer asks ten times a week: "Where was I?"
Why use this skill?
Stop losing time remembering where you left off. Context Resume reconstructs your mental model, tasks, and blockers after any project interruption.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jcools1977/context-resumeWhat This Skill Does
Context Resume is a cognitive recovery tool designed specifically for software developers. The average developer is interrupted every 11 minutes, often requiring over 20 minutes to achieve a state of 'deep work' after a break. When you return to a project after hours, days, or weeks, your IDE might open your files, but your mental model is often lost. This skill acts as a memory bridge, reconstructing your project state by analyzing git history, uncommitted changes, stashed work, and file-level metadata. It doesn't just show you what files are open; it tells you what you were thinking, why you made specific technical decisions, which tests were failing, and exactly what your next step should be. It transforms the "Where was I?" panic into an immediate, productive continuation of your workflow.
Installation
To add this capability to your agent, run the following command in your terminal:
clawhub install openclaw/skills/skills/jcools1977/context-resume
Once installed, the skill will initialize on command and index your active repository to build an internal map of your session artifacts.
Use Cases
- Monday Morning Recovery: Re-orient yourself after a weekend away, catching up on the specific logic flaws you were wrestling with on Friday afternoon.
- Project Switching: Context-switch between two different complex features without losing your place in either.
- Returning from PTO: Re-onboard yourself into a codebase after a multi-week absence by having the agent summarize your last known "mental state" and identifying pending blockers.
- Late Night Handoffs: Remind yourself of the specific architectural decisions or temporary "hack" workarounds you left in the code before shutting down for the night.
Example Prompts
- "I'm back from the weekend. What was I working on in this branch, and why was that JPY test failing?"
- "Context resume: I haven't touched this project in two weeks. Give me a summary of my last session and tell me the most critical thing to fix first."
- "Show me the decision log for this feature. Why did I stash that flat tax calculation, and what were the arguments against using it?"
Tips & Limitations
- Quality of Commits: The efficacy of Context Resume is directly proportional to your commit habits. Meaningful commit messages and descriptive stash labels significantly improve the agent's ability to reconstruct your intent.
- Limitations: The agent cannot read your literal thoughts, only the artifacts you leave behind. If you have significant uncommitted changes with no comments or descriptive code structure, the analysis will be based purely on file diffs and timestamps.
- Privacy: This skill performs local analysis of your repository data. Ensure you have the necessary permissions if working in a highly sensitive or confidential codebase.
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-jcools1977-context-resume": {
"enabled": true,
"auto_update": true
}
}
}Tags
Flags: file-read
Related Skills
markdown-knowledge
将本地 Markdown 知识库与 OpenClaw 集成,支持语义检索和上下文注入。仅在用户触发时检索(搜索知识库、查一下知识库等),不主动注入。
calling-agent-squad
Activate a multi-agent team (the Squad) to manage complex projects, business tasks, or development workflows. The squad includes a Manager, Architect, Coder, Reviewer, and Observer. Use when the user wants to "call a squad", "start a project", or "deploy squad" with specialized roles and quality control loops.
context-compressor
Intelligently compress context — conversations, code, logs. Preserve key information while reducing token usage. Auto-detects content type and applies optimal compression.
daily-report-generator
Automatically generate daily/weekly work reports from git commits, calendar events, and task lists. Use when you need to quickly create professional work reports without manual effort.
auto-context
智能上下文卫生检查器。分析当前会话的上下文污染程度 (长对话、主题漂移、噪声累积),建议:continue、/fork、/btw 或新会话。 支持手动触发(/auto-context)和自动触发(响应层实现)。 基于 ArXiv 论文和认知心理学研究的多维度评估体系。