context-recovery
Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels.
Why use this skill?
Keep your OpenClaw AI agent on track with context-recovery. Automatically restore session history, thread context, and project tasks across all supported communication platforms.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jdrhyne/context-recoveryWhat This Skill Does
The context-recovery skill acts as the short-term memory bridge for your OpenClaw AI agent. When long-running sessions exceed token limits or undergo compaction—often signaled by a <summary> tag—your agent may lose track of specific technical details or ongoing tasks. This skill proactively scans your chat history across platforms like Slack, Discord, Telegram, and Signal to reconstruct the missing narrative. It intelligently fetches recent message history, prioritizes thread-based conversations, and parses for specific project identifiers, URLs, and pending tasks to restore the continuity of your work without needing manual reminders or re-inputting documentation.
Installation
To add this capability to your agent, use the OpenClaw CLI tool to fetch the package from the official registry:
clawhub install openclaw/skills/skills/jdrhyne/context-recovery
Once installed, the skill will register itself to monitor for compaction signals and user requests automatically. No further configuration is required to begin recovery operations within supported channels.
Use Cases
- Resuming Work: Use this when returning to a project after a multi-hour gap where the agent has archived the previous conversation state.
- Compaction Recovery: Triggered automatically when the agent reports a summary of the session instead of the full conversation history.
- Clarifying Ambiguity: Useful when you refer to "that PR" or "the branch" and the agent needs to link those keywords back to the specific channel activity.
- Multi-Threaded Coordination: Ideal for switching back to a specific Slack thread or Discord conversation where you were finalizing code or planning deployment steps.
Example Prompts
- "What were we working on just before you summarized the session?"
- "Continue the refactoring process for the PR we were discussing yesterday."
- "Do you remember the specific API endpoint we decided on in this thread?"
Tips & Limitations
- Token Budget: The skill enforces a strict 100-message limit per recovery operation to ensure the context remains concise and cost-effective.
- Privacy: The skill operates strictly within the session and channel API history. It does not perform unauthorized local file system scans or interact with external data services.
- Best Practices: If context is still unclear, try pointing the agent to a specific timeframe; although the skill is adaptive, it works best when the relevant messages have occurred within the last few hours of activity.
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-jdrhyne-context-recovery": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api
Related Skills
nutrient-openclaw
OpenClaw-native PDF/document processing skill for Nutrient DWS. Best for OpenClaw users who need PDF conversion, OCR, text/table extraction, PII redaction, watermarking, digital signatures, and API credit checks via built-in `nutrient_*` tools. Triggers on OpenClaw tool names (`nutrient_convert_to_pdf`, `nutrient_extract_text`, etc.), "OpenClaw plugin", "Nutrient OpenClaw", and document-processing requests in OpenClaw chats. For non-OpenClaw environments, use the Universal Nutrient Document Processing skill instead.
todo-tracker
Persistent TODO scratch pad for tracking tasks across sessions. Use when user says "add to TODO", "what's on the TODO", "mark X done", "show TODO list", "remove from TODO", or asks about pending tasks. Also triggers on heartbeat to remind about stale items.
sysadmin-toolbox
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
munger-observer
Daily wisdom review applying Charlie Munger's mental models to your work and thinking. Use when asked to review decisions, analyze thinking patterns, detect biases, apply mental models, do a "Munger review", or run the Munger Observer. Triggers on scheduled daily reviews or manual requests like "run munger observer", "review my thinking", "check for blind spots", or "apply mental models".
jira
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.