session-watchdogMonitors session context usage and saves checkpoints when approaching limits to prevent data loss before compaction or long tasks.
Install via ClawdBot CLI:
clawdbot install xbillwatsonx/session-watchdogGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 20, 2026
A team of writers or researchers uses the AI to draft extensive documents, requiring preservation of narrative flow and key decisions across multiple sessions. The watchdog ensures critical plot points or research findings are saved before context compaction disrupts continuity.
Developers rely on the AI for coding assistance, bug tracking, and task prioritization over lengthy conversations. The skill proactively saves checkpoints of code changes, unresolved issues, and project configurations to prevent loss during context limits.
Legal professionals use the AI to analyze case details, draft documents, and track pending tasks. The watchdog monitors context to save essential decisions, unresolved legal points, and file modifications before compaction, ensuring no critical information is lost.
Support agents engage in extended conversations with complex customer issues, requiring context on past interactions and pending resolutions. The skill saves checkpoints of important context and unresolved issues to maintain service quality despite session limits.
Researchers collaborate with the AI to synthesize data, draft papers, and manage literature reviews over long sessions. The watchdog preserves key findings, pending analyses, and project states to avoid disruption from context compaction.
Offer the session watchdog as a premium feature in a monthly subscription plan, targeting professionals who rely on extended AI interactions. Revenue is generated through tiered pricing based on usage limits and advanced monitoring capabilities.
License the skill to businesses for integration into their internal AI tools, providing enhanced session management for collaborative workflows. Revenue comes from one-time licensing fees or annual contracts with support and updates.
Provide basic session monitoring for free users, with advanced features like automated checkpointing and priority alerts available as paid upgrades. Revenue is generated through in-app purchases or upgrade subscriptions.
💬 Integration Tip
Integrate the skill by setting up periodic context checks and user alerts, ensuring it triggers automatically based on token thresholds without manual intervention.
Scored Apr 19, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCER...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括:(1) 滑动窗口式短期记忆,(2) 自动摘要生成中期记忆,(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Store secrets, long-term memory, daily logs, and anything custom in your Convex backend instead of local files