openclaw-continuityStructured continuity and follow-up skill for OpenClaw agents. Use when an agent needs to decide whether natural user dialogue should stay as casual chat, be...
Install via ClawdBot CLI:
clawdbot install redwakame/openclaw-continuityGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
exec(Calls external URL not in known-safe list
https://github.com/AdaBot666/openclaw-continuityUses known external API (expected, informational)
api.telegram.orgAI Analysis
The skill definition describes a legitimate continuity/follow-up management system with no evidence of hidden malicious instructions, credential harvesting, or obfuscation. The external URL is the skill's declared public GitHub homepage, which is expected and not a data exfiltration endpoint. The 'UNSAFE_SHELL' signal likely refers to internal script execution for skill operation, not arbitrary user command execution.
Generated Oct 3, 2026
A mental health chatbot uses the skill to track when a user mentions a difficult upcoming event (e.g., an interview or anniversary) and automatically stages a follow-up check-in after the event. The skill maintains causal memory of the user's emotional state, schedules a cooldown-aware prompt, and suppresses follow-ups during quiet hours or sleep times. It ensures the agent doesn't forget the thread while avoiding intrusive nudges.
An AI support agent for an e-commerce platform uses the skill to park unresolved customer issues and track delegated tasks (e.g., 'I'll check with the warehouse and get back to you'). When the user returns to a new session, the skill reattaches the pending follow-up, respects cooldown periods to avoid over-messaging, and closes the loop with a concise daily-memory trace.
A personal AI assistant helps users manage tasks and reminders by classifying natural conversation into casual chat, staged memory, or tracked follow-up. It remembers delegated tasks like 'remind me to review the budget next week' and uses time-aware continuity guards to deliver a timely nudge. The skill also supports /new carryover to let the user pick which unfinished thread to continue.
An online tutoring bot tracks a student's watchful state (e.g., struggling with a math concept) and schedules follow-up practice without overwhelming them. The skill promotes candidate topics to incidents and hooks, applies routine-aware wording (e.g., adapting to the student's study schedule), and ensures follow-ups only appear when relevant. It also preserves voice/image discussion style preferences for multimodal learners.
A post-discharge care bot monitors patient-reported symptoms and uses the skill to stage a follow-up if a sensitive event (e.g., new pain) is mentioned. It respects sleep/rest suppress and quiet-hours behavior to avoid disturbing patients at night, and maintains an event chain summarizing context before, during, and after the symptom report. The skill helps the agent decide whether to escalate or simply check in later.
The core skill is open-source and free for basic follow-up tracking, while advanced features like multi-turn causal memory, /new carryover, and routine-aware scheduling are locked behind a subscription. This model attracts individual developers and small teams, then upsells to power users who need deeper continuity. Revenue comes from monthly subscriptions (e.g., $9.99/month) and enterprise licensing.
The skill is packaged as an SDK that chatbot platform providers (e.g., customer support, therapy apps) integrate into their own products. The platform pays a per-seat or per-conversation fee based on usage volume. This model scales with the platform's user base and provides recurring revenue through API calls or active users.
The skill's creators offer paid consulting services to help enterprises integrate the continuity layer into their existing AI agents, including custom configuration for industry-specific workflows (e.g., healthcare compliance, e-commerce SLAs). This model targets large organizations that need tailored setups and ongoing support. Revenue comes from one-time integration projects and retainer fees.
💬 Integration Tip
Ensure OPENCLAW_STATE_DIR and OPENCLAW_CONFIG_PATH are set before first run, and validate the config using the provided schema to avoid state corruption. Start with the harness to test routing logic before deploying to production, and keep rhythm/nudge features disabled by default until you understand their impact.
Scored Oct 3, 2026
Audited Apr 19, 2026 · audit v1.0
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in o...
Transcribe YouTube videos to text by extracting captions and subtitles directly from the video URL using yt-dlp without audio processing.
Proactive security monitoring, threat scanning, and auto-remediation for OpenClaw deployments
Create or improve SOUL.md files for OpenClaw agents through guided conversation. Use when designing agent personality, crafting a soul, or saying "help me create a soul". Supports self-improvement.
macOS Gateway 24/7 watchdog with 4-layer health checks and auto-repair. Monitors: L1 process alive, L2 HTTP port, L3 WebSocket communication (1006 detection)...