continuity-kernelOpenClaw continuity kernel for fail-open llm_input injection, deterministic runtime contracts, and shadow-mode eval receipts.
Install via ClawdBot CLI:
clawdbot install tkuehnl/continuity-kernelGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
https://github.com/cacheforge-ai/cacheforge-skillsAI Analysis
The skill's primary functions are local file operations, testing, and generating artifacts, with no evidence of sending user data to external servers or containing hidden malicious instructions. The only external reference is to a public GitHub repository for documentation, which is consistent with the skill's stated purpose and does not constitute a privacy risk.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Use continuity-kernel to inject bounded context from past interactions into LLM inputs, ensuring consistent support across sessions. Persist user session state with deterministic contracts for reliable issue tracking, and run shadow-mode evals to monitor response quality without affecting live operations.
Employ this skill to maintain continuity in patient data updates across medical sessions, with fail-open behavior to prevent system crashes during storage errors. Generate reproducible runtime proofs for compliance audits and use shadow evals to assess data handling robustness under simulated perturbations.
Integrate continuity-kernel to inject historical trading context into decision-making models, ensuring deterministic state persistence for strategy tracking. Utilize shadow-mode evals to test bot performance under market noise scenarios, appending quality snapshots for performance reviews.
Apply the skill to persist student progress and learning paths with zero-config SQLite storage, enabling seamless context injection for personalized content. Run shadow evals to evaluate platform reliability under data deletion perturbations, ensuring robust educational delivery.
Use continuity-kernel to maintain context across lengthy legal document reviews, with deterministic contracts for case state persistence. Implement fail-open logic to handle storage errors gracefully and generate audit receipts for regulatory compliance through shadow-mode evaluations.
Offer continuity-kernel as a cloud-based service with tiered subscriptions, providing enhanced reliability and audit features for AI agents. Revenue is generated through monthly fees based on usage levels and premium support for custom integrations.
Sell enterprise licenses to organizations requiring robust audit trails and deterministic runtime proofs for regulatory compliance. Revenue comes from one-time license fees and annual maintenance contracts for updates and technical support.
Provide consulting services to integrate continuity-kernel into existing AI systems, tailoring it for specific industry needs like healthcare or finance. Revenue is generated through project-based fees and ongoing optimization contracts.
💬 Integration Tip
Ensure Python3 is installed and set the CONTINUITY_KERNEL_DB_PATH environment variable to customize storage location, avoiding :memory: for production to maintain persistence.
Scored Jun 19, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.