context-compression-claude-codeUse this skill whenever the conversation context is getting long, when a user asks to "compress", "summarize", or "clean up" the conversation, or when you de...
Install via ClawdBot CLI:
clawdbot install lizlzzzz/context-compression-claude-codeGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 7, 2026
In task-oriented scenarios where goals span multiple sessions, the agent compresses completed steps while preserving incomplete tasks and key decisions. This prevents context window overflow in extended coding or project management sessions, ensuring continuity.
For chat-oriented support, the agent discards small talk and acknowledgments, but retains user preferences and unresolved issues. This keeps the context lean and focused on actionable information, improving response efficiency.
In research-oriented conversations, the agent keeps conclusions and sources, compresses procedural discussions. This is ideal for analysts gathering data over time, ensuring key findings remain accessible without clutter.
In multi-user group chats, the agent aggressively discards irrelevant messages and retains only directly relevant content. This reduces noise and maintains focus on the user's active queries or tasks.
Offer the compression skill as a premium add-on for AI assistants, charging a monthly fee per user. Revenue is generated from recurring subscriptions based on usage tiers or number of active sessions.
Provide context compression as an API endpoint, billing per compression job or per token processed. This appeals to developers integrating the skill into their own applications.
License the full compression system to enterprises for internal AI tools, with custom retention policies and priority support. Revenue comes from annual licensing fees.
💬 Integration Tip
To integrate, configure the PreCompact hook in your agent's settings and map the tiered classification to your conversation history format. Test with sample long chats to calibrate compression thresholds.
Scored May 7, 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.