Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.
Data sourced from ClawHub. View on ClawSkills
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install context-compactorOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install context-compactorβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/context-compactor/π‘Extract and place the folder at the path above, then restart your agent.
Category
πDocuments & NotesPlatforms
What Context Compactor can do for your AI workflow
Token-based context compaction directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
Trusted by 1,593+ developers worldwide
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing Context Compactor
Help me get started with Context Compactor
Explains what Context Compactor does, walks through the setup, and runs a quick demo based on your current project
Use Context Compactor to token-based context compaction for local models (MLX, llama
Invokes Context Compactor with the right parameters and returns the result directly in the conversation
What can I do with Context Compactor in my documents & notes workflow?
Lists the top use cases for Context Compactor, with example commands for each scenario
Guides & tutorials for AI skills
10 Fresh GitHub Agent Skills Added in June 2026
A hand-checked shortlist of recently updated GitHub agent skills that were not already in our catalog, excluding marketplaces, awesome lists, managers, and generic skill directories.
The 7 AI Skills Every Software Developer Should Have Installed in 2026
After testing dozens of developer-focused AI skills, these are the seven that have proven genuinely useful across different tech stacks and workflows β not just impressive demos, but tools that hold up under daily use.
Context Compactor extends your AI assistant with the ability to token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits. Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using Context Compactor as its underlying capability.
Context Compactor works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) β an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install Context Compactor once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.
Context Compactor installs like any other MCP skill: drop the folder into `~/.claude/skills/context-compactor/` for global access, or `.claude/skills/context-compactor/` to keep it scoped to one project. After a quick restart of Claude, you can trigger it explicitly with `/context-compactor`, or let the AI decide when it's the right tool for your request.
Context Compactor has been installed 1,593 times, making it one of the more actively used skills in the Documents & Notes category. The install rate suggests it solves a real, recurring need rather than a niche edge case. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/context-compactor/ for personal use (all projects), or .claude/skills/context-compactor/ for project-specific use. Restart your AI client, then invoke with /context-compactor or let the AI discover it automatically.
Context Compactor supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
Context Compactor is free to install. Check the repository for licensing information.
Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.
Context7 MCP
Context7 MCP - Intelligent documentation search and context for any library
Context Optimizer
Advanced context management with auto-compaction and dynamic context optimization for DeepSeek's 64k context window. Features intelligent compaction (merging, summarizing, extracting), query-aware relevance scoring, and hierarchical memory system with context archive. Logs optimization events to chat.
Context Recovery
Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram,...
Automate my documents & notes tasks using Context Compactor
Identifies repetitive steps in your workflow and sets up Context Compactor to handle them automatically
Context Compactor is categorized under Documents & Notes. These skills help AI agents perform specialized tasks in this domain.