Claudeshrink

Automatically compress large natural text or log files before processing. Trigger when the user pastes massive text blobs, or asks to analyze a large file (logs, docs, transcripts), or provides a prompt that is too large for the context window. DO NOT trigger on source code files or structural data (JSON, XML).

5 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add g-akshay/ClaudeShrink --skill claudeshrink
Manual install
git clone --depth 1 https://github.com/g-akshay/ClaudeShrink.git /tmp/ClaudeShrink
mkdir -p ~/.claude/skills
cp -r /tmp/ClaudeShrink/. ~/.claude/skills/claudeshrink

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Overview

ClaudeShrink compresses large inputs using [LLMLingua](https://github.com/microsoft/LLMLingua) (gpt2) before you reason over them. This preserves semantic content while dramatically reducing token usage.

The compressor lives at: `~/.claude/skills/ClaudeShrink/scripts/compressor.py`
It runs inside an isolated venv at: `~/.claude/skills/ClaudeShrink/.venv`

---

## When to Use

- User pastes a large block of text, logs, or a document (>~8000 chars / ~2000 tokens)
- User asks to analyze, summarize, or reason over a large file on disk
- User's prompt is very long and would benefit from compression before reasoning
- User explicitly says "use ClaudeShrink" or "compress this"

---

## Instructions

Follow these steps in order every time this skill is triggered:

1. **Self-check: verify the environment is installed.** Run:
   ```bash
   test -f ~/.claude/skills/ClaudeShrink/.venv/bin/python && echo "ready" || echo "not_installed"
   ```
   - If output is `ready`, proceed to step 2.
   - If output is `not_installed`, run the installer first:
     ```bash
     bash ~/.claude/skills/ClaudeShrink/install.sh
     ```
     If `install.sh` is missing (skill was added without cloning), fetch and run it:
     ```bash
     curl -fsSL https://raw.githubusercontent.com/g-akshay/ClaudeShrink/main/install.sh | bash
     ```
     Wait for it to complete, then proceed to step 2.

2. **Identify the input source** — is it a file path, raw pasted text, or a prompt?
Read the full skill on GitHub

Details

Skill name
claudeshrink
Repository
g-akshay/ClaudeShrink
License
MIT
Repo updated
25 April 2026

FAQ

What does the Claudeshrink skill do?

Automatically compress large natural text or log files before processing. Trigger when the user pastes massive text blobs, or asks to analyze a large file (logs, docs, transcripts), or provides a prompt that is too large for the context window. DO NOT trigger on source code files or structural data (JSON, XML).

How do I install the Claudeshrink skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add g-akshay/ClaudeShrink --skill claudeshrink. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Claudeshrink popular?

It lives in g-akshay/ClaudeShrink, which has 5 GitHub stars and 1 forks.

Related skills

Eforest Agent Skills

5

eforest-finance/eforest-agent-skills

eForest symbol and forest NFT operations for agent workflows.

AI, LLMs & Agents

Claude Design Idea to Ready

5

chohra-med/claude_design_skill

Take a UI from a one-line idea to on-brand, shippable design with Claude, in the correct order — brand foundation first, then components, screens, interactions, accessibility, and only then generation via /design. Use whenever someone wants to design, redesign, or generate a screen, page, component, or onboarding flow and wants the output to match an existing brand instead of looking like generic AI UI. Triggers on "design this screen", "build a UI for", "make this on-brand", "redesign", "generate a page/component", "use /design", or any task that will produce visual interface.

AI, LLMs & Agents

Filemaker AI Vocabulary

5

andykear/FileMaker-AI-vocabulary

Use this skill whenever Claude needs to name, call, or validate a FileMaker function or script step — writing a calculation, writing a script, checking whether a function or script step exists, checking parameter order or count, or checking whether a script step is supported on a given platform (Pro, Go, WebDirect, Server, Cloud, Data API, Custom Web Publishing). Trigger any time FileMaker calculation syntax or script step syntax is being written or reviewed. Do not name or call a FileMaker function or script step from memory alone — check the reference files first.

AI, LLMs & Agents

Awaken Agent Skills

5

Awaken-Finance/awaken-agent-skills

Awaken DEX trading and market data operations for agents.

AI, LLMs & Agents

Ghidra Iterative Re

5

GeReV/ghidra-iterative-re

Use when reverse-engineering a game (or any binary) in Ghidra via MCP or PyGhidra - establishes the apply-cascade-verify loop, the SourceType trust model that stops an agent corroborating its own guesses, invariant bracketing against Ghidra's silent collateral damage, and the game-specific evidence sources worth sweeping before any analysis.

AI, LLMs & Agents

AI Repo Safety

5

letya999/ai-repo-safety-skill

Git-hook-backed secret and supply-chain gates for AI-coded repos. Use when initializing a repo, handling a leaked secret, making a public release, or when the user names this skill. Do not load just because a coding session started.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.