Agent skill
crush
AI-powered CLI tool by Charm for code analysis, diagnostics, and interactive Q&A. Core Scenario: When the user needs intelligent code suggestions, explanations, or fast local development diagnostics.
Install this agent skill to your Project
npx add-skill https://github.com/x-cmd/skill/tree/main/data/x-cmd/crush
SKILL.md
crush - AI Assistant for Code Analysis
crush is an AI-driven tool developed by Charm that provides context-aware suggestions and code explanations, integrating with Language Server Protocol (LSP) for a smooth developer experience.
When to Activate
- When the user wants interactive AI assistance for code analysis.
- When performing fast diagnostics or seeking intelligent suggestions within a project.
- When running single, non-interactive AI prompts for code explanation.
- When the user needs a debugged or YOLO-approved execution of AI commands.
Core Principles & Rules
- API Key Inheritance: Inherits
OPENAI_API_KEYandGEMINI_API_KEYfromx openaiandx geminiconfigurations. - Context Awareness: Best used within a specific project directory (
--cwd) to leverage local code context. - YOLO Mode: Use
-yor--yoloto automatically accept permissions for high-speed interaction.
Additional Scenarios
- Non-Interactive Prompts: Use the
runsubcommand for quick queries. - Debugging: Enable detailed logs with
-dfor troubleshooting AI interactions.
Patterns & Examples
Interactive Session
# Start an interactive AI session for the current project
x crush
Non-Interactive Query
# Ask for a quick code explanation
x crush run "Explain the use of context in Go"
Sandboxed/CWD Execution
# Run crush in a specific project directory with debug logging
x crush -d -c /path/to/project
Checklist
- Ensure relevant AI API keys (OpenAI/Gemini) are set up via their respective x-cmd modules.
- Verify the target directory if using the
--cwdflag. - Confirm if YOLO mode is appropriate for the current task safety.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
pufferlib
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.
fluidsim
Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.
metabolomics-workbench-database
Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.
geniml
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
astropy
Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.
Didn't find tool you were looking for?