CLI Tools
Command line utilities
xemu
by koenhendriks
Control the xemu Xbox emulator for SSX 3 reference comparisons - boot it with the ISO, restore saved snapshots (character select, race briefing, race start) in about a second, press controller buttons, pause/resume and take lossless screenshots without stealing the user's focus. Use whenever our recompiled build's output needs checking against real Xbox behaviour (lighting, colours, geometry, menus, race scenes).
cate-extension
by 0-AI-UG
Build, test, and publish a Cate extension, a web panel (optionally backed by a local server) that runs on Cate's canvas. Use when the user wants to create or scaffold a Cate extension, add a panel to Cate, work with the extension manifest, cateApi scopes, or the window.cate host API, or submit an extension to the cate-extensions catalog.
bash-pro
by rmyndharis
Master of defensive Bash scripting for production automation, CI/CD
bash-defensive-patterns
by rmyndharis
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.
git-advanced
by chaterm
Git 高级操作
agent-memory-mcp
by benjaminasterA
"A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions)."
active-directory-attacks
by benjaminasterA
"This skill should be used when the user asks to \"attack Active Directory\", \"exploit AD\", \"Kerberoasting\", \"DCSync\", \"pass-the-hash\", \"BloodHound enumeration\", \"Golden Ticket\", ..."
address-github-comments
by benjaminasterA
"Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI."
browser-harness
by browser-use
"Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work."
termux-safe
by ferrumclaudepilgrim
Android/Termux constraints reference. Prevents Claude Code from suggesting commands that fail silently on Android (sudo, systemd, non-Termux paths, etc.).
pdf-processing-anthropic
by lawvable
Toolkit for comprehensive PDF manipulation, including extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. Use to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
loongsuite-pilot-ops
by alibaba
loongsuite-pilot-ops
context-budget
by affaan-m
Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.
ck
by affaan-m
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
skill-stocktake
by affaan-m
"Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation."
continuous-learning-v2
by affaan-m
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
strategic-compact
by affaan-m
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
bun-runtime
by affaan-m
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
bun-runtime
by affaan-m
Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
obliteratus
by NousResearch
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods (+ 4 Python-API-only), 15 analysis modules, 116 model presets across 5 compute tiers. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.
native-mcp
by NousResearch
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
openhands
by NousResearch
Delegate coding to OpenHands CLI (model-agnostic, LiteLLM).
code-tidy
by lltx
整理 Java 代码。对 Git 未提交的 Java 类和方法添加/补充 Javadoc 注释，更新日期注释。当用户说"整理代码"、"添加注释"、"更新日期注释"时触发。
cate-cli
by 0-AI-UG
Drive Cate browser, terminal, editor, panel, and coding-agent orchestration surfaces from a Cate terminal. Browser page automation uses native agent-browser command syntax.