🛠️
AI Engineering

Tool Specification

by kangarooking

Tool Specification is an AI Engineering skill for Claude Code, published by kangarooking in system-prompt-skills.

182 stars40 forkson kangarooking/system-prompt-skillsAdded 2026/09/06+3% in starsRepository updated 2026/05/04
agent-designagent-skillsai-agentscangjie-skillcontext-managementprompt-engineeringprompt-injectionsystem-prompttool-use
Install in seconds
Install Tool Specification
Copy Tool Specification into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/kangarooking/system-prompt-skills/tree/main/tool-specification ~/.claude/skills/tool-specification

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/kangarooking/system-prompt-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
tool-specification/SKILL.md in kangarooking/system-prompt-skills
Installs to
~/.claude/skills/tool-specification
Collection
One of 15 skills cataloged from this repository
Category
AI Engineering3278 skills

What Tool Specification does

Tool Specification defines how to design AI tool interfaces, discovery, permissions, and parallel execution. Use it when an agent needs to call external APIs, manage many tools, or delegate work to sub-agents.

Tool Specification is cataloged under AI Engineering on DirSkills. Tool Specification comes from a repository tagged agent-design, agent-skills, ai-agents, cangjie-skill and context-management.

Documentation

README

工具定义与集成模式 (Tool Specification)

R — 原文 (Reading)

Claude Code: ToolSearch 用于延迟加载, parallel tool calls, Agent tool 用于子代理委托 Claude Chrome: PURL 紧凑命令模式, 三层行动分类 (Prohibited/Explicit Permission/Regular) GPT-4o: Content Reference System, file_search with citation format ChatGPT Agent Mode: 三通道架构 (analysis/commentary/final), browser+computer+container tools Meta AI: 四个命名空间 (media, browser, meta_1p, container, third_party) with full JSON Schema Grok 4: Custom XML function call format (xai:function_call), code_execution with stateful REPL

I — 方法论骨架 (Interpretation)

工具定义与集成的核心设计模式包含五个正交维度:

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Tool Specification

  • What else does kangarooking publish alongside Tool Specification?

    Tool Specification is one of 15 skills that DirSkills catalogs from kangarooking/system-prompt-skills, the repository it ships in. Its siblings there include Agent Delegation, Citation System and Code Engineering. Each one is a separate skill with its own page in this directory, installs the same way Tool Specification does, and is maintained by kangarooking in that same repository. The rest of the collection is listed on the kangarooking/system-prompt-skills page.

  • How does Tool Specification compare to other AI Engineering skills?

    Tool Specification ranks #3056 by stars among the 3278 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Tool Specification against them. Open each page to compare what they document and how they install.

More from kangarooking/system-prompt-skills

Tool Specification is one of 15 skills cataloged on DirSkills from kangarooking/system-prompt-skills.

See all 15 skills
🧩
4h ago

Agent Delegation

Agent Delegation describes how to split work across specialized sub-agents with isolated context, briefing-based handoffs, and validation gates. Use it when designing multi-agent systems, task lifecycles, or cross-tool coordination; not for single-agent routing.
AI Engineering
18240
🔗
4h ago

Citation System

Citation System defines inline citation formats and source-tracking rules for answers that need traceable evidence. Use it for document Q&A, RAG, code references, and other outputs where users must verify where information came from.
AI Engineering
18240
🛠️
4h ago

Code Engineering

Code Engineering defines system-prompt rules for coding agents that edit files, manage Git workflows, and verify changes. Use it for autonomous or guided code modification tasks, not for pure code Q&A or infrastructure setup.
AI Engineering
18240
🧠
4h ago

Context Management

Context Management helps design token budgets, compression strategies, lazy loading, and persistent memory for long-running AI assistants and multi-session systems. Use it when conversation history, large files, or user preferences need to stay usable without overflowing the context window.
AI Engineering
18240
🧭
4h ago

Conversation Flow

Conversation Flow defines how an AI classifies user intent, routes requests into task-specific paths, and chooses when to ask clarifying questions versus proceed autonomously. Use it for multi-step assistants and agents that need structured dialogue management.
AI Engineering
18240
🛡️
4h ago

Injection Defense

Injection Defense helps design system prompts that resist prompt injection, jailbreaks, social engineering, and trust-boundary breaks. Use it for agents or chatbots that process external content like documents, web pages, email, or memory.
AI Engineering
18240