跳到正文
TakoAPI
返回技能列表

skills-ttt

由 chengxindl 提供

Coding Agents & IDEs
347下载量由 clawskills.sh 提供
1浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool.

描述

该技能的功能

A guide for creating modular skill packages that extend agent capabilities with specialized knowledge, workflows, and tool integrations. Covers skill structure (SKILL.md frontmatter, scripts, references, assets), design principles like progressive disclosure, and a six-step creation process from gathering requirements to iteration.

The three-level loading system (metadata, then SKILL.md body, then bundled resources) keeps context window usage proportional to task complexity rather than loading everything upfront.

何时使用

  • Scaffolding a new skill directory for a domain-specific workflow
  • Adding reusable scripts to avoid rewriting PDF or image processing code each session
  • Reorganizing an overgrown skill into separate reference files by domain or variant
  • Writing trigger descriptions so the right skill activates on the right user request
  • Validating skill naming conventions and frontmatter before publishing

示例工作流

输入

User asks: Help me create a skill for querying our BigQuery tables

智能体
  1. 1

    Asks clarifying questions to establish concrete usage examples and which table domains matter

  2. 2

    Identifies references/schema.md as a reusable resource to document table schemas and relationships

  3. 3

    Runs init_skill.py to scaffold the skill directory at ~/.deepagents/agent/skills/bigquery

  4. 4

    Writes SKILL.md frontmatter with comprehensive trigger descriptions and body instructions referencing schema.md

  5. 5

    Runs quick_validate.py to confirm required fields, naming conventions, and description length

输出

A bigquery skill directory with SKILL.md and references/schema.md ready for agent use

安装

clawhub install chengxindl/skills-ttt

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接