The Agent Skills Directory
npx skills add https://smithery.ai/skills/blurjp/getting-started-with-skills在声明使用技能前,务必使用 Read 工具。 会话启动钩子不会自动为你读取技能。未调用 Read 就声明使用技能等于撒谎。
遵循强制性的工作流程。 编码前先进行头脑风暴。在开始任何任务前,先检查相关技能。
为检查清单创建 TodoWrite 待办事项。 仅靠大脑记忆 = 步骤会被跳过。每次都是如此。
1. 检查技能列表:在会话开始时检查,或运行 find-skills [PATTERN] 进行筛选。
2. 如果存在相关技能,你必须使用它:
${SUPERPOWERS_SKILLS_ROOT}/skills/category/skill-name/SKILL.md不要找借口:
原因: 技能文档记录了经过验证的、能节省时间并防止错误的技术。不使用现有技能意味着重复解决已解决的问题并犯已知的错误。
如果存在针对你任务的技能,你必须使用它,否则你将无法完成任务。
如果技能包含检查清单,你必须为每一项创建 TodoWrite 待办事项。
不要:
原因: 没有 TodoWrite 跟踪的检查清单 = 步骤会被跳过。每次都是如此。与遗漏步骤的代价相比,TodoWrite 的开销微乎其微。
示例: skills/testing/test-driven-development/SKILL.md, skills/debugging/systematic-debugging/SKILL.md, skills/meta/writing-skills/SKILL.md
当你使用 Read 工具阅读完一个技能后,声明你正在使用它:
"我已阅读 [技能名称] 技能,并将用它来 [你正在做的事情]。"
示例:
原因: 透明度有助于你的合作伙伴理解你的过程并及早发现错误。这也确认了你确实阅读了该技能。
每个技能都具有相同的结构:
when_to_use 告诉你此技能是否适用于你的情况许多技能包含严格的规则(如 TDD、调试、验证)。 请严格遵循。不要为了适应而放弃纪律。
有些技能是灵活的模式(如架构、命名)。 将核心原则适应到你的具体情境中。
技能本身会告诉你它属于哪种类型。
你的合作伙伴的具体指令描述的是做什么,而不是怎么做。
"添加 X"、"修复 Y" = 这是目标,不是跳过头脑风暴、TDD 或 RED-GREEN-REFACTOR 的许可。
危险信号: "指令很具体" • "看起来很简单" • "工作流程太繁琐"
原因: 具体的指令意味着清晰的需求,而这正是工作流程最重要的时候。在"简单"任务上跳过流程,正是简单任务变成复杂问题的原因。
开始任何任务时:
技能有检查清单? 为每一项创建 TodoWrite 待办事项。
找到相关技能 = 必须阅读并使用它。这不是可选的。
每周安装次数
–
来源
首次出现
–
Use Read tool before announcing skill usage. The session-start hook does NOT read skills for you. Announcing without calling Read = lying.
Follow mandatory workflows. Brainstorming before coding. Check for skills before ANY task.
Create TodoWrite todos for checklists. Mental tracking = steps get skipped. Every time.
1. Check skills list at session start, or run find-skills [PATTERN] to filter.
2. If relevant skill exists, YOU MUST use it:
${SUPERPOWERS_SKILLS_ROOT}/skills/category/skill-name/SKILL.mdDon't rationalize:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
Why: Skills document proven techniques that save time and prevent mistakes. Not using available skills means repeating solved problems and making known errors.
If a skill for your task exists, you must use it or you will fail at your task.
If a skill has a checklist, YOU MUST create TodoWrite todos for EACH item.
Don't:
Why: Checklists without TodoWrite tracking = steps get skipped. Every time. The overhead of TodoWrite is tiny compared to the cost of missing steps.
Examples: skills/testing/test-driven-development/SKILL.md, skills/debugging/systematic-debugging/SKILL.md, skills/meta/writing-skills/SKILL.md
After you've read a skill with Read tool, announce you're using it:
"I've read the [Skill Name] skill and I'm using it to [what you're doing]."
Examples:
Why: Transparency helps your human partner understand your process and catch errors early. It also confirms you actually read the skill.
Every skill has the same structure:
when_to_use tells you if this skill matches your situationMany skills contain rigid rules (TDD, debugging, verification). Follow them exactly. Don't adapt away the discipline.
Some skills are flexible patterns (architecture, naming). Adapt core principles to your context.
The skill itself tells you which type it is.
Your human partner's specific instructions describe WHAT to do, not HOW.
"Add X", "Fix Y" = the goal, NOT permission to skip brainstorming, TDD, or RED-GREEN-REFACTOR.
Red flags: "Instruction was specific" • "Seems simple" • "Workflow is overkill"
Why: Specific instructions mean clear requirements, which is when workflows matter MOST. Skipping process on "simple" tasks is how simple tasks become complex problems.
Starting any task:
Skill has checklist? TodoWrite for every item.
Finding a relevant skill = mandatory to read and use it. Not optional.
Weekly Installs
–
Source
First Seen
–
头脑风暴技能:AI协作设计流程,将创意转化为完整规范与实施计划
83,800 周安装