跳到正文
cccskills
免费在 GitHub 公开

prompt-engineering

Use when designing or improving prompts, commands, hooks, skills, or sub-agent instructions, including output quality, reliability, and token efficiency.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(4)

  • SKILL.md1.5 KB
  • references/agent-best-practices.md1.4 KB
  • references/core-patterns.md3.0 KB
  • references/persuasion-principles.md1.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Prompt Engineering

Use this skill to design robust prompts that are clear, testable, and cost-aware.

When to Use This Skill

  • Creating or refactoring prompts for skills, commands, hooks, and reusable templates
  • Improving output consistency, formatting, or reasoning quality
  • Reducing token usage or latency while preserving quality
  • Choosing the right level of strictness (high, medium, low freedom)
  • Defining guardrails and verification steps for fragile workflows

Workflow

  1. Define the exact task outcome, constraints, and required format.
  2. Choose the minimum instruction detail needed for the task's fragility.
  3. Start with a concise baseline prompt.
  4. Add structure: examples, explicit output schema, and failure handling.
  5. Add verification criteria for correctness and uncertainty handling.
  6. Test on varied and edge-case inputs, then iterate.

Expected Outputs

  • A production-ready prompt (or template) with clear task, context, and output contract
  • A short rationale for major design choices
  • A test checklist with representative inputs and edge cases
  • Notes on token and latency tradeoffs

References

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when working with the 1Password CLI (`op` command) for secrets management, retrieving API keys, injecting secrets into development environments, or any task involving 1Password vault operations. Triggers on: "1password", "op command", "secrets management", "api keys from vault", "op run", "op read", "service account token".

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Create and manage teams of specialized AI agents that work together on tasks. Use when setting up multi-agent workflows, agent squads for content/marketing/research pipelines, configuring heartbeat-based agent coordination, or managing agent personalities via SOUL.md files. Enables orchestration of multiple OpenClaw sessions as a coordinated team with shared task systems (Linear, Trello, etc.).

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Create algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use when users request generative art, algorithmic art, flow fields, or particle systems. Create original works rather than copying existing artists.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

CSS and UI animation patterns for responsive, polished interfaces. Use when implementing hover effects, tooltips, button feedback, transitions, or fixing animation issues like flicker and shakiness.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

Use when starting creative work (features, components, functionality, or behavior changes) to clarify user intent, requirements, and design before implementation.

中文简介正在准备中。当前显示原文说明。

thedaviddias/agent-forge32026年5月18日 更新

查看 thedaviddias 的全部技能

报告此技能的问题