跳到正文
cccskills
免费在 GitHub 公开

coding-guidelines

Guide an AI agent through code changes with explicit assumptions, simple implementations, focused edits, and testable goals. Use it for bug fixes, features, refactoring, or reviews to reduce guesswork and unnecessary changes.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.

查看安装方法

适用场景

  • Fixing a bug with a test that reproduces it
  • Adding a feature without expanding its scope
  • Refactoring while preserving existing behavior
  • Reviewing code for unnecessary complexity

包含的文件(1)

  • SKILL.md2.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Coding Guidelines

Behavioral guidelines to reduce common LLM coding mistakes. These principles bias toward caution over speed—for trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them—don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.
  • Disagree honestly. If the user's approach seems wrong, say so—don't be sycophantic.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it—don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" → "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" → "Write a test that reproduces it, then make it pass"
  • "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

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

Audit and improve website accessibility using WCAG 2.1, guidelines for making web content usable by people with disabilities. Check image descriptions, contrast, forms, keyboard controls, and screen reader support with automated and manual testing.

中文简介正在准备中。当前显示英语简介。

  • Checking a site before launch
  • Fixing keyboard navigation and focus
  • Improving form labels and error messages
tech-leads-club/agent-skills70742026年10月17日 更新

Plan personalized sales emails to prospects you have not contacted before. This skill covers prospect selection, contact research, email drafts, follow-up sequences, inbox delivery, and reply handling, with guidance on tools and campaign improvements.

中文简介正在准备中。当前显示英语简介。

  • Drafting personalized sales emails for new prospects
  • Planning a sequence of emails and follow-ups
  • Investigating low reply rates or spam placement
tech-leads-club/agent-skills70742026年10月17日 更新

Plan pricing for AI products by comparing charges based on usage, tasks, or results. Use customer value and computing costs to shape pricing tiers, usage limits, hybrid plans, and margin improvement strategies.

中文简介正在准备中。当前显示英语简介。

  • Choosing how to charge for an AI product
  • Designing pricing tiers and usage limits
  • Reviewing low margins
tech-leads-club/agent-skills70742026年10月17日 更新

ai-sdr

免费

Plan AI sales development systems that qualify prospects, organize outreach, classify replies, and hand opportunities to people. Use customer criteria, budget, CRM setup, and sales goals to shape platform choices and a four-week rollout plan.

中文简介正在准备中。当前显示英语简介。

  • Planning an AI sales development rollout
  • Defining prospect scores and qualification criteria
  • Improving outreach with low reply or meeting conversion rates
tech-leads-club/agent-skills70742026年10月17日 更新

ai-seo

免费

Plan AI-assisted SEO, from keyword research and competitor comparison pages to content production using data and templates. It also guides content changes for AI search citations, tool selection, quality checks, and ongoing performance tracking.

中文简介正在准备中。当前显示英语简介。

  • Planning competitor alternative and comparison pages
  • Designing page production using data and templates
  • Reviewing content for citations in AI Overviews
tech-leads-club/agent-skills70742026年10月17日 更新

Plan UGC campaigns, ads built around user-style content, from creator recruitment and production briefs to AI video variations. Organize organic testing, paid promotion, and creative refreshes for TikTok, Meta, and YouTube Shorts.

中文简介正在准备中。当前显示英语简介。

  • Recruiting creators for product videos
  • Writing a short video production brief
  • Planning AI-generated ad variations
tech-leads-club/agent-skills70742026年10月17日 更新

查看 tech-leads-club 的全部技能

报告此技能的问题