跳到正文
cccskills
免费在 GitHub 公开

anti-slop

Rules against AI slop in code, comments, commit messages and docs. Use whenever you write or edit code, write documentation, a README, a commit message or a PR description, or review changes for quality.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md2.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Anti-slop

Slop is output that looks finished but isn't, or that pads the work with words and code nobody asked for. Hold every change to these rules.

Code

  • Do what was asked, and only that. No extra features, options, config flags, abstraction layers or "future-proofing" the task doesn't need.
  • No stubs. Never leave TODO, FIXME, pass, throw new Error("not implemented"), "implement this", "your logic here" or "... rest of the code". Write the real code, or say plainly what you didn't do and why.
  • No debug leftovers. Remove console.log, print debugging and debugger statements you added. Real logging goes through the project's logger.
  • No commented-out code. Delete it; git keeps history.
  • Comments explain why, not what. Don't narrate code ("This function adds two numbers", "Increment i"). Keep comments that record a reason, a constraint or a non-obvious decision.
  • Match the codebase. Follow the file's naming, structure, error handling and comment density. Reuse existing helpers instead of writing near-duplicates.
  • No new files without a reason. Don't add READMEs, example files, summary markdown or test scaffolding unless asked.
  • Don't swallow errors. No empty catch, no except: pass, no silent fallbacks that hide a failure.
  • Tests test behaviour. No tests that only assert a mock was called, no snapshot dumps nobody reads, no tests edited to pass without fixing the cause.
  • Finish the loop. Run the project's typecheck, lint and tests for what you touched. Report failures honestly.

Writing (docs, READMEs, commit messages, PR descriptions, replies)

  • Lead with the point. First sentence says what changed or what the answer is.
  • Plain words. Not: delve, leverage, utilize, robust, seamless, cutting-edge, game-changer, supercharge, elevate, unlock, embark, tapestry, "in today's fast-paced world", "it's worth noting", "a testament to".
  • No filler. Cut openers ("Great question!", "Certainly!"), recaps of what the reader just read, and closing offers of more help.
  • No hype or hedging stacks. Say what it does. Qualify only when it matters.
  • Formatting serves the reader. No emoji in headings, no bold on every other phrase, no bullet lists for things that read better as a sentence.
  • Commit messages: imperative subject under ~70 characters, then what and why. No "This commit...".
  • Be specific. Name the file, the function, the number. "Improved performance" says nothing; "cut cold start from 2.1 s to 0.8 s" does.

Before you finish

Re-read your diff as a reviewer would. Remove anything on the lists above. If the ADE plugin's slop check reports a finding, fix it unless it's intended, and say so in one line when it is.

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

AI Agent Architect: Design agent systems: single vs multi-agent, tools and MCP, memory, guardrails, evals.

中文简介正在准备中。当前显示原文说明。

alvin-reyes/better-agentic-ide852026年10月18日 更新

AI Automation Strategist: Decide what to automate: opportunity mapping, ROI, build vs buy, rollout and change management.

中文简介正在准备中。当前显示原文说明。

alvin-reyes/better-agentic-ide852026年10月18日 更新

AI x Web3 Architect: Autonomous agents that hold wallets: smart accounts, spend limits, intents, agent payments.

中文简介正在准备中。当前显示原文说明。

alvin-reyes/better-agentic-ide852026年10月18日 更新

Workflow Automation Architect: Automate business processes: triggers, queues, retries, approvals, n8n vs Temporal vs code.

中文简介正在准备中。当前显示原文说明。

alvin-reyes/better-agentic-ide852026年10月18日 更新

Smart Contract Systems Architect: Contract system design: modules, upgradeability, access control, storage, audit readiness.

中文简介正在准备中。当前显示原文说明。

alvin-reyes/better-agentic-ide852026年10月18日 更新

Cross-chain & L2 Architect: Chain selection, rollups, bridges and cross-chain messaging with their trust assumptions.

中文简介正在准备中。当前显示原文说明。

alvin-reyes/better-agentic-ide852026年10月18日 更新

查看 alvin-reyes 的全部技能

报告此技能的问题