Skip to content
Agentmart
Submit a tool

correct

用户要求防止本仓库反复出现的 Agent 错误时,收集重复实例并优先用架构、类型、检查或测试消除错误,文档只保留判断规则。

Skill by sunny0826

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sunny0826-correct

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

用户要求防止本仓库反复出现的 Agent 错误时,收集重复实例并优先用架构、类型、检查或测试消除错误,文档只保留判断规则。

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/correct

What's inside

Skill name
correct
Description
用户要求防止本仓库反复出现的 Agent 错误时,收集重复实例并优先用架构、类型、检查或测试消除错误,文档只保留判断规则。
License
MIT
Instructions
18 lines in SKILL.md · view on GitHub

Files (4)

  • LICENSE
  • SKILL.md
  • openai.yaml · agents/
  • sources.md · references/

SKILL.md (first lines)

# 把重复错误变成结构约束

阅读本任务所需的提交、回退、评审和项目规则,按错误类别归并。至少两次实际出现才认定重复类别;引用具体证据,不把一次个人偏好当作全仓库约束。

1. 优先通过架构消除:单一状态拥有者、一个受支持入口、隐藏内部实现、一个事实来源、删除诱导错误的旧路径。
2. 其次通过类型表达合法状态;仍能编译的错误用 lint/CI 检查阻止,错误消息指出正确文件、类型或函数。已有大量遗留时可只阻止新增,不扩大无关迁移。
3. 测试可观察行为,遵守包内 [行为测试](../principle-test-behavior-not-implementation/SKILL.md)。行为坏了仍通过,或只改内部实现就失败的测试,应修正或删除。
4. 文档和 Agent 规则最后写,只记录结构无法判定的判断要求。

先处理最常见的真实类别,逐项证明新机制对真实过去错误失败、对修复后状态通过。用一致的本地和 CI 检查入口;没有 CI 运行条件就标未验证。异常例外须有行内原因、到期时间和明确人工许可,不能借口流程新建批准者。

维护“规则—执行机制”对应表;已有规则又犯错说明机制不足,应提升执行层级,错误不再可能发生时删掉无用提示。按 [结构编码](../principle-encode-lessons-in-structure/SKILL.md) 选择机制。每类可独立交付,但只在已有授权下提交或修改全局规则。

交付各类别证据、选定层级、未用更高层级的原因、失败/通过证明和剩余范围。

来源与适配见 [说明](references/sources.md),保留 [MIT 许可](LICENSE)。

From sunny0826/agent-conductor-skill, MIT.

More from sunny0826/agent-conductor-skill

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 16, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from sunny0826

Cite this page

correct skill. Agent Mart. https://agentmart.dev/skills/sunny0826-correct (last updated 2026-10-24)