Agent Skill · 开发规范

cursor-best-practices（Cursor 最佳实践）

cursor-best-practices 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

cursor-best-practices 是开发规范类 Agent Skill，可用宿主为 Codex、Claude、Cursor、Gemini CLI，通过GitHub 仓库获取，权限为操作浏览器；许可证为 MIT，第三方扫描有提醒项，按安装量在开发规范类的 1,265 个 Skill 里排第 543。

总安装 1,023周安装 41GitHub Stars 5下载 331核验 2026-05-01

开发规范操作浏览器 GitHub 仓库未标认证来源可访问许可证明确审计提醒 Codex Claude Cursor Gemini CLI

安装说明

本站只整理中文说明，不托管安装包，也不代用户安装。

GitHub

许可证: MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：cursor-best-practices（Cursor 最佳实践）
来源仓库：https://github.com/hktitan/cursor-best-practices
仓库路径：skills/cursor-best-practices
安装命令：
npx skills add https://github.com/hktitan/cursor-best-practices --skill cursor-best-practices
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异；本站展示可直接复制的安装命令，安装前请核对来源页面。

skills.shnpx skills

npx skills add https://github.com/hktitan/cursor-best-practices --skill cursor-best-practices

这个 Skill 是做什么的

开发规范类 Skill 用来统一代码风格、目录结构和评审口径，产出多为检查清单或改写建议。

cursor-best-practices 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。

通过 npx skills add 命令从指定仓库安装，需结合原始 README 核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。适用宿主包括 Codex、Claude、Cursor、Gemini CLI，接入前应确认版本、权限和运行环境要求。

来源仓库内路径：skills/cursor-best-practices

上手步骤

4 步

1
确认自己的宿主工具
公开资料标注支持 Codex、Claude、Cursor、Gemini CLI；先确认自己用的是其中之一，再按对应工具的 Skills 目录放置。
2
拿到安装命令
可以直接复制的命令是 npx skills add https://github.com/hktitan/cursor-best-practices --skill cursor-b…；命令里的占位符换成自己的路径或密钥再执行。
3
安装后重启宿主
命令执行完要完全退出宿主工具再打开，让新装的 Skill 被重新扫描到，否则列表里可能看不到。
4
按最小权限试用
它需要操作浏览器，先在测试目录或测试账号里跑，确认没问题再放到正式项目。

常见问题

6 条

cursor-best-practices 怎么安装？

在终端执行 npx skills add https://github.com/hktitan/cursor-best-practices --skill cursor-best-practi…。装完完全退出宿主工具再打开，让它重新扫描本地 Skill。

cursor-best-practices 支持哪些 AI 工具？

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录，一般也能手动放进去，但要自己确认触发方式是否一致。

cursor-best-practices 需要什么权限？

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力，使用时可能读取或操作网页内容，需要在受控环境中确认权限边界。

cursor-best-practices 是免费的吗？

来源标注的许可证是 MIT。本站不代收任何费用，也不托管安装包；能否商用、要不要署名，以许可证原文为准。

cursor-best-practices 用的人多吗？

公开数据是累计安装 1,023 次，近一周安装 41 次，下载 331 次，GitHub 5 星。这些数字来自第三方目录统计，只能当作热度参考，不代表质量或安全性。

cursor-best-practices 安全吗？

第三方扫描有提醒项，说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

同时适配 4 种工具，换客户端不用重新找替代品。
3 个目录同时收录，说明这个 Skill 流传比较广。
许可证明确为 MIT，商用和分发边界好判断。

先想清楚的地方

第三方扫描存在提醒项或未通过项，需要人工逐条确认。
第三方目录整理，版本更新和行为细节以来源仓库为准。

适不适合你

更适合

已经在用 Codex，想直接扩展它能力的人。
需要处理开发规范类任务、又不想每次都手写提示词的人。

不太适合

需要厂商级技术支持和 SLA 的生产系统。

开发规范类 Skill 对比

6 个同类

Skill	总安装	GitHub 星	权限	许可证	扫描
vercel-react-best-practices Vercel React 最佳实践 · Codex、Claude	8,490,720	25,918	操作浏览器	MIT	通过
web-design-guidelines 网页设计指南 · Codex、Claude	6,686,016	25,885	需要联网	MIT	有提醒
remotion-best-practices Remotion 最佳实践 · Codex、Claude	6,505,632	3,027	操作浏览器	MIT	有提醒
supabase-postgres-best-practices Supabase Postgres 最佳实践 · Codex、Claude	3,175,523	2,030	需要联网	MIT	通过
next-best-practices Next.js 最佳实践 · Codex、Claude	1,848,240	841	操作浏览器	MIT	通过
cursor-best-practices Cursor 最佳实践 · 本页	1,023	5	操作浏览器	MIT	有提醒

按安装量取同分类前几名；数字来自第三方目录统计，只作热度参考，不代表质量结论。

SKILL.md 原文

cursor-best-practices

A structured repository for creating and maintaining Cursor Best Practices optimized for agents and LLMs. This skill provides references/ (on-demand docs) and assets/templates/ (rule, command, and subagent templates) covering rules, commands, skills, subagents, ignore files, Agent security, workflows, and community resources.

When to use

Apply this skill when users:

Set up or initialize Cursor, create the .cursor folder, or ask "setup my.cursor folder"
Write or edit .cursor/rules, AGENTS.md, or rule frontmatter
Create or use slash commands, skills, or subagents
Configure .cursorignore or .cursorindexingignore
Work with Agent modes (Agent, Ask, Plan, Debug), semantic search, or @mentions
Ask about TDD, git-style commands, large codebases, or Cursor workflows
Discover rules or MCPs (cursor.directory) or skill recommendations (skills.sh)
Ask about plugins, hooks, Cloud Agent, CLI, worktrees, or deeplinks

Rules

Locations: Project .cursor/rules/ (.md/.mdc), user Cursor Settings → Rules, Team dashboard. Precedence: Team → Project → User.

Types and when to use:

Type	When to use
Always Apply	Must affect every request (e.g. "No `any` in TS", "Run tests before done"). Use sparingly.
Apply Intelligently	General guidance when relevant (e.g. "Prefer functional components").
Apply to Specific Files	Use `globs` (e.g. `*/.test.ts`, `/api/`). Rule loads only when those files are in context.
Apply Manually	User invokes with `@rule-name` when needed (e.g. release process, legacy quirks).

Frontmatter: description (keyword-rich, helps relevance), globs (file-specific), alwaysApply (use rarely). Keep each rule <500 lines; split by concern, link to references/. AGENTS.md = project-root plain markdown alternative; no frontmatter.

Best practices: Composable rules, concrete examples. Reference—don't copy—long runbooks. Start simple; add rules when the agent keeps making the same mistake. Migrate legacy .cursorrules to Project Rules or AGENTS.md.

See: Rules. assets/templates/rules/_sections.md | references/templates-index.md | references/rules-and-commands.md.

Commands

Locations: Project .cursor/commands/, user ~/.cursor/commands/, Team dashboard. Format: Plain Markdown .md; filename = command name. Trigger with / in chat. Parameters: Text after the command is passed as context (e.g. /fix-issue 123 → "123").

Available templates (copy into .cursor/commands/):

Command	Purpose
`/code-review`	Review for correctness, security, quality, tests. Output: Critical / Suggestion / Nice to have.
`/pr`	Summarize changes, propose PR title/description, suggest review checklist.
`/run-tests-and-fix`	Run tests, fix failures, re-run until green; summarize changes.
`/security-audit`	Security-focused review (injection, auth, secrets, deps).
`/setup-new-feature`	Propose plan (files, modules, patterns), suggest implementation steps.
`/fix-issue`	Fix bug or feature from issue # or description.
`/update-deps`	Update deps, run tests, report breaking changes.
`/docs`	Generate or update docs for @-mentioned code or current feature.
`/make-cursor-compatible`	Make codebase Cursor compatible: add.cursor folder,.cursorignore, AGENTS.md, rules, commands, indexes.
`/lint-and-fix`	Run linter, auto-fix issues, report remaining issues.
`/format`	Format code according to project standards.
`/check-coverage`	Check test coverage, identify gaps, suggest improvements.
`/analyze-deps`	Analyze dependency tree, identify unused/duplicate deps, suggest optimizations.
`/generate-types`	Generate TypeScript/types from schemas, APIs, or JSON.

See: Commands. assets/templates/commands/.

Skills and subagents

Skills: Loaded from .agents/skills/, .cursor/skills/, or ~/.cursor/skills/ (and .claude/skills/, .codex/skills/ for compatibility). Each skill is a folder with SKILL.md; optional scripts/, references/, assets/. Frontmatter: name, description (required); optional license, compatibility, metadata, disable-model-invocation (when true, skill only applies when invoked via /skill-name). Agent applies when relevant or via /skill-name. Use /migrate-to-skills (Cursor 2.4+) to convert eligible rules and commands to skills. Subagents: .cursor/agents/ or ~/.cursor/agents/; markdown + YAML name, description, optional model, readonly, background. Foreground vs background; built-ins (Explore, Bash, Browser).

When to use: Subagents — context isolation, parallel work, multi-step specialized tasks (e.g. verifier that only runs tests/lint). Skills — single-purpose, repeatable tasks (changelog, format, domain-specific workflows).

Templates: Copy subagent templates from assets/templates/agents/ → .cursor/agents/. Available subagents:

Read-only (review/analysis):

verifier.md — Runs tests and lint, reports only
reviewer.md — Code review for correctness, security, quality, tests
security-auditor.md — Security-focused review
linter.md — Linting and code style review
architect.md — Architectural pattern and design review

Editable (can modify code):

documenter.md — Generate/update documentation
tester.md — Write and update tests
refactorer.md — Refactor code while maintaining functionality
debugger.md — Investigate and identify bugs
performance-analyzer.md — Analyze performance issues and bottlenecks
accessibility-checker.md — Review code for a11y compliance
migrator.md — Handle code migrations systematically
dependency-manager.md — Review and manage dependencies
formatter.md — Format code according to standards
type-generator.md — Generate types from schemas/APIs

Skill recommendations: assets/recommended-skills.md and skills.sh only; suggest npx skills add <owner/repo>.

See: Skills, Subagents.

Ignore files

.cursorignore: Project root; same syntax as .gitignore. Excluded paths are not used for semantic search, Tab, Agent, Inline Edit, @mentions. Not terminal/MCP. Why: Security (secrets, keys, credentials), performance (large repos). .cursorindexingignore: Indexing only; files still usable if @-mentioned.

Must exclude: .env, .env.*, *.key, *.pem, credentials.json, **/secrets/**. Add project-specific paths. Use ! carefully; parent exclusions limit re-includes.

See: Ignore files. assets/templates/rules/ignore-cursorignore-secrets.md.

Agent and security

Agent: Rules + tools (search, read, edit, terminal, MCP) + your messages. Summarization (/summarize), checkpoints. Queue (Enter) vs Ctrl+Enter (send immediately).

Security: File edits allowed (except protected config); use VCS. Terminal: approval by default; avoid "Run everything". MCP: approve connection + each tool call. Network: GitHub, link fetch, search only. Put secrets in .cursorignore.

See: Agent overview, Agent security. references/agent-and-security.md.

Agent modes

Mode	Purpose	Tools
Agent	Implement, refactor, multi-file work.	Full (search, read, edit, terminal, MCP).
Ask	Learning, Q&A, exploration.	Search + read only; no edits.
Plan	Research → clarify → plan → you review → "Build".	Search + read. Plans in `.cursor/plans/`; Shift+Tab to switch.
Debug	Reproducible bugs; hypotheses → instrument → reproduce → fix → verify.	Full.

Switch: Mode picker in chat; Ctrl+. to cycle. Best practice: Plan with Ask/Plan, implement with Agent. If Agent builds wrong thing, revert → refine plan → re-run.

See: Plan Mode, Debug Mode. assets/templates/rules/modes-plan-then-agent.md. references/modes-context-tools.md.

Workflows and large codebases

TDD: Write tests → run (expect fail) → commit tests → implement → run until pass → commit impl. Run tests before done: assets/templates/rules/workflows-run-tests-before-done.md.

Git-style commands: /pr, /fix-issue, /review, /update-deps, /docs in .cursor/commands/. Codebase understanding: "How does X work?", "How do I add Y?"; broad → narrow. Diagrams: Ask for Mermaid architecture/data-flow. Hooks: .cursor/hooks.json for long-running loops. Design → code: Paste mockups; use Browser for preview.

Large codebases: Domain rules in .cursor/rules with globs; Plan with Ask, implement with Agent. Tab = quick edits; Inline Edit (Ctrl+K) = single-file; Chat/Agent = multi-file. Use @files, @folder, @Code; scope down; new chats when context is noisy.

See: Agent workflows, Large codebases. references/workflows-and-codebases.md.

Semantic search, @mentions, Tab

Semantic search: Meaning-based; natural-language questions. Indexing on workspace open; usable ~80% completion. Use both grep (exact) and semantic (conceptual): assets/templates/rules/context-use-grep-and-semantic.md.

@Files & Folders: Reference by path; drag from sidebar. @Code: Specific snippets (most precise). @Docs: Bundled or Add new doc (URL). /summarize — compress context. Best practice: assets/templates/rules/context-use-at-mentions.md.

Tab: Inline autocomplete; Tab accept, Esc reject, Ctrl+Right partial. Use for speed; Inline Edit or Chat for larger changes.

See: Semantic search, @ Mentions, Tab.

Bugbot, MCP, shortcuts

Bugbot: PR review (bugs, security, quality). .cursor/BUGBOT.md at project root (always included) and nested per directory (included when reviewing files under that path); Team rules from dashboard apply to all repos. Trigger: comment cursor review or bugbot run; use verbose=true for request ID. Autofix spawns a Cloud Agent to fix reported issues (commit to branch or new branch). MCP: External tools; approve connection + tool calls. cursor.directory for community rules & MCPs. Skills: skills.sh only.

Shortcuts: Ctrl+I Agent | Ctrl+K Inline Edit | Ctrl+. cycle modes | Enter queue, Ctrl+Enter send | Tab accept completion, Esc reject.

See: Bugbot, MCP.

Plugins, Hooks, Cloud Agent, CLI, Worktrees, Deeplinks

Plugins: Bundle rules, skills, agents, commands, MCP servers, and hooks in distributable packages. .cursor-plugin/plugin.json manifest; install from Cursor Marketplace or team marketplaces (Teams/Enterprise). See: Plugins.

Hooks: .cursor/hooks.json (project) or ~/.cursor/hooks.json (user). Observe or gate agent loop stages (e.g. beforeShellExecution, afterFileEdit, sessionStart). Command-based (script) or prompt-based (LLM). See: Hooks.

Cloud Agent: Agents run in the cloud; access via API, Linear, GitHub, Slack, Desktop (Cloud in dropdown), or cursor.com/agents (Web/PWA). MCP support; spend limit; "Apply" to bring worktree changes to your branch. See: Cloud Agent.

CLI: agent command for interactive or non-interactive use. Modes: Agent, Plan, Ask. Cloud handoff: & in chat or agent -c "prompt". Sessions: agent ls, agent resume. See: CLI.

Worktrees: Parallel agents run in separate Git worktrees. .cursor/worktrees.json for setup (e.g. setup-worktree, OS-specific). Best-of-N: run same prompt on multiple models; Apply to merge result. See: Worktrees.

Deeplinks: Share prompts, commands, or rules via cursor://anysphere.cursor-deeplink/ or https://cursor.com/link/. Max 8,000 characters. See: Deeplinks.

.cursor layout and setup workflow

Folders: rules/, commands/, skills/, agents/. Optional: hooks.json, worktrees.json. AGENTS.md = simple alternative to rules.

Setup my.cursor folder

When the user asks to set up, initialize, or create the .cursor folder:

Create: .cursor/rules/, .cursor/commands/, .cursor/skills/, .cursor/agents/.
Optional .cursorignore: If missing, add minimal (e.g. node_modules/, .env, *.log, dist/). Use .gitignore syntax; adjust for stack.
Optional templates: Offer to copy from this skill. If user agrees:

- Commands: Copy from assets/templates/commands/ → .cursor/commands/ (e.g. code-review.md, lint-and-fix.md, format.md, etc.). - Agents: Copy from assets/templates/agents/ → .cursor/agents/ (e.g. verifier.md, reviewer.md, linter.md, formatter.md, etc.). - Rules: Optionally copy from assets/templates/rules/ or add one starter rule or AGENTS.md.

Confirm: List what was created and how to use it (e.g. "Use /code-review in chat," "Add rules to .cursor/rules/").

See: assets/templates/rules/context-setup-cursor-folder.md. references/templates-index.md.

Troubleshooting

Rules not applying? Check type (Always / Intelligent / Globs / Manual), description (keywords), and globs (paths match). Request ID: "Get request ID" or cursor review verbose=true when reporting. See: Common issues, Troubleshooting guide. references/modes-context-tools.md.

平台分布

Claude Code

31.56%

按下载量换算104

Gemini CLI

21.32%

按下载量换算71

Antigravity

18.36%

按下载量换算61

Cursor

12.61%

按下载量换算42

OpenCode

7.75%

按下载量换算26

qoder

3.06%

按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力，使用时可能读取或操作网页内容，需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项，安装前请自行复核。

继续浏览同类 Skills

更多开发规范 Skills（1,265）返回 Skills 目录

上一个 Skill

cursor-best-practices（Cursor 最佳实践）

siviter-xyz/dot-agent

cursor-best-practices 用于查找、检索和筛选相关信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

下一个 Skill

customaize-agent:apply-anthropic-skill-best-practices（customaize Agent apply Anthropic 技能最佳实践）

neolabhq/context-engineering-kit

customaize-agent:apply-anthropic-skill-best-practices 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息，适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态，以及是否会触发联网、命令执行或文件读写。

安装方式

这个 Skill 是做什么的

上手步骤

常见问题

cursor-best-practices 怎么安装？

cursor-best-practices 支持哪些 AI 工具？

cursor-best-practices 需要什么权限？

cursor-best-practices 是免费的吗？

cursor-best-practices 用的人多吗？

cursor-best-practices 安全吗？

值得选的地方和要先想清楚的地方

适不适合你

开发规范类 Skill 对比

SKILL.md 原文

cursor-best-practices

When to use

Rules

Commands

Skills and subagents

Ignore files

Agent and security

Agent modes

Workflows and large codebases

Semantic search, @mentions, Tab

Bugbot, MCP, shortcuts

Plugins, Hooks, Cloud Agent, CLI, Worktrees, Deeplinks

.cursor layout and setup workflow

Setup my.cursor folder

Troubleshooting

See also

平台分布

安全审计

权限和风险

继续浏览同类 Skills