myinit
When to use
Use this skill when creating or updating AGENTS.md for a repository.
Use it especially when:
- the current
AGENTS.mdis long, generic, or stale - agents repeatedly make the same avoidable mistakes
- repository workflows changed and agent guidance needs pruning
Instructions
Treat AGENTS.md as a living list of non-discoverable landmines and workflow gotchas, not a codebase overview.
Core rule: discoverability filter
Before adding any line, ask:
Can an agent discover this by reading the repo (
README, code, config, scripts, directory tree)?
- If yes: do not include it in
AGENTS.md. - If no, and it materially affects task success/cost/safety: include it.
What earns a line
Include only guidance that is:
- Non-discoverable from repository files alone
- Operationally significant (changes commands, outcomes, or safety)
- Actionable (specific enough to execute)
Typical examples:
- Non-standard tooling choices (e.g. use
uvinstead ofpip) - Command caveats (e.g. tests must run with
--no-cachedue to fixture behavior) - Hidden constraints/landmines (deprecated directories still imported in production)
- Critical local conventions that are not encoded in lint/tests/config
What to remove or avoid
Do not include:
- Tech stack summaries
- Directory structure overviews
- Architecture descriptions agents can infer from code
- Generic best-practice advice
- Rules already enforced by tooling (linters, typecheck, tests, CI)
- Mandatory boilerplate headers unless the repo explicitly requires one
Recommended structure
Prefer short, high-signal sections such as:
Scope & routing(which areas need separate/module-local AGENTS files)Non-discoverable commandsLandmines / do-not-touch areasTask-specific constraints
For large repos, recommend hierarchical AGENTS.md files near relevant modules instead of one monolithic root file.
Source files to check first
- Existing
AGENTS.md README.mdPROJECT.md(if present)- Cursor rules (
.cursor/rules/or.cursorrules) - Copilot instructions (
.github/copilot-instructions.md) GEMINI.md- CI/workflow files and package manager config (for command/tooling mismatches)
If AGENTS.md exists, improve it incrementally instead of replacing it blindly.
Maintenance mindset
AGENTS.md is temporary guidance, not permanent configuration.
When recurring issues appear:
- Prefer fixing the root cause in code/tooling (lint rule, test, script, structure)
- Keep only the minimum instruction needed until the root cause is solved
- Prune stale instructions aggressively
Quality gate before finalizing
For each line in AGENTS.md, verify:
- Is it non-discoverable?
- Is it still accurate today?
- Does it materially reduce mistakes/cost/time?
Delete any line that fails one of these checks.
More from cruldra/skills
tauri-v2
Tauri v2 项目开发助手 - 提供 CLI 项目管理、最佳实践指导和代码生成。适用于 (1) 创建和管理 Tauri v2 项目 (2) 开发桌面和移动应用 (3) 配置构建和分发流程 (4) 实现安全的前后端通信 (5) 应用架构设计和性能优化。
15pandoc
当用户需要对某个文档进行格式转换时(例如将 Markdown 转换为 DOCX、PDF、HTML 等)使用该技能。
12refine-dev
协助开发基于 Refine 框架的 React 应用。提供项目初始化、核心配置、数据提供者(Data Providers)、认证(Auth Provider)以及 UI 库集成的指导。专注于使用 shadcn/ui 构建现代化的后台管理系统。
11dri-text-analysis
使用 DRI 文本分析法(Data-Rule-Interaction)对自然语言需求描述进行逐词拆解与领域建模。将非结构化的业务需求文本降维为数据(D)、规则(R)、交互(I)三个维度的结构化架构抽象,直接产出可用于系统设计的概念表格。适用于需求分析、领域语言提取、架构设计前的文本解析,以及将长篇需求文档转化为清晰的开发任务拆解。
9vite-starter
使用 Vite 创建现代前端项目,支持 React、Vue、Svelte、Solid、Preact、Lit、Qwik 和 Vanilla JS,可选 TypeScript。当用户需要初始化新的前端项目、搭建 SPA、创建组件库、设置现代构建工具时使用此技能。触发场景:用户说"创建 vite 项目"、"新建 react/vue/svelte 应用"、"初始化前端项目"、"搭建 spa"、"用 vite 起一个项目"、"create vite project"、"new frontend app",或明确提及 Vite、HMR、快速构建工具时。
7plantuml-renderer
Use when the user wants to render PlantUML diagrams from pasted text or files that contain valid PlantUML blocks (such as .puml, .md, or .docx text content), and expects image/text output like svg, png, txt, or utxt via local Java + plantuml.jar.
7