菜单
Running log of the user's environment preferences and configuration changes — CLAUDE.md rules, settings, and conventions. Use to recall how the user likes their environment set up, and append a dated entry whenever you make an environment change (anything that isn't building a skill).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | environmental-preparations |
| description | Running log of the user's environment preferences and configuration changes — CLAUDE.md rules, settings, and conventions. Use to recall how the user likes their environment set up, and append a dated entry whenever you make an environment change (anything that isn't building a skill). |
Claude has no memory across sessions. This skill is the durable record of how the user likes the environment configured. Read it when preparing a project's environment; append to it whenever an environment change is made (CLAUDE.md edits, settings, conventions — anything that isn't a skill build).
Append a new entry under Change log, newest first: a dated heading, what changed, and where it applies.
~/.claude/CLAUDE.md: terse instructions, StructuredOutput over inline schemas, TOON over JSON for payloads, drop empty/no-finding sections, target <15k input tokens — applied when first writing any LLM agent prompt.C:\Users\Amit\.claude\CLAUDE.md (Working conventions section).~/.claude/CLAUDE.md: (1) the plan.md/tasks.md planning workflow, and (2) always follow python-guidelines before writing Python.C:\Users\Amit\.claude\CLAUDE.md.project-planning and python-guidelines skill descriptions are already trigger-tuned; the global rules are the durable backstop.CLAUDE.md, declaring plan.md as the source of truth and tasks.md as the derived execution breakdown (Milestones, sub-tasks, status table), and instructing session-start to resume at the next Pending/In Progress task.project-planning skill ("Project-root CLAUDE.md rule" section), which offers to add it to a project root on first setup.Gathers the project details each specialized coder needs before it writes code — frontend theme/typography/layout, backend API/caching/DB shape, containerization build/runtime shape, CI/CD pipeline shape — then hands each coder only its scoped answers. Use before invoking any coder, once a worktree feature is scoped, or whenever splitting work across parallel coders.
Builds a missing `<lang>-guidelines` skill for a language/stack, packaged as a standalone plugin and registered in a marketplace, before any code is written. Use whenever no `<lang>-guidelines` skill exists yet for the stack about to be coded (React, FastAPI, Docker, CI/CD, or anything else) — invoke this FIRST, before any coder runs, then follow the generated skill.
Invoke BEFORE writing any Dockerfile or containerizing an app for deployment. Language-agnostic image-build conventions — multi-stage builds, non-root, layer caching, healthcheck, and hadolint tooling.
Invoke BEFORE writing any Python code (CLI tools, libraries, APIs, modules, tests). Encodes the project's Python + uv + ruff + pyright + pytest architecture, plus conditional references for DB, API, and caching work.
Invoke BEFORE writing any React/TypeScript frontend code (components, hooks, routes, forms). Encodes the project's React + TypeScript + Vite + pnpm conventions, architecture rules, and tooling commands.
Read a project's plan.md and build or update a tasks.md broken into Milestones and sub-tasks, with per-task descriptions and a status tracking table, splitting tasks that are too large and marking progress. Use at the start of a project or session ("read the plan", "build a tasks file", "continue where we left off"), whenever a plan.md exists and tasks need to be derived or refreshed, or when the user asks to track/update project progress.