setup-claude-md
Instructions
You are generating a comprehensive CLAUDE.md file that follows Claude Code best practices.
Input
- Read
.claude/skills/setup-claude-md/claude-code-best-practices.mdas your reference for what a great CLAUDE.md contains - Analyze the current project structure, package.json / pyproject.toml / Cargo.toml / etc. for build commands, tech stack, etc.
- If
docs/project-plan-refined.mdexists, reference it for project context and architecture decisions
Process
-
Analyze the project (like /init would):
- Tech stack and language
- Build, test, lint, and format commands
- Project structure and key directories
- Existing CI/CD configuration
- Environment setup requirements
-
Apply best practices from reference file to produce a CLAUDE.md that includes all of the following sections:
Required Sections:
- Project Overview: 2-3 sentences on what this project is
- Bash Commands: All build, test, lint, typecheck, and dev server commands. Include single-test commands for performance.
- Code Style: Language-specific conventions (imports, naming, module system, formatting rules)
- Architecture: Key patterns, state management, data flow, important directories and what they contain
- Workflow Rules: Branch naming, commit conventions, PR process, CI requirements
- Testing Conventions: Test framework, file naming, how to run individual tests, coverage expectations
- Environment Setup: Required env vars, secrets handling, local dev dependencies
- Common Pitfalls: Known gotchas, things that break easily, unexpected behaviors specific to this project
- Verification Checklist: What to run before considering any task complete (typecheck, lint, test, build)
-
Do NOT include:
- Generic advice that isn't specific to the project
- Verbose explanations — keep entries concise and actionable
- Anything that duplicates what's in other config files
Output
- Write to
CLAUDE.mdin the project root - If a CLAUDE.md already exists, read it first and merge (preserve any custom content, update/add missing sections)
Validation Criteria
Read .claude/skills/_shared/validation-pattern.md and apply it.
Specific criteria for this skill:
- All required sections are present
- Bash commands are correct (test at least the build and lint commands by running them)
- Code style section matches what's actually in the codebase (check a few real files)
- No generic filler — every line is specific to this project
- File is concise (aim for under 100 lines; agents perform worse with bloated CLAUDE.md files)
More from brite-nites/britenites-claude-plugins
verification-before-completion
Ensures tasks are genuinely resolved before marking them done. Activates at task checkpoints during plan execution — validates that fixes actually work, tests genuinely pass, and acceptance criteria are met. Prevents premature completion declarations.
16writing-plans
Breaks work into bite-sized tasks before coding. Activates when a multi-step task needs planning — creates tasks small enough for a junior developer to follow (2-5 minutes each), with exact file paths, complete implementation details, and verification steps. References Linear issue context and project-specific test commands from CLAUDE.md.
14systematic-debugging
Four-phase root cause analysis for bug investigation. Activates when debugging unexpected behavior, failing tests, or production issues — follows reproduce, isolate, analyze, fix with defense-in-depth. Uses condition-based waiting instead of arbitrary delays. Available anytime, not tied to the inner loop sequence.
14refine-plan
Refines a v1 project plan into agent-ready tasks with clear context, implementation steps, and validation criteria. Use after /plan-project has produced a v1 plan.
13executing-plans
Executes a structured plan using subagent-per-task with TDD enforcement. Activates when given an approved plan to implement — launches fresh subagents for each task, enforces red-green-refactor, runs two-stage review per task, and checkpoints between tasks. Parallelizes independent tasks.
13git-worktrees
Creates an isolated git worktree for task execution. Activates when starting work on a planned issue — sets up a new branch with Linear issue ID, runs project setup, and verifies a clean test baseline before coding begins.
12