setup-claude-dev-kit
Use when setting up a new dev machine for Claude Code, onboarding to a project, or optimizing development environment - interactive installer that detects existing setup, configures shell, editor, git, templates, and quality gates with configurable enforcement
What this skill does
# Setup Claude Dev Kit ## Overview Claude-native installer for a comprehensive developer environment. Detects existing setup and adapts accordingly - greenfield gets opinionated defaults, existing setups get respectful merges. ## When to Use - Setting up new dev machine for Claude Code - Onboarding to a team using Claude - Optimizing existing development environment - User asks about Claude dev setup, environment, or tooling ## Quick Reference | Bundle | Components | |--------|------------| | minimal | shell | | standard | shell, editor, git, templates | | full | shell, editor, git, templates, quality, memory | ## Installation Flow ### 0. Quick Start Question (First Prompt) **Ask immediately before anything else:** ``` Welcome to Claude Dev Kit! How would you like to proceed? 1. ๐ Feeling Lucky - Auto-configure everything with smart defaults 2. ๐๏ธ Guided Setup - Walk me through the options ``` **If "Feeling Lucky" selected:** - Skip all subsequent prompts - Auto-detect environment (greenfield vs adaptation) - Install **standard** bundle (shell, editor, git, templates) - Use these defaults: - Shell: Install p10k, keep existing aliases - Editor: Add extensions, merge settings (don't overwrite) - Git: Add hooks and templates, preserve existing config - Templates: Create CLAUDE.md if missing - Quality enforcement: **soft** (warns but allows bypass) - Backup everything before changes - Show summary at end **Feeling Lucky behavior:** ``` ๐ Feeling Lucky mode activated! Detecting environment... macOS, zsh, VS Code Mode: Greenfield Installing standard bundle: โ Shell (zsh, powerlevel10k, fonts, aliases) โ Editor (VS Code settings, extensions) โ Git (hooks, templates, conventions) โ Templates (CLAUDE.md, .claude/ directory) Creating backups... done Installing components... [progress] โ Complete! Restart your terminal to activate. ``` ### 1. Detect Environment ```bash # Check OS uname -s # Darwin, Linux, etc. # Check shell echo $SHELL [ -d ~/.oh-my-zsh ] && echo "Oh My Zsh installed" # Check editor command -v code && echo "VS Code installed" command -v cursor && echo "Cursor installed" # Check existing customization (adaptation signals) [ -f ~/.p10k.zsh ] && echo "Powerlevel10k configured" [ -f ~/.gitconfig ] && echo "Git configured" ls ~/.vscode/extensions 2>/dev/null | wc -l ``` ### 2. Determine Mode **Greenfield signals:** - Default shell prompt (no p10k/starship/oh-my-zsh) - No ~/.gitconfig or minimal config - VS Code with <5 extensions - No ~/.claude directory **Adaptation signals:** - Custom shell theme/prompt - Extensive git aliases - Editor heavily customized - Existing dotfiles repo ### 3. Present Options ``` Detected: macOS 14.x, zsh, VS Code, [Greenfield/Adaptation] mode Which bundle would you like? 1. Minimal - shell only (~2 min) 2. Standard - shell + editor + git + templates 3. Full - everything including quality gates 4. Custom - pick individual components ``` ### 4. Install Components For each selected component, invoke its skill: - `setup-cdk-shell` - Shell environment - `setup-cdk-editor` - Editor configuration - `setup-cdk-git` - Git workflow - `setup-cdk-templates` - Project templates - `setup-cdk-quality` - Quality gates - `setup-cdk-memory` - Context management ### 5. Adaptation Mode Behaviors When existing setup detected: 1. **Backup first:** ```bash mkdir -p ~/.claude-dev-kit/backups/$(date +%Y-%m-%d) cp ~/.zshrc ~/.claude-dev-kit/backups/$(date +%Y-%m-%d)/ ``` 2. **Show diff before changes** - Get user approval 3. **Merge, don't replace:** ```bash # Append to .zshrc rather than overwrite echo "# Claude Dev Kit additions" >> ~/.zshrc ``` 4. **Conflict resolution:** ``` You have starship installed. We recommend powerlevel10k. 1. Keep starship (skip shell theme) 2. Try powerlevel10k (backs up starship config) 3. Skip shell setup entirely ``` ### 6. Quality Gate Configuration ``` What enforcement level for quality checks? 1. Advisory - suggestions only, never blocks 2. Soft - warns but allows --no-verify bypass 3. Hard - must pass, CI enforced ``` ### 7. Verify & Report ```bash # Verify installations command -v p10k && echo "โ Powerlevel10k" [ -f ~/.claude/settings.json ] && echo "โ Claude configured" [ -d .git/hooks ] && echo "โ Git hooks" ``` **Generate adoption score:** ``` Environment Score: 8/10 Claude-optimized Installed: โ Shell completions โ Powerlevel10k theme โ Git hooks โ CLAUDE.md template Optional additions: - Quality gates (+1) - Memory tools (+1) ``` ## Key Behaviors - **Idempotent** - Safe to re-run, updates rather than duplicates - **Rollback-aware** - Tracks changes, can undo if something fails - **Progress visible** - Uses TodoWrite so user sees status - **Non-destructive** - Backs up existing configs before modifying ## Component Skills | Skill | Purpose | |-------|---------| | `setup-cdk-shell` | Zsh, p10k, fonts, completions, aliases | | `setup-cdk-editor` | VS Code/Cursor settings, extensions | | `setup-cdk-git` | Hooks, commit templates, PR templates | | `setup-cdk-templates` | CLAUDE.md templates, project scaffolds | | `setup-cdk-quality` | Linting, testing, review automation | | `setup-cdk-memory` | Context/conversation management | ## Updating ```bash # Check for updates Skill: update-claude-dev-kit # Update specific component Skill: update-cdk-shell ```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts โ single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score โฅ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.