Prettier formatting

Author: Nick Sullivan

.claude/commands/ai-coding-config.md

@@ -5,7 +5,9 @@ argument-hint: [update | add]
 
 # AI Coding Configuration
 
-Manages reusable AI configurations across machines and projects. The system lives in `~/.ai_coding_config` and contains Cursor rules, Claude commands, agents, skills, personalities, and GitHub workflows.
+Manages reusable AI configurations across machines and projects. The system lives in
+`~/.ai_coding_config` and contains Cursor rules, Claude commands, agents, skills,
+personalities, and GitHub workflows.
 
 ## Usage
 
@@ -15,7 +17,10 @@ Manages reusable AI configurations across machines and projects. The system live
 
 ## Interaction Guidelines
 
-Use AskUserQuestion when presenting discrete choices that save the user time (selecting a personality, choosing update strategy, handling file conflicts). This lets users quickly click options while still allowing free-form text via "Other". Only use when it genuinely speeds up the interaction.
+Use AskUserQuestion when presenting discrete choices that save the user time (selecting
+a personality, choosing update strategy, handling file conflicts). This lets users
+quickly click options while still allowing free-form text via "Other". Only use when it
+genuinely speeds up the interaction.
 
 ---
 
@@ -34,11 +39,13 @@ Detect project type and framework specifics. Django differs from FastAPI. React
 Show available configurations that match this project. Group by relevance - framework-specific first, then universal. For each option, read description from frontmatter to explain what it does.
 
 Available configurations:
+
 - Rules (`.cursor/rules/` subdirectories and files)
 - Personalities (one or none)
 - Agents (specialized AI assistants, default to all)
 - Skills (intelligent selection based on project type - see skills-selection section)
-- Commands (always copy all, create in `.claude/commands/` with symlinks in `.cursor/commands/`)
+- Commands (always copy all, create in `.claude/commands/` with symlinks in
+  `.cursor/commands/`)
 - Standard configs (VSCode settings, Prettier, GitHub workflows)
 
 Use AskUserQuestion to present personality options as quick-select.
@@ -48,28 +55,36 @@ Use AskUserQuestion to present personality options as quick-select.
 Walk through `~/.ai_coding_config/.claude/skills/` and evaluate each skill for relevance to the current project.
 
 For each skill directory:
+
 1. Read the SKILL.md frontmatter to get the description
 2. Evaluate whether the skill matches this project's context
-3. Categorize as: recommended (strong match), optional (might be useful), or skip (not relevant)
+3. Categorize as: recommended (strong match), optional (might be useful), or skip (not
+   relevant)
 
 Skill evaluation criteria:
 
 Universal skills (always recommend):
+
 - brainstorming: Useful for any project - refining ideas into designs
 - research: Useful for any project - web research for current information
 - systematic-debugging: Useful for any project with code - root cause analysis
 
 Project-specific skills (match against signals):
-- skill-creator: Only for ai-coding-config repo itself (check if current project IS the config repo)
+
+- skill-creator: Only for ai-coding-config repo itself (check if current project IS the
+  config repo)
 - youtube-transcript-analyzer: Projects with docs/, research/, or learning-focused goals
 
 When evaluating a skill you haven't seen before:
+
 1. Read its SKILL.md description carefully
 2. Look for "Use when..." triggers in the description
-3. Match triggers against project signals (package.json, file structure, existing configs)
+3. Match triggers against project signals (package.json, file structure, existing
+   configs)
 4. When uncertain, categorize as optional and let user decide
 
 Present skills grouped by category:
+
 - Recommended: Strong match for this project type
 - Optional: Might be useful depending on workflow
 - Skipping: Not relevant (explain briefly why)
@@ -80,39 +95,47 @@ Use AskUserQuestion to confirm skill selection, showing recommended pre-selected
 <file-installation>
 Copy selected configurations intelligently, respecting existing customizations. Compare files with diff when they exist. For conflicts, use AskUserQuestion to offer choices (overwrite, skip, show diff, or custom action). Never silently overwrite.
 
-Installation mapping: Rules → `.cursor/rules/` (preserve subdirectory structure), Commands → `.claude/commands/` with symlinks in `.cursor/commands/`, Context → `.claude/context.md`, Agents → `.claude/agents/`, Skills → `.claude/skills/` (copy entire skill directories for selected skills only), Personalities → `.cursor/rules/personalities/` (common always, additional with `alwaysApply: true`), VSCode → `.vscode/`, Prettier → `.prettierrc`, GitHub workflows → `.github/workflows/`, Gitignore → `.cursor/.gitignore` and `.claude/.gitignore`, Directory context → `.cursor/AGENTS.md` and `.claude/AGENTS.md` (explains directory purpose and references prompt-engineering rules).
+Installation mapping: Rules → `.cursor/rules/` (preserve subdirectory structure),
+Commands → `.claude/commands/` with symlinks in `.cursor/commands/`, Context →
+`.claude/context.md`, Agents → `.claude/agents/`, Skills → `.claude/skills/` (copy
+entire skill directories for selected skills only), Personalities →
+`.cursor/rules/personalities/` (common always, additional with `alwaysApply: true`),
+VSCode → `.vscode/`, Prettier → `.prettierrc`, GitHub workflows → `.github/workflows/`,
+Gitignore → `.cursor/.gitignore` and `.claude/.gitignore`, Directory context →
+`.cursor/AGENTS.md` and `.claude/AGENTS.md` (explains directory purpose and references
+prompt-engineering rules).
 
-Report what was copied, skipped, and how conflicts were handled.
-</file-installation>
+Report what was copied, skipped, and how conflicts were handled. </file-installation>
 
 <installation-verification>
 Confirm files are in expected locations. List installed rules (framework-specific, then universal), commands, agents, skills. Confirm symlinks point correctly. Verify personality selection and `alwaysApply` setting. Confirm VSCode settings, Prettier config, GitHub workflows, gitignore files, and directory AGENTS.md files.
 
-Provide clear summary without deep validation.
-</installation-verification>
+Provide clear summary without deep validation. </installation-verification>
 
 <recommendations>
 After successful installation, provide actionable next steps.
 
 Always recommend:
+
 1. Generate AGENTS.md if missing at project root (run /generate-AGENTS-file)
-2. List available commands (/load-cursor-rules, /personality-change, /create-prompt, /troubleshoot, /setup-environment, /handoff-context, /product-intel)
+2. List available commands (/load-cursor-rules, /personality-change, /create-prompt,
+   /troubleshoot, /setup-environment, /handoff-context, /product-intel)
 
 Conditional recommendations:
+
 - Git worktrees → suggest /setup-environment
 - Error monitoring detected → mention /troubleshoot
 - Competitive product → suggest /product-intel
 
-Show only genuinely useful recommendations.
-</recommendations>
-</setup-mode>
+Show only genuinely useful recommendations. </recommendations> </setup-mode>
 
 ---
 
 <update-mode>
 Systematically update all configuration types from the repo to latest versions.
 
-Start by pulling latest from `~/.ai_coding_config` and comparing against the current project.
+Start by pulling latest from `~/.ai_coding_config` and comparing against the current
+project.
 
 Configuration categories that must be checked (in this order):
 
@@ -124,10 +147,11 @@ Configuration categories that must be checked (in this order):
 2. Top-level Rules (`.cursor/rules/`)
    - Universal rules apply to all projects regardless of framework
    - Compare: autonomous-development-workflow, code-review-standards, external-apis,
-     fixing-github-actions-builds, git-commit-message, git-interaction, git-worktree-task,
-     naming-stuff, prompt-engineering, user-facing-language, heart-centered-ai-philosophy,
-     trust-and-decision-making
-   - Preserve project-specific rules (sentry, typescript-coding-standards, testing-standards-typescript, code-comments, etc.)
+     fixing-github-actions-builds, git-commit-message, git-interaction,
+     git-worktree-task, naming-stuff, prompt-engineering, user-facing-language,
+     heart-centered-ai-philosophy, trust-and-decision-making
+   - Preserve project-specific rules (sentry, typescript-coding-standards,
+     testing-standards-typescript, code-comments, etc.)
 
 3. Rule Subdirectories (`.cursor/rules/`)
    - Check each subdirectory: ai/, frontend/, observability/, django/, python/
@@ -136,7 +160,8 @@ Configuration categories that must be checked (in this order):
    - Example: ai/agent-file-format.mdc, frontend/react-components.mdc
 
 4. Agents (`.claude/agents/`)
-   - Compare all agent files: design-reviewer.md, seo-specialist.md, site-keeper.md, plus project-custom agents
+   - Compare all agent files: design-reviewer.md, seo-specialist.md, site-keeper.md,
+     plus project-custom agents
    - Update repo agents (description and formatting improvements common)
    - Preserve project-specific agents
 
@@ -151,15 +176,16 @@ Configuration categories that must be checked (in this order):
    - Prettier config (.prettierrc)
    - GitHub workflows (.github/workflows/)
 
-For each category: use diff to identify changes. Categorize as trivial (typos, formatting)
-or significant (logic, descriptions, instructions). List files new to repo or unique to project.
+For each category: use diff to identify changes. Categorize as trivial (typos,
+formatting) or significant (logic, descriptions, instructions). List files new to repo
+or unique to project.
 
 Present update strategy to user: "Update all", "Update selectively", or custom approach.
-Show diffs for significant changes before applying. Never silently overwrite project customizations.
+Show diffs for significant changes before applying. Never silently overwrite project
+customizations.
 
 After copying: verify files are in correct locations, symlinks point correctly, and
-descriptions in frontmatter were updated.
-</update-mode>
+descriptions in frontmatter were updated. </update-mode>
 
 ---
 
@@ -177,42 +203,50 @@ Fetch latest Claude Code documentation for the mechanism you're implementing (co
 <mechanism-selection>
 Decision framework:
 
-Trigger: User manually → Command, Claude autonomously → Skill, Claude delegates focused work → Agent, Bundling multiple mechanisms → Plugin
+Trigger: User manually → Command, Claude autonomously → Skill, Claude delegates focused
+work → Agent, Bundling multiple mechanisms → Plugin
 
 Context: Needs isolation → Agent, Uses main conversation → Command or Skill
 
-Compatibility: Commands work in both Claude Code and Cursor, Skills are Claude Code only (create companion Command for Cursor if needed), Agents work in Claude Code (Cursor can @ mention paths), Plugins are Claude Code only
+Compatibility: Commands work in both Claude Code and Cursor, Skills are Claude Code only
+(create companion Command for Cursor if needed), Agents work in Claude Code (Cursor can
+@ mention paths), Plugins are Claude Code only
 
 Clarifying questions:
+
 1. Who triggers this - user manually or Claude autonomously?
 2. Needs isolated context window or uses main conversation?
 3. Must work in Cursor or Claude Code only acceptable?
-4. Single capability or bundling multiple features?
-</mechanism-selection>
+4. Single capability or bundling multiple features? </mechanism-selection>
 
 <artifact-creation>
 Commands: Create `.claude/commands/command-name.md` with frontmatter including description.
 
-Skills: Create `.claude/skills/skill-name/SKILL.md` with frontmatter (name, description). Description is critical - Claude uses it to decide when to activate. Add supporting files as needed. Create companion Command for Cursor if needed.
+Skills: Create `.claude/skills/skill-name/SKILL.md` with frontmatter (name,
+description). Description is critical - Claude uses it to decide when to activate. Add
+supporting files as needed. Create companion Command for Cursor if needed.
 
-Agents: Determine plugin location (or create new plugin). Create `plugins/plugin-name/agents/agent-name.md` with frontmatter (name, description, tools, model). Agents live in plugins.
+Agents: Determine plugin location (or create new plugin). Create
+`plugins/plugin-name/agents/agent-name.md` with frontmatter (name, description, tools,
+model). Agents live in plugins.
 
-Plugins: Create `plugins/plugin-name/` directory structure with `.claude-plugin/plugin.json` manifest. Bundle commands (via symlinks), skills, agents, hooks, MCP servers. Add README.md. Update `.claude-plugin/marketplace.json`.
+Plugins: Create `plugins/plugin-name/` directory structure with
+`.claude-plugin/plugin.json` manifest. Bundle commands (via symlinks), skills, agents,
+hooks, MCP servers. Add README.md. Update `.claude-plugin/marketplace.json`.
 </artifact-creation>
 
 <creation-verification>
 Verify files are in correct locations, frontmatter includes required fields, skill descriptions clearly define activation criteria, commands work when invoked, plugins are properly structured.
 
-Explain what was created and how to test it.
-</creation-verification>
-</add-mode>
+Explain what was created and how to test it. </creation-verification> </add-mode>
 
 ---
 
 <execution-philosophy>
 Work conversationally, not robotically. Focus on outcomes. Determine best approach for each situation. Show file paths when copying. Let users make all choices. Verify everything works before finishing.
 
-Respect existing files - always check before overwriting. Use diff to understand differences, then decide intelligently or ask. Better to be thoughtful than fast.
+Respect existing files - always check before overwriting. Use diff to understand
+differences, then decide intelligently or ask. Better to be thoughtful than fast.
 
-Explain choices helpfully. Don't just list files - explain what they do and why someone might want them.
-</execution-philosophy>
+Explain choices helpfully. Don't just list files - explain what they do and why someone
+might want them. </execution-philosophy>

.claude/commands/generate-llms-txt.md

@@ -1,10 +1,12 @@
 ---
-description: Generate or update llms.txt file to help LLMs understand and navigate your site
+description:
+  Generate or update llms.txt file to help LLMs understand and navigate your site
 ---
 
 # Generate llms.txt
 
-Creates or updates llms.txt - a standardized file that helps Large Language Models understand and navigate your website or documentation at inference time.
+Creates or updates llms.txt - a standardized file that helps Large Language Models
+understand and navigate your website or documentation at inference time.
 
 <philosophy>
 llms.txt provides LLM-friendly navigation and context for websites and documentation. It should be:
@@ -26,18 +28,21 @@ Determine the appropriate location:
 - static/ directory for Django, Flask, Hugo
 - Repository root as fallback
 
-Choose the location that makes the file accessible at /llms.txt when the site is deployed.
-</file-placement>
+Choose the location that makes the file accessible at /llms.txt when the site is
+deployed. </file-placement>
 
 <content-structure>
 Follow the llmstxt.org standard format:
 
 ```markdown
 # Project Name
 
-> Brief 1-2 sentence description of what this project/site is and what it helps users accomplish.
+> Brief 1-2 sentence description of what this project/site is and what it helps users
+> accomplish.
 
-Additional context paragraph (optional): More detailed information about the project's purpose, key features, or important background that helps LLMs understand how to use the site effectively.
+Additional context paragraph (optional): More detailed information about the project's
+purpose, key features, or important background that helps LLMs understand how to use the
+site effectively.
 
 ## Documentation
 
@@ -63,17 +68,18 @@ Additional context paragraph (optional): More detailed information about the pro
 ```
 
 Structure requirements:
+
 - H1 title with project name
 - Blockquote summary for quick context
 - H2 sections organizing documentation by category
 - Markdown links with concise descriptions
 - "Optional" section for less critical resources
 
 Link format:
+
 - Use relative paths for internal documentation
 - Use absolute URLs for external resources
-- Prioritize most important links first within each section
-</content-structure>
+- Prioritize most important links first within each section </content-structure>
 
 <content-discovery>
 Identify documentation and resources to include:
@@ -86,14 +92,14 @@ Identify documentation and resources to include:
 - Specialized agents from .claude/agents/
 
 Organize by importance:
+
 1. Getting started and quickstart guides
 2. Core concepts and tutorials
 3. API reference and technical documentation
 4. Advanced topics and edge cases
 5. Contributing and community resources
 
-Target file size: Under 2KB for focused navigation.
-</content-discovery>
+Target file size: Under 2KB for focused navigation. </content-discovery>
 
 <update-workflow>
 When llms.txt already exists:
@@ -109,9 +115,11 @@ Next.js project with comprehensive docs:
 ```markdown
 # AI Coding Config
 
-> Plugin marketplace for Claude Code and Cursor providing reusable coding standards, workflows, and AI agents.
+> Plugin marketplace for Claude Code and Cursor providing reusable coding standards,
+> workflows, and AI agents.
 
-Provides a marketplace of plugins that bundle coding rules, slash commands, and specialized agents. Plugins maintain single source of truth through symlinks.
+Provides a marketplace of plugins that bundle coding rules, slash commands, and
+specialized agents. Plugins maintain single source of truth through symlinks.
 
 ## Documentation
 
@@ -144,7 +152,8 @@ Django API project:
 
 > RESTful API for processing payments across multiple providers with unified interface.
 
-Supports Stripe, PayPal, and Square with automatic failover and transaction reconciliation.
+Supports Stripe, PayPal, and Square with automatic failover and transaction
+reconciliation.
 
 ## Documentation
 
@@ -169,6 +178,7 @@ Supports Stripe, PayPal, and Square with automatic failover and transaction reco
 - [Architecture](docs/architecture.md): System design
 - [Contributing](CONTRIBUTING.md): Development setup
 ```
+
 </examples>
 
 <quality-criteria>