Browse skills

Generate a D2 diagram from a text description

Render .d2 files to SVG or PNG images

Validate D2 syntax in .d2 files or directories

Internal routing hub for d2 diagram skills

This skill should be used when the user asks to "show dev-setup config", "change the worktrees directory", "update the port pattern", "configure dev-setup settings", or wants to view or update settings in .claude/dev-setup.json.

Generate dev server lifecycle scripts (start/stop/status/ports) from detected project structure

This skill should be used when the user asks to "create a worktree", "set up an isolated workspace", "create a branch for a feature", "start working on a new branch", or before executing an implementation plan that needs an isolated git workspace.

Audit code changes across 13 quality dimensions before or after merge

Scan a codebase and auto-generate relevant diagrams from its structure

Change theme, output format, or check plugin dependencies

Generate a Mermaid diagram from a text description

Render .mmd or .md files to SVG images

Validate Mermaid syntax in .md files or directories

Self-hosted AI accounting tool that analyzes receipts, invoices, and bank transactions using LLMs. Use when: automating personal/business bookkeeping, categorizing expenses with AI, preparing tax documents, building self-hosted financial tools.

Use when checking Paperclip org health, reviewing agent efficiency, diagnosing token waste, verifying governance compliance, or before and after making org changes. Also use when agents seem idle or unproductive, costs spike, tasks stall, heartbeats fail silently, you see 409 conflicts, stale locks, blocked deadlocks, or suspect agents burning tokens with no progress.

Auto-update third-party marketplace plugins on session start

Interpret third-party feedback by running parallel internal and peer interpretations to surface intent, correctness concerns, and ambiguities. Use when the user asks to "interpret feedback", "interpret comments", "what does this feedback mean", "clarify reviewer intent", "understand this review", or "interpret these suggestions".

Run an independent peer interpretation of third-party feedback via codex. Returns structured intent interpretations without applying changes. Use when the user asks to "peer interpret feedback", "get a second opinion on this feedback", or "interpret feedback independently".

Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map the codebase", "map codebase", "architecture report", "codebase overview", "architecture overview", "what am I looking at", or "explain this codebase".

Run an independent peer review via codex. Use when the user asks to "peer review", "peer review my code", "peer review my plan", "peer review my spec", "peer review my prompt plan", "get a second opinion", or "independent review".