dotfiles

Browser automation CLI wrapping Playwright for one-shot tasks like navigation, page interaction, screenshots, and scraping. Use when driving a live browser from the terminal. Skip for repeat automations that warrant a full Playwright script.

Author and maintain agent context markdown — AGENTS.md, rules, skills, memory files. Use when creating, editing, or refactoring any agent-focused doc, or after major codebase exploration to capture learning.

Author and audit Agent Skills. Use when creating a new skill, refactoring an existing one, or rewriting skill metadata (name, description, allowed-tools).

Build ASCII/Unicode animations such as loading spinners, logo reveals, particle effects, and terminal art. Covers character grids, frame loops, per-character state machines, ordering, and performance. Use when designing any character-based visual animation.

Run tests, builds, migrations, or any command needing real CI secrets/services on Blacksmith. Use when testing or validating code, or before any commit or push that should be verified against CI.

Use when editing files in a Bun project (bun.lock or bun.lockb at the root, a packageManager field set to bun in package.json, or imports from the bun namespace) or running bun/bunx commands. Covers Bun-native APIs, the bun test runner, bun build --compile, and the Bun-optimized tsconfig.

End-of-session capture of state changes, novel learnings, and durable preferences into project context files. Use when the user runs `/capture-context`, says "capture context" / "update the docs", or when wrapping a session that introduced non-trivial deps, architecture changes, or explicit "remember this" callouts.

Compress natural language to caveman-style fragments to save tokens, in live conversation or in files. Preserves all technical substance, code, URLs, paths, structure. Use when user says "/caveman-speak", "caveman mode", "talk caveman", "go caveman", "caveman compress the X file/spec/doc", "compress X to caveman", "make a caveman version of X", "cavemanify X", or toggles off ("stop caveman", "normal mode", "back to normal", "english mode").

Manage dotfiles with chezmoi — source state, templates, scripts, and file attributes (dot_, private_, executable_, .tmpl). Use when working inside a chezmoi-managed dotfiles repo (~/.local/share/chezmoi) or running chezmoi commands.

Configure Claude Code hooks in settings.json (PreToolUse, PostToolUse, SessionStart, Stop, etc.). Use when adding or debugging Claude Code hooks, or automating actions tied to Claude tool events. Skip for OpenCode automations (use opencode-plugin-config).

Configure Codex CLI/app/IDE settings. Use when editing Codex config.toml, project .codex layers, permissions, sandbox/approvals, MCP servers, hooks, plugins, skills, TUI settings, models, shell environment policy, or Codex troubleshooting defaults.

Use the ctx7 CLI to fetch library documentation, manage AI coding skills, and configure Context7 MCP. Activate when the user mentions "ctx7" or "context7", needs current docs for any library, wants to install/search/generate skills, or needs to set up Context7 for their AI coding agent.

Build, test, configure, deploy, and debug dbt projects. Use when running dbt CLI commands, or editing dbt files like models, sources, tests, UDFs, or Jinja.

Build TypeScript scripts and CLIs on Deno — from one-off scripts to multi-command Cliffy CLIs. Use when writing .ts files run by deno, structuring deno.json with tasks/tests/permissions, or designing a subcommand layout.

Use when working with Lightdash YAML files, dbt models with Lightdash metadata, the lightdash CLI (deploy, upload, download, preview, lint, sql, set-warehouse), or creating/editing charts, dashboards, metrics, and dimensions as code

Design subagents — specialized assistants with their own system prompt, model, and permissions. Use when adding or modifying subagents for Claude Code, OpenCode, Codex, or equivalent coding agent platforms.

Opinionated production Python standards with automatic version detection (3.10-3.13). Use when writing, reviewing, or refactoring Python in repos that want modern type syntax, explicit condition checks where practical, pathlib operations, interface guidance, and pragmatic production patterns.

Systematically explore a web app via agent-browser, find bugs and UX issues, and produce a report with reproduction evidence. Use when asked to dogfood, QA, or test a site/app/platform in the browser.

Write maintainable SQL with CTE pipelines (import, transform, output). Use when writing non-trivial SQL meant to be committed, reviewed, or reused. Skip for one-off ad-hoc queries.

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify) via agent-browser over Chrome DevTools Protocol. Use when scripting or inspecting an Electron app from the terminal.

Codebase intelligence for JavaScript and TypeScript. Free static layer finds unused code (files, exports, types, dependencies), code duplication, circular dependencies, complexity hotspots, architecture boundary violations, and feature flag patterns. Runtime coverage merges production execution data into the same health report for hot-path review, cold-path deletion confidence, and stale-flag evidence - a single local capture is free, while continuous/cloud runtime monitoring is paid. 94 framework plugins, zero configuration, sub-second static analysis. Use when asked to analyze code health, find unused code, detect duplicates, check circular dependencies, audit complexity, check architecture boundaries, detect feature flags, clean up the codebase, auto-fix issues, merge runtime coverage, or run fallow.

Idiomatic fish shell scripting and config — functions, completions, abbreviations, conf.d, argparse. Use when editing .fish files or anything under ~/.config/fish.

Author, audit, and scaffold GitHub Actions workflows. Use when editing .github/workflows/*.yml, picking runners or marketplace actions, debugging workflow failures, or scaffolding CI/release workflows for Supermodel Labs projects.

Generate or extend .gitignore files with project-aware patterns. Use when creating .gitignore, ignoring a new tool/language, or auditing existing rules.

Control herdr from inside it. Manage workspaces and tabs, split panes, spawn agents, read output, and wait for state changes via CLI commands that talk to the running herdr instance over a local unix socket.

Create and edit JSON Canvas (.canvas) files with nodes, edges, groups, and connections. Use when editing .canvas files or building visual canvases, mind maps, or flowcharts (e.g. in Obsidian).

Build and debug lazygit customCommands in config.yml — prompts, contextual keybindings, commandMenus, template-based construction, and conventional-commit flows. Use when editing lazygit config or designing a custom command.

Facilitate a 10–15 minute Mental Contrasting + Implementation Intentions (MCII) goal-setting exercise. Use when the user asks to set a learning goal, structure skill development, or plan learning for a new project.

Offer 10–15 minute learning exercises after architectural work — new files, schema changes, refactors, unfamiliar patterns. Use when wrapping a meaningful chunk of work or when the user asks to understand code more deeply.

Use Linear effectively, not dogmatically. Unless project-local guidance overrides this global skill, use this for any work creating, managing, linking, or shipping work on Linear projects and issues.

This skill should be used when the user asks to "add an app to my MCP server", "add UI to my MCP server", "add a view to my MCP tool", "enrich MCP tools with UI", "add interactive UI to existing server", "add MCP Apps to my server", or needs to add interactive UI capabilities to an existing MCP server that already has tools. Provides guidance for analyzing existing tools and adding MCP Apps UI resources.

This skill should be used when the user asks to "add MCP App support to my web app", "turn my web app into a hybrid MCP App", "make my web page work as an MCP App too", "wrap my existing UI as an MCP App", "convert iframe embed to MCP App", "turn my SPA into an MCP App", or needs to add MCP App support to an existing web application while keeping it working standalone. Provides guidance for analyzing existing web apps and creating a hybrid web + MCP App with server-side tool and resource registration.

This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.

Configure Neovim with the LazyVim framework in Lua, for plugins, keymaps, options, autocmds, snippets, LSP, formatters, linters, themes. Use when editing files under ~/.config/nvim/lua/.

Write Neovim plugins in Lua compatible with lazy.nvim; using vim.api, plugin layout, health checks, lazy-loading, busted tests, floating windows, async. Use when authoring a Neovim plugin or its lazy.nvim spec. Skip for editing personal nvim config (use neovim-config).

Use the Notion CLI `ntn` for authenticated Notion API requests, pages, data sources, file uploads, and Notion Workers. Use when the user asks to run or script `ntn`, inspect Notion API endpoints, create or edit Notion content from the terminal, or deploy and operate Notion Workers.

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when editing .base files or building database-style views in an Obsidian vault.

Script Obsidian vaults via the Obsidian CLI for notes, tasks, properties, and search, plus plugin/theme dev (reload plugins, run JS, capture errors, screenshots, DOM inspect). Use when driving an Obsidian vault from the terminal or debugging an Obsidian plugin/theme. Skip for static markdown editing (use obsidian-markdown).

Manage Obsidian vault frontmatter via the rematter CLI to validate schemas, sync to external destinations (Astro, etc.), rename fields, and manage filenames. Use for bulk frontmatter operations across an Obsidian vault or any collection of markdown with frontmatter.

Create and edit Obsidian Flavored Markdown — wikilinks, embeds, callouts, properties, and tags. Use when editing .md files inside an Obsidian vault.