claude-code-starter

Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally sniff the source site for new endpoints). Confirms scope with the user, plans + executes the fix autonomously, scrubs PII, and opens a PR against mvanhorn/printing-press-library. Two user-in-loop checkpoints: scope after capture, PR draft before open. Trigger phrases: "amend the CLI", "submit a patch", "fix what I just dogfooded", "open a PR for this CLI", "patch this CLI", "add features to my CLI", "rename this command", "add these feeds to <cli>", "sniff for new APIs in <cli>", "amend with these ideas", "use printing-press-amend", "run printing-press-amend".

Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a broken/lost internal copy. Trigger phrases: "import the CLI", "bring it into my library", "fetch from public library", "I don't have it locally yet".

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by main printing-press SKILL.md (Phase 4.85) and printing-press-polish SKILL.md during the diagnostic loop. Not for direct user invocation — its actionable wrappers are /printing-press and /printing-press-polish.

Polish a generated CLI to pass verification and become publish-ready. Runs diagnostics (dogfood, verify, scorecard, go vet, gosec), automatically fixes all issues (verify failures, static-analysis findings, dead code, descriptions, README, MCP tool quality), reports the before/after delta, and offers to publish. Use after any /printing-press run, or on any CLI in $PRESS_LIBRARY/. Trigger phrases: "polish", "improve the CLI", "fix verify", "make it publish-ready", "clean up the CLI", "get this ready to ship".

Regenerate an existing printed CLI from scratch under the current Printing Press, with prior research, prior novel features, and prior patches (post-publish hand-fixes) carried into the writing pipeline as reconciliation context rather than dropped on the floor. Pulls the CLI from the public library if it isn't local, recommends reuse-vs-redo of prior research based on age, then hands off to /printing-press with the right context. Use when a machine upgrade would benefit a published CLI more than manual polish. Trigger phrases: "reprint <api>", "regenerate <api>", "redo the <api> CLI", "rebuild <api> from scratch", "this CLI would benefit from a reprint".

Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side

Web content + endpoint discovery without the browser-driving overhead. Use for clean markdown fetch of any URL (libcurl-impersonate Chrome JA4, auto-pulls cookies from your real browser), one-shot intent-driven scraping (`unbrowse run`), and capture/replay of authenticated JSON endpoints so you don't have to drive a UI every time. Primary surface is the CLI (`unbrowse <cmd>`); MCP server is available at `npx -y unbrowse mcp` as an alternative for hosts that have it wired up.

Universal engineering agent: build features, fix bugs, deep debugging. Covers planning (PRDs, brainstorming), code review (TypeScript/React 19, Rust, security, performance), feature implementation (ralph mode), git safety, browser automation, task tracking, Codex review & rescue, and web research. The one skill for all engineering work.

Quick debugging patterns and known production failure traps. Reference guide for common issues.

Safe production deployment with quality gates, safety audits, and rollback. Deploys to PRODUCTION by default.

Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)

Reverse-engineer ANY binary, bundle, or distributable — compiled native (.exe/.dll/.so/.dylib/Mach-O), JVM (.jar/.apk/.dex), .NET (.dll/.exe IL), iOS (.ipa), browser extensions (.crx/.xpi), WebAssembly (.wasm), Python bytecode (.pyc), React Native Hermes (.hbc), JS bundles, firmware blobs, installers (.deb/.rpm/.dmg/.msi). Routes to the correct tool per file class — Ghidra is just one tool in the kit. Use when the user says decompile, disassemble, reverse-engineer, RE, "look inside this binary/app/extension/firmware", triage malware, audit a binary for vulns, diff functions across versions, or port a closed-source thing to a CLI. Does NOT pentest live websites — for that route to /carmack with browser-automation patterns.

Download Libby audiobooks (MP3/m4b, odmpy or Chrome CDP) and eBooks to PDF/EPUB (libby-dl pdf/ebook). Triggers on libby download, libby audiobook, libby ebook, libby pdf, odmpy libby, libby-dl.

Design and build frontend interfaces with high design quality. Picks a bold aesthetic direction, then hands the brief to the Hallmark anti-AI-slop engine (default) to design/build/audit/redesign — or generates screens via Google Stitch MCP when the user explicitly asks for Stitch. Use for UI design, screen mockups, design systems, building components / pages / apps, or any "design" / "build a [component/page/UI]" request.

THE master iOS/macOS skill — one entry point for ALL Apple work except production shipping. Develop, build, run, debug, review, test, screenshot, ASO, App Store metadata, compliance scanning, Capacitor web-wrap apps, native Swift/SwiftUI, Rust-core apps. Routes to the right tool (xcodebuildmcp, axiom, asc, greenlight, axe) and the right granular skill. Shipping (archive → TestFlight → App Store) lives in /ship's iOS phase. Triggers: "ios", "iphone app", "build the app", "run on simulator", "app crash", "swiftui", "capacitor", "app store screenshots", "ASO", "app review", "TestFlight" (dev questions), "/ios".

MERGED (2026-06-12) — kept as a redirect for muscle memory. iOS development (build/run/debug/review/test/screenshots/ASO) is now the /ios super skill; iOS release (greenlight → sign → archive → TestFlight → App Store → OTA sync) is /ship's Phase 4.7 (references/ios-release.md). Invoking /ios-ship routes to those.

Build, structure, and ship web apps/sites with the Hono framework — the Barklee default for new sites and for converting React SPAs to SSR. Use when the user wants to create a Hono app, convert/remake a site in Hono, add SSR + islands on Cloudflare Workers, set up Hono routing/middleware/JSX, choose between hono/jsx (server) and hono/jsx/dom (client), wire the Vite build, or asks "is this Hono", "make it Hono", "Hono SSR", "Hono on Workers", "@hono/jsx", "islands", "hono framework". Loads current, verified Hono API patterns so you leverage the framework fully instead of guessing from memory.

Meta-skill that inspects ALL installed skills and picks the best skill(s) for a task, then invokes them — so you don't have to remember which skill to call. Use when the user says "/router", "route this", "which skill for…", "pick the best skill", "just get this done", or hands you a task without naming a skill and you want the strongest tool for it. Self-improves: an auto-refreshing catalog of every skill + a decision log the /router learn step mines to fix mis-routes. You can still call any skill directly (router is optional, never a gate).

When the user wants to audit or optimize an App Store or Google Play listing. Also use when the user mentions 'ASO audit,' 'app store optimization,' 'optimize my app listing,' 'improve app visibility,' 'app store ranking,' 'audit my listing,' 'why aren't people downloading my app,' 'improve my app conversion,' 'keyword optimization for app,' or 'compare my app to competitors.' Use when the user shares an App Store or Google Play URL and wants to improve it.

Default output format for reports, summaries, analyses, dashboards, audits, comparisons, digests, briefings, and any deliverable with structured/spatial information. Generates a single self-contained HTML file (no external dependencies) the user can open in a browser, share, print to PDF, or paste into Notion. Lightweight cousin of /design and /magazine — no AI generation server, no editorial chrome, just clean Tailwind-via-CDN HTML that beats Markdown on scannability, comparison, and feel. Use whenever the user asks for a report, summary, breakdown, analysis, audit, dashboard, comparison, or any deliverable that previously would have been a .md file. Triggers: 'report', 'summary', 'audit', 'analysis', 'dashboard', 'compare', 'breakdown', 'rundown', 'brief', 'digest', 'overview', 'recap', 'write up', 'document', 'deliverable'. Reference: https://thariqs.github.io/html-effectiveness/

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.

This skill should be used when writing Ruby gems following Andrew Kane's proven patterns and philosophy. It applies when creating new Ruby gems, refactoring existing gems, designing gem APIs, or when clean, minimal, production-ready Ruby library code is needed. Triggers on requests like "create a gem", "write a Ruby library", "design a gem API", or mentions of Andrew Kane's style.

Generate a working CLI from any API, then wrap it in a Claude Code skill. Point it at API docs, a live URL, or a peek-api capture and get a dual-mode Commander.js CLI (human + agent output) plus a ready-to-use skill folder. Use when user wants to wrap an API in a CLI, generate a CLI from API docs, turn an API into a command-line tool, scaffold a CLI from discovered endpoints, or create a skill for an API.

Generates talking avatar videos by chaining image generation (nano-banana), voice synthesis (MiniMax Speech via fal.ai), and lip-sync animation (OmniHuman 1.5 or Infinite Talk via fal.ai). Use when asked to "create a talking avatar", "generate a video with speech", "make an avatar say something", "lip-sync", or any video generation task combining portrait + voice + animation.

Talk to OpenAI Codex CLI from Claude Code. Send prompts, delegate tasks, get second opinions, and run parallel investigations. Use when the user says "ask codex", "codex chat", "talk to codex", "get codex opinion", "codex-chat", or wants to delegate work to Codex for a second perspective.

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.

This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.

This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.

This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for grammar, punctuation, mechanics, and style guide compliance.

Execution plan management for long-running coding sessions. Combines self-contained living plans (restartable from file alone) with generator-evaluator separation, sprint contracts, and structured context handoffs. Use when: building a multi-milestone feature, running a multi-session refactor, any task too large for one context window, or when the user says 'exec-plan', 'execution plan', 'create a plan', 'resume plan', 'eval my work', or 'plan status'. Commands: /exec-plan create, /exec-plan resume, /exec-plan status, /exec-plan eval, /exec-plan close, /exec-plan list.

This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.

This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Provides expert-level analysis and diagnosis for Meta Ads campaigns. Use this skill to interpret performance data, identify root causes of issues, and generate actionable recommendations, with a special focus on correctly handling the 'Breakdown Effect'. Use when the user mentions Meta Ads analysis, campaign diagnosis, ad performance, CPA analysis, ROAS analysis, or asks to analyze exported data from Meta Ads Manager.

Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.

Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial/interactive diagram rather than text. Also triggers for: flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and any request containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'. Even when the user doesn't explicitly ask for a visual, use this skill proactively when the topic has spatial, sequential, or systemic relationships that a diagram would clarify better than prose.

Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps.

Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase resources, call Browserbase Functions, browse or scaffold Browserbase templates, fetch or search web content, diagnose browse setup, discover site-specific Browse.sh skills, or install/refresh this browse skill.

Phased super-skill that turns a web app (improvebayarea.com or any Cloudflare Workers / SPA / PWA site) into a store-ready native iOS app with Capacitor — end to end. Use when the user wants to "make this an iOS app", "wrap the site", "ship improvebayarea to the App Store", add camera/geolocation/push to a web app, set up live web updates without App Store resubmission, build/run/test the app on the iOS Simulator, or asks how the web↔app update loop works. Detects the active phase and loads only that phase's reference file, the way /carmack loads only the relevant mode. Orchestrates the installed Capgo 48 capacitor-skills, awesome-ionic-mcp, XcodeBuildMCP + /xcode-test, /ios-ship (greenlight + privacy manifest), context7, sosumi, app-store-screenshots and aso-audit. Triggers: "capacitor", "wrap web app", "make it an iOS app", "ship to app store", "live updates / OTA", "Capgo".

Operate the Clerk CLI (`clerk` binary) for authentication, user/org/session management, instance config, env keys, and any Clerk Backend or Platform API call. Use when the user mentions Clerk management tasks, "list clerk users", "create a clerk user", "update organization", "pull clerk config", "clerk env pull", "clerk doctor", "clerk api", or any ad-hoc Clerk API request. Prefer the CLI over raw HTTP: it handles auth, key resolution, app/instance targeting, and formatting automatically.