damusix

Use when building TypeScript CLIs. Guides command structure, interactive prompts, tab completion, and terminal UI niceties (spinners, progress, inline regions) using citty, `@clack/prompts`, `@bomb.sh/tab`, and `@bomb.sh/tty` — and shipping them: CI gates, versioning (Changesets / release-please), and npm or single-binary release.

Implements HTMX interactions, configures swap behaviors, debugs hx-* requests, and builds hypermedia-driven UI components. Use when tasks involve hx-* attributes, HTMX AJAX requests, swap strategies, server-sent events, WebSockets, or hypermedia-driven UIs.

Implements, evaluates, and deploys multi-armed bandit algorithms — including Thompson Sampling, UCB, epsilon-greedy, LinUCB, EXP3, and contextual bandits. Covers algorithm selection, experiment harnesses, offline evaluation (IPS, Doubly Robust), infrastructure patterns, and correctness verification. Use when the user asks about multi-armed bandits, exploration-exploitation tradeoffs, adaptive experiments, A/B testing alternatives, online optimization, bandit-based recommendation or personalization systems, or contextual bandits.

AST-based code search, lint, and rewrite using ast-grep. Use when finding code patterns structurally (not textually), writing lint rules, building codemods, or migrating API usage across a codebase. Prefer over regex grep when the match target is a syntactic construct (function call, import, class field, assignment).

Build, customize, and deploy Ghost CMS themes. Use whenever the user mentions Ghost themes, Ghost CMS, Handlebars templates (.hbs), Ghost Admin, membership/subscription integration, custom settings, or the content API — even without saying "theme". Trigger on: building a blog theme, creating a Ghost site, editing .hbs templates, member-only content, hero sections, routing (routes.yaml), image optimization, dark mode, search, deploy, gscan validation, JSON-LD/SEO, or any mention of {{ghost_head}}, {{ghost_foot}}, {{#foreach}}, {{#get}}, {{img_url}}, {{asset}}, @custom, @member, or Portal. Also use to modify, extend, or debug an existing theme. Also trigger on Koenig editor cards and .kg-* card styling (kg-image-card, kg-gallery-card, kg-bookmark-card, kg-callout-card, kg-toggle-card, kg-header-card, kg-signup-card), card_assets, cards.min.css, and breakout/wide/full-width card layout.

Writes and executes JavaScript-based shell scripts using Google's zx library. Use when writing shell scripts, automation, build tools, file processing, CLI tools, deployment scripts, data pipelines, or batch operations. Also covers piping, streams, parallel execution, retries, cross-platform scripting, built-in fs utilities, and minimist argument parsing.

Creates, configures, and debugs `@hapi/hapi` servers — implements routes, plugins, auth schemes, validation, caching, and request lifecycle hooks. Use when building HTTP APIs, setting up stale-while-revalidate caching, registering server methods, configuring views, managing startup sequences, or troubleshooting response marshalling.

Write and run HTTP API tests in Hurl's plain-text format. Use when testing REST/GraphQL APIs, writing integration or smoke tests for HTTP endpoints, chaining requests with captured values, polling async APIs, converting curl commands into maintainable tests, or producing executable API documentation. Trigger on .hurl files, the hurl or hurlfmt CLI, jsonpath/xpath response assertions, or any ask to 'test an API' with a simple text-based tool.

Conventions for editing the atomic CLI and command artifacts in this repo. Auto-fires on phrases like "add a CLI subcommand", "wire a new flag", "prompt the user", "add a doctor check", "add a doctor repair", "edit cmd/atomic/main.go", "extend claudeinstall", "add an internal package", "use huh", "add a command", "create a new verb", "add a partial", "render templates", "edit a command", "edit commands/", "create a new command", "edit an agent", "edit agents/", or "add an agent". Contributor-only — never bundled, never installed.

Hypothesis-driven debugging skill. Use when a bug, test failure, crash, or unexpected behavior is reported. Auto-trigger on error pastes or "broken/doesn't work/failing" language. Explicit invocation: /atomic-debug. Output: symptom statement → hypothesis table → cheapest test first → root cause. No symptom-patching. Boundary with atomic-tdd: this skill owns diagnosing an unknown root cause. Once the cause is known and you are writing the fix, that is atomic-tdd's job (failing test first, then the fix).

Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit invocation: /atomic-tdd. Boundary with atomic-debug: this skill owns writing or changing code — new behavior, or a fix whose root cause is already understood. Diagnosing why something is broken (unknown cause) is atomic-debug's job; debug to the root cause first, then return here to write the fix test-first.

Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by side", "visual options for", "compare these layouts", "show layout options", "wireframe some choices". Also invoked by /atomic-plan just-in-time when a design question is genuinely visual. Scope is strictly visual choices — mockup, layout, color, spacing, hierarchy, diagram — not conceptual or text decisions, which stay in the terminal.

Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.

Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the <wikis> block in ~/.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via `atomic wiki bucket add` rather than a bare mkdir. Also fires on "add a bucket", "set up a karpathy wiki", "karpathy realm", "set up a wiki for my projects", "add this to my wiki", "wiki this", "what does my wiki know about X", "is my wiki stale". Not invoked by other commands — this skill is the conversational entry point for wiki and bucket operations; /refresh-wiki is the synthesis engine.

Compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", or invokes /atomic-commit. Auto-triggers when staging changes.

Evidence-before-claim gate. Auto-triggers when Claude is about to claim "done", "fixed", "passing", "complete", "ready to merge", "looks good", "should work", "should pass", "green", or any synonym. Iron rule: no completion claim without a fresh verification command run in this turn. Explicit invocation: /atomic-verify.

Use when the user asks to "write a ralph prompt", "build something with ralph", "create a ralph loop", "set up ralph", "initialize ralph", "start a new ralph project", "run ralph", "configure ralph", "instantiate a ralph loop", or describes a feature, task, or project they want to build autonomously. The primary workflow is an interactive prompt-writing guide that helps users craft high-quality task prompts through structured clarification. Also covers setup, initialization, and execution.

This skill should be used when saving memories, searching for past context, remembering decisions, forgetting memories, or managing the memory store. Trigger phrases include "remember this", "save a memory", "what did we decide about", "search memories", "forget this", "list tags", "rescan architecture". Guides effective use of ai-memory MCP tools (save_memory, search_memories, list_tags, delete_memory, rescan_project_architecture) and slash commands (/remember, /forget).

SolidJS framework development skill for building reactive web applications with fine-grained reactivity. Use when working with SolidJS projects including: (1) Creating components with signals, stores, and effects, (2) Implementing reactive state management, (3) Using control flow components (Show, For, Switch/Match), (4) Setting up routing with Solid Router, (5) Building full-stack apps with SolidStart, (6) Data fetching with createResource, (7) Context API for shared state, (8) SSR/SSG configuration. Triggers: solid, solidjs, solid-js, solid start, solidstart, createSignal, createStore, createEffect.