shmulc8

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Apply vertical slice architecture to organize code by feature instead of by technical layer. Use when adding a new feature, endpoint, command, query, or use case. Use when deciding whether to create new files or edit existing ones. Use when implementing CQRS, mediator pattern, plugin architecture, event-driven patterns, or auto-discovery registration. Use when the user asks about additive architecture, feature folders, or minimizing edit surface. Also trigger when you notice yourself about to add a new method to an existing controller or service — that is the moment this skill is most needed.

Use when the user wants a hands-free loop where grabbing UI elements in the browser with React Grab feeds tasks to the agent automatically, with no copy-paste or manual handoff. Triggers: "watch react grab", "monitor my grabs", "auto-process react grab", "watch my clipboard for grabs". Not for a one-off paste of a single grab; this is the continuous, always-on loop.

Deploy the Hebrew Codenames co-pilot to its HF Space (shmulc/hebrew-codenames-copilot) by uploading changed files from hf_space/, and report the build stage. Use when asked to "deploy", "push to HF", "ship the Space", or "release the co-pilot".

Pull and summarize user feedback (👍/👎 on clues) for the Hebrew Codenames co-pilot from the private HF dataset shmulc/codenames-feedback. Use when asked to "check feedback", "any new feedback", "grab feedback", review clue thumbs-up/down, or see what users complained about.

QA the Hebrew Codenames engine — run the clue-legality regression, the clue-quality benchmark against the feedback set, and optionally verify the live HF Space. Use before committing engine changes, after tuning scoring or legality, or when asked to "run QA", "run the tests", "run the benchmark", or "check the engine still works".

Use this skill for playing, teaching, or moderating the Hebrew version of Codenames (שם-קוד). Triggers include requests to explain rules, generate clues, validate guesses, simulate games, or clarify legal/illegal actions. Especially for generating high-quality Spymaster clues that avoid opponent and assassin words.

View and manage inline GitHub PR review comments with full thread context from the terminal

Manage isolated development sessions using git worktrees. Use when the user wants to work on a feature branch with isolated Cursor/IDE sessions, create a worktree for a ticket (e.g., "create worktree for PROJ-1234"), switch between features without stashing, preserve session history per feature, or manage multiple branches simultaneously. Triggers on "create worktree", "new worktree", "worktree for ticket", "isolated session", "feature branch session".

Finds and deletes "Captain Obvious" tests — tests that can never fail or check nothing. It catches assertions the type checker already guarantees (typeof/isinstance/toBeDefined on typed values), assertion-free tests, tautologies (expect(true).toBe(true), assert x == x, len >= 0), arrange-assert echoes (const x = 5; expect(x).toBe(5)), mock-echo tests, unawaited async assertions, dead/swallowed/conditional assertions, overly-broad pytest.raises(Exception), and duplicate test bodies. Use whenever the user wants to clean up a test suite, remove redundant/useless/tautological/AI-generated tests, mentions tests that "never fail" or "test nothing", or says "captain obvious". Works on TypeScript (Jest/Vitest/bun:test) and Python (pytest + mypy). The detection is fully deterministic — always run the bundled scripts, never scan test files one by one yourself.

An agent skill that helps developers and AI coding agents write, configure, scaffold, audit, and debug native lifecycle hooks across AI coding agents (Claude Code, Cursor, Windsurf, Aider, Antigravity, Continue, Roo Code, Copilot). Activate this skill whenever asked how to write hooks, setup write guards, intercept agent tool calls, block dangerous shell commands, or configure linting/testing feedback loops for any AI coding agent.

Coach the user step-by-step through writing a conference talk proposal (CFP / Call for Papers) that content committees actually accept. Use this whenever the user is writing or brainstorming a talk proposal, an abstract or title for a tech talk, a speaker submission, or asks how to get accepted to speak at a conference — even if they just say "help me submit to [conference]" or "I have a talk idea" and don't use the word CFP. Also trigger when the user wants feedback on a draft abstract/title, is stuck for a talk idea, or wants to tailor an existing talk for a specific conference. This skill guides ideation, structure, and polish; it does NOT ghost-write a finished proposal from a cold start.

Turn a packaged Codex pet (the output of hatch-pet - pet.json + spritesheet.webp) into a playable, customizable side-scrolling platformer that ships as a self-contained static site. Use when the user wants to build a game from a pet sprite, theme or customize a pet game, generate themed game art around a Codex pet, or deploy a shareable pet game. The pet's fixed 8x9 atlas drives the player character; the output is a static bundle (index.html + game.js + styles.css + assets) with no backend, deployable to Netlify or any static host.