tomasz-tomczyk

Review code changes, a plan, a live page (running dev server), or a local HTML file with crit inline comments. Use when asked to review code, a plan, a diff, a running web app, or when you want structured human feedback on your work.

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR, or read/interpret a crit review JSON file. Covers crit comment, crit share, crit unpublish, crit pull, crit push, review file format, and resolution workflow. Not for invoking an interactive review loop — that's the `/crit.md` workflow.

Review code changes, a plan, a live page (running dev server), or a local HTML file with crit inline comments. Use when asked to review code, a plan, a diff, a running web app, or when you want structured human feedback on your work.

Review code changes, a plan, a live page (running dev server), or a local HTML file with crit inline comments. Use when asked to review code, a plan, a diff, a running web app, or when you want structured human feedback on your work.

Review code changes, a plan, a live page (running dev server), or a local HTML file with crit inline comments. Use when asked to review code, a plan, a diff, a running web app, or when you want structured human feedback on your work.

Review code changes, a plan, a live page (running dev server), or a local HTML file with crit inline comments. Use when asked to review code, a plan, a diff, a running web app, or when you want structured human feedback on your work.

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR, or read/interpret a crit review JSON file. Covers crit comment, crit share, crit unpublish, crit pull, crit push, review file format, and resolution workflow. Not for invoking an interactive review loop — that's the `crit` skill.

Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.

Battle-tested gotchas and debugging recipes for Oban background jobs in Elixir (including Oban Pro). Use when writing or debugging Oban workers, queues, batches, or cron jobs; when a custom Oban instance name raises "No Oban instance named ...", when jobs run forever or get discarded, when a queue won't pause/resume or resets on deploy, when REINDEX/long DB ops deadlock under concurrency, when a batch callback never fires, or when inspecting job/queue state in a running node.

Audit and improve marketing copy aimed at engineers — READMEs, landing pages, feature pages, tweets, launch posts. Based on Michael Seibel's YC pitch framework adapted for developer tools. Use when asked to "review copy", "audit the homepage", "improve the README", "check the marketing", or when writing new marketing content for a dev tool.

Review code changes, a plan, a live page (running dev server), or a local HTML file with crit inline comments. Use when asked to review code, a plan, a diff, or a running web app, when you want structured human feedback on your work, or when authoring crit comments programmatically. Covers the interactive review loop plus crit comment, crit share, and GitHub PR sync.

Write or rewrite transactional and growth emails (invitations, onboarding, referrals, re-engagement) using startup email copy principles from YC/Airbnb. Use when asked to "write an email", "rewrite this email", "invitation email", "onboarding email", or when reviewing email copy for conversion.

Use when validating a feature request, user feedback, or product idea. Generates Mom Test-style questions that ask about past behavior instead of hypothetical futures. Use when asked to "validate this idea", "mom test questions", "interview questions for this feature", or given a feature request to evaluate.

Generate multiple design explorations for a UI feature, each inspired by a different company's design language. Spawns parallel agents that research a company's style, then implement a standalone HTML prototype. Use when asked to "explore designs", "design options", "compare UI approaches", or "design sprint".