Add comments, feedback, review notes, or replies to existing JIRA issues. Use when the user wants to post a comment, reply to a discussion, leave review feedback, or add notes on a JIRA ticket. Transforms raw input into clear, well-structured comments. Also use when the user wants to post code review findings or PR review results to a JIRA ticket. Triggers on any request to comment on, reply to, or add feedback to a JIRA issue.
Pull SEO metrics from the DataForSEO API v3 — keyword research (search volume, CPC, keyword difficulty, search intent, keyword ideas), competitor & domain analysis (which keywords a domain ranks for, organic traffic estimates, competitors, keyword gaps, top pages), live Google SERP & rank checking, and backlink profiles (referring domains, anchors, link quality). Use this whenever the user wants SEO data, keyword metrics, search volume, keyword difficulty, SERP positions, rankings, competitor research, traffic estimates, or backlink analysis for any website or project — and especially whenever DataForSEO is mentioned. Routes the request to the right endpoint and runs it via a generic client script using DATAFORSEO_LOGIN / DATAFORSEO_PASSWORD from the environment. Triggers on requests like "how much search volume does X get", "what keywords does competitor.com rank for", "find SEO competitors for my site", "check our Google ranking for Y", "analyze the backlinks of Z", "keyword research for this project", or a
Collaborative Agent Teams code review with cross-reviewer communication, AI Slop detection, and a unified professional report. Use when the user asks to review a PR, review code changes, or run a code review. Spawns a team of independent reviewer teammates (Virtual Mariusz, Backend Solidifier, Frontend Virtuoso, Quality Purist, Security Sentinel, Devil's Advocate) that can communicate with each other and share findings. Produces a professional report with executive summary, AI Slop score, cross-reviewer findings, and verdict.
Smart triage of Agent Teams Review findings into three action groups (Fix Now / Fix Later / Skip) with intelligent grouping and severity verification. Use when the user wants to triage, prioritize, or sort review findings after a code review. Also use when the user asks what to fix first, wants an action plan from a review, or mentions triage, prioritize findings, review priorities, or sort review results. Requires a completed review report from agent-teams-review.
Tighten and declutter an existing document so a human can read it fast — cut filler, repetition, throat-clearing, and marketing fluff while keeping every fact, decision, number, and caveat, and keeping the language natural (no jargon, no telegraphic shortcuts). Use when a document (especially one drafted by AI) is bloated, padded, or slow to skim — e.g. the user says "uporządkuj ten dokument", "to jest za długie", "skróć to ale nie gub treści", "wytnij lanie wody", "this doc is bloated", "cut the fluff", "make this readable", "too verbose", "remove the AI slop" — or just generated a long README / spec / report / proposal / release notes / JIRA description and wants it trimmed. Also trigger right after producing a long document, to offer a tightened pass. Do NOT use for writing a new document from scratch, for summaries that intentionally drop information, for translation, or for editing code.
Poprawia wskazany polski tekst stylistycznie, gramatycznie i interpunkcyjnie tak, żeby brzmiał naturalnie — usuwa „sztuczność" typową dla tekstów generowanych przez AI (kalki z angielskiego, nadużywane zaimki i dzierżawcze, „posiadać", nominalizacje, puste waciki marketingowe, monotonny rytm), poprawia szyk wyrazów oraz polską interpunkcję (przecinki przed że/który/aby, cudzysłów „", półpauzy, liczby, kapitalizacja). Zachowuje sens, ton, rejestr, długość, formatowanie, linki, słowa kluczowe SEO i przeznaczenie tekstu (email, wpis na blog, opis SEO, komentarz, post, ogłoszenie). Używaj zawsze, gdy użytkownik prosi o poprawienie, redakcję, korektę, dopracowanie lub „uczłowieczenie" polskiego tekstu, mówi że coś „brzmi sztucznie", „jak z AI", „nienaturalnie", „drętwo", chce poprawić styl, gramatykę, szyk albo interpunkcję po polsku, dopracować polski email/blog/opis/post, albo wywołuje /polish-correct. Nie tłumacz i nie dopisuj treści — popraw tylko to, co już jest.
Analyze changes and propose CLAUDE.md updates. Accepts an optional argument describing what changed (e.g., `/claude-md we switched from Jest to Vitest`). Use when the user says "update claude.md", "sync claude.md", "document this in claude.md", after finishing a task that introduced new patterns or conventions, when new tools/commands/dependencies were added, or when project architecture changed. Do NOT trigger for simple questions about CLAUDE.md content, reading CLAUDE.md, or general project questions.
Create clean conventional commits. Use when the user wants to commit changes, make a commit, save progress, or says "commit". Offers three message variants (short, descriptive, multi-line) with live preview, automatic task number detection from branch names, and conventional commit prefixes. Never adds Co-Authored-By lines.