Triage router for all Luzmo problems. Use first whenever anything is broken, not working, or behaving unexpectedly. Triggers on: "not working", "broken", "why is X failing", "debug", chart "0 height", "chart not loading", "wrong data showing", API errors. Diagnoses root cause by symptom and routes to the right implementation skill. Does NOT implement fixes. Use this skill first - even if you think you know the fix - for any Luzmo error, rendering failure, data anomaly, or unexpected behavior.

This skill should be used when the user says "pick issue", "work on issue", "arness code pick", "arness code pick issue", "arn-code-pick-issue", "grab issue", "pick from backlog", "what should I work on", "show issues", "find issue", "browse issues", "next issue", "select issue", "choose issue", "what's unblocked", "work on next feature", "pick from feature tracker", or wants to browse issues filtered by Arness labels, select one, and route it to the appropriate Arness pipeline skill for implementation. Supports local-first dependency resolution from a greenfield feature backlog when available. Requires an issue tracker (GitHub or Jira) to be configured for remote issue browsing. Do NOT use this for creating new issues — use /arn-code-create-issue for that.

Review frontend code under `web/` or `packages/dify-ui/` when the user explicitly requests a review or audit. Supports PRs, branches, pending changes, files, and pasted diffs. Do not use for implementation-only requests, diagnosis without review intent, or backend-only code.

Set up, audit, verify, or fix website conversion tracking. Use when the conversion is a form submission, booked meeting, chat, phone call, signup, or purchase; when conversions must reach Google Ads, Meta, GA4, LinkedIn, TikTok, or Microsoft Ads; when the work involves GTM tags and dataLayer events, pixels, the Conversions API (CAPI), Enhanced Conversions, server-side tagging, or gclid and fbclid capture; or when the user reports conversion problems like "conversions stopped", "double counting", "spend but no conversions", "GA4 and Google Ads don't match", or an Unverified or Inactive status. Covers lead gen and ecommerce. Always fire on confirmed success, never the submit click; verify a test conversion arrives; diagnose before changing anything; offer free and native paths alongside paid ones and disclose partner tools. For tracking plans and UTMs, see analytics. For attribution models, see attribution. For campaigns and bidding, see ads. For CRM lead-stage design, see revops.

When the user wants to plan, build, or optimize SMS, MMS, or WhatsApp marketing — including welcome flows, abandoned cart texts, post-purchase, win-back, promotional sends, or transactional/auth SMS. Also use when the user mentions "SMS marketing," "text message campaigns," "SMS sequence," "SMS automation," "abandoned cart text," "post-purchase SMS," "Klaviyo SMS," "Postscript," "Attentive," "Twilio," "A2P 10DLC," "TCPA," "SMS compliance," "short code," "toll-free SMS," "MMS campaign," "should I do SMS," "SMS vs email," "WhatsApp marketing," "WhatsApp Business API," "WhatsApp templates," or "click-to-WhatsApp." For email sequences, see emails. For SMS copy framing, see copywriting. For opt-in popups that capture phone numbers, see popups.

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," "lifecycle emails," "trigger-based emails," "email funnel," "email workflow," "what emails should I send," "welcome series," or "email cadence." Use this for any multi-email automated flow. Emails avoid AI tells like 'it's not X, it's Y' reveals, 'no X, no Y, no Z' lists, and fake 'Re:' subject lines. For cold outreach and outbound sequences, see cold-email. For in-app onboarding, see onboarding.

Write and debug Flink SQL that runs on Confluent Cloud, enforcing the CC-vs-Apache-Flink (OSS) dialect boundary. Use when the working directory is a Confluent Cloud Flink workspace, when a Flink SQL statement needs checking before it runs on a CC compute pool, or when the user mentions CC Flink, Confluent Cloud Flink SQL, the `confluent flink` CLI, a CFU compute pool, `CREATE CONNECTION`, or asks to check or debug Flink SQL whose runtime is Confluent Cloud. Also trigger when a Flink SQL question is posed and nothing establishes an Apache Flink OSS runtime. Do NOT trigger for: building or deploying Flink UDFs in Java (UDF/UDTF/PTF — use flink-udf); a full CDC pipeline from a database through Flink into Tableflow/Iceberg/Delta Lake (use confluent-cloud-cdc-tableflow); Kafka Streams topology work (use kafka-streams-programming); or Flink SQL confirmed to run on Apache Flink OSS, not Confluent Cloud.

Apply the Doherty Threshold — keep system response under 400ms to preserve user flow. Use when diagnosing perceived slowness or setting a performance budget. For what to show during unavoidable waits, use `loading-states`.

Diagnoses product-market fit from survey, usage and pipeline data and returns a scored verdict with the next moves. Use when you ask 'do we have product-market fit', 'is our PMF survey good enough', 'what does 35% very disappointed mean', 'should we scale yet', 'why is growth stalling', or need a Sean Ellis survey, retention check, or PMF level read. Draws on 137 insights from 66 Lenny's Podcast guests incl. Sean Ellis, Todd Jackson and Rahul Vohra.

Check the health of published EAS Update: crash rates, install/launch counts, unique users, payload size, and the split between embedded and OTA users per channel. Use when the user asks how an update is performing, whether a rollout is healthy, how many users are on the embedded build vs OTA, or wants to gate CI on update health.

Set up isolated git worktrees — create a new branch for fresh work, or attach a worktree to an existing branch, PR, or commit. Use when starting isolated work or isolating an existing ref.

Plan AI-native hackathon scope, demo pitch, and judge Q&A. Use when the user needs 1-hour pitch prep, 24-hour build scoping, AI Native DevCon-style track choice, idea pressure tests, or a spec-led hack plan. Do not use for code generation, implementation support, or non-hackathon DevRel content.

Review local dirty changes, committed branches, and PR diffs with Codex CLI; report findings, validation, blockers, and merge-readiness evidence. Use when the user asks for Codex review, autoreview, independent model review, or pre-ship validation.

Answers questions about, retrieves safe excerpts from, explains concepts from, and summarizes key arguments in Birgitta Böckeler's talk "State of Play: AI Coding Assistants" (AI Native Dev conference, 2026). Use when the user asks about the last 12 months in AI coding assistants, model-task fit, LLM statelessness, context window and attention trade-offs, coding harnesses, harness engineering/context engineering, skills/MCP/sub-agents/plugins/hooks, guide-and-sensor feedback loops, background agents and swarms, review bottlenecks, AI coding costs, cognitive surrender, or risk-based supervision of coding agents.

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring. Use when a task needs biomedical literature from PubMed rather than general web search.

Orchestrate bootstrapping a working MVP from a design or spec document — ingest the SDD/PRD, plan thin vertical slices, scaffold the first end-to-end slice, then drive a generator-evaluator build loop with review and gated feat commits. Use when a design or spec document must become a running MVP through planned vertical slices.

Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests. Use when the user asks for a code tour, onboarding walkthrough, PR tour, or an explanation of how a subsystem works.

Capture architectural decisions as numbered ADR markdown files in docs/adr/ with context, alternatives considered, consequences, and an index README. Use when the user says 'record this decision' or 'ADR this', chooses between frameworks or databases, discusses trade-offs, or asks why the codebase is shaped this way.

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

Ships coding work to a tested draft PR from one opt-in entry point: detects the tier, runs Micro/Lite here, and on Full writes a short brief with sealed checks, works to them here, and converges once with a local review loop before the PR; prints a paste-ready /goal. Use when asked to "implement autonomously", "independently", "in isolation", "in a worktree", "end-to-end", "all the way to a PR", "ship this", "land this", "take care of this", "handle this without me", or /aw.