Answers BMad questions and recommends the next skill from what is installed. Use when the user asks bmad for help, what to do next or where to start; to set up, update, repair, doctor, migrate or check the status of the installation, or add modules; or to see or change the active initiative.

Capture the user's UX vision in two documents: DESIGN.md for how the product looks and EXPERIENCE.md for how it behaves. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX"

Test a product concept with Amazon's Working Backwards method: write the press release for the finished product first, then answer hard customer and stakeholder questions, ending in a complete PRFAQ document. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'

Decision-grade research on a topic or this repository. Use when the user says "deep recon", "research this", "draft a research prompt", "process this research report", "market research", "domain research", "technical research", "competitor research", "what users say about X", "literature review", "help me choose between", "research the codebase", "research how X works here" or "why is X built this way". Not for a quick code question answered in chat.

Sofia, the Product Owner: turns any input (an idea, brief, PRD, transcript, notes) into a ticket's requirements, slices initiatives into epics and epics into stories, writes and refines tickets, runs the board, validates the tree, replans when a change lands, and sets up the ticket store. Use when the user asks for Sofia or the product owner, or says 'create a spec', 'distill this PRD', 'write the initiative from', 'slice this', 'split this epic', 'break this into stories', 'make a ticket', 'refine this ticket', 'what's ready', 'status of', 'publish', 'validate these tickets', 'this changed, what now', 'set up the ticket store'.

Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.

Keep Stave's Claude and Codex provider runtimes in sync when editing one of them. Use when a change touches `electron/providers/claude-sdk-runtime.ts`, `electron/providers/codex-app-server-runtime.ts`, executable lookup, env construction, CLI session launch env, tooling status probes, or any provider-agnostic behavior. Trigger on phrases like "provider runtime", "claude adapter", "codex adapter", "sibling adapter", "PATH env", "CLAUDE_CONFIG_DIR", "CODEX_HOME", "tooling status", "어댑터 대칭", "양쪽 프로바이더 확인".

Answer a question from a knowledge base, read-only, with citations to wiki pages and raw sources. Use for any question about the wiki's subject matter, or when the user says ask the wiki, what do we know about, or query.

Use when writing or updating a zine — Skylark's spec format. Covers the required sections (tl;dr, Components, Structure, Decisions, Changelog) and the principles for what belongs in a zine versus a skill or elsewhere.

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"

Writes a technical tutorial, blog post, or doc from a brief in briefs/, in Daisy's voice, and exports paste-ready files for Medium, Substack, and dev.to. Use when Daisy asks to write, draft, or create an article, post, tutorial, or doc.

Guides a user through collecting the credentials needed to deploy their own copy of Open Harness, deploying this repo on Vercel, and completing first-run setup. Use for requests about deploying, self-hosting, configuring credentials, or getting started with a fork of this app.

Use when uploading locally trained model weights (YOLO, RF-DETR, YOLO-NAS, PaliGemma, Florence-2) to Roboflow — the client-side Python SDK upload flow, safe API key handling, per-family packaging requirements, and verifying the upload.

Use when the user wants to inspect or change the state of products in App Store Connect, Google Play Console, RC Billing, or Test Store (prices, availability, localizations, review screenshots) via RevenueCat product-store-state plans

Migrate existing untested code into the Grove test suite. Use when the user asks to "migrate this code", "convert to Grove", "make this testable", "move this example to the test suite", "add tests for this existing code", "migrate the code on this page", or wants to convert documentation code examples that currently live outside of Grove into properly tested, snippeted examples. Supports both page-level migration (scan an RST page for all code) and snippet-level migration (convert a single code block).

Systematic, safety-first diagnosis of developer network failures such as connection refused, DNS resolution errors, TLS certificate problems, proxy failures, and package registry timeouts. Use when a command fails with a network-shaped error (curl, npm, pip, git, docker), when a service is unreachable, or when the user asks to debug connectivity, DNS, TLS, or proxy issues.

Receive Docker Hub repository webhooks. Use when building a Docker Hub push webhook receiver, because Docker Hub webhooks are UNSIGNED — there is no signature header, no shared secret, no HMAC, no timestamp and no auth option, so signature verification is impossible and must be replaced with a secret URL token plus a re-check against the Docker Hub API. Use when parsing the push_data.tag / push_data.pusher / repository.repo_name payload, when handling the dhi_metadata object on mirrored Docker Hardened Image repositories, when asking why there is no event type field to switch on, or when wondering what to do about the legacy callback_url field.

Receive and verify Deck (deck.co) webhooks, the event stream for Deck's computer-use agents API (agents, sources, Deck Vault credentials, sessions, tasks, task runs, workflows, storage). Use when setting up a Deck webhook event destination, generating the caller-provided whsec_ signing secret, debugging Standard Webhooks signature verification (webhook-id, webhook-timestamp, webhook-signature), rotating secrets, or handling events like task_run.completed, task_run.failed, task_run.interaction_required (MFA prompts), credential.verified, credential.invalid, workflow_run.completed, storage.created and test.ping.

Routes to the correct Hookdeck product skill. Covers Event Gateway (inbound: receive webhooks, webhook endpoints, local dev, event queue), Outpost (outbound: send webhooks to customers) and Inspect (free webhook test URLs with no account: see what a webhook sent). Use when working with any Hookdeck product and unsure which skill to use.

Researches, drafts, reviews, and updates pull request descriptions as durable project documentation, grounded in the diff, repository docs, and live GitHub issues and PRs. USE FOR: writing a PR body or PR description, updating a PR description after new commits, review guides, validation summaries, issue linkage, explaining how a change fits product work. DO NOT USE FOR: resolving review threads (use fusion-github-review-resolution), implementing an issue end-to-end (use fusion-issue-solving), drafting issues (use fusion-issue-authoring), or dependency PR verdicts (use fusion-dependency-review).