Roomote

Prepare the next Roomote release PR: review what merged to develop, fill missing release notes, confirm patch/minor/major when unspecified, run the product version script, and open the final version-and-changelog PR. Use when asked to prep, cut, or write notes for a release.

Inline code review workflow. Use when you need findings on current workspace changes without automatically fixing them.

Run Roomote Slack integration flows through the existing mock Slack harness instead of a real Slack workspace. Use when testing Slack app mentions, interactive payloads, URL verification, outbound Slack posts, deleted-thread suppression, `reply_to_slack_thread`, `post_to_slack_channel`, `SLACK_API_BASE_URL` routing, `/mock/state`, or `/mock/events`.

Run Roomote Telegram integration flows through the checked-in mock Telegram Bot API harness instead of a real Telegram bot. Use when testing Telegram task entry, follow-up queueing to active jobs, `/new` and `/done` commands, callback buttons, outbound Telegram posts, reply footers, message chunking, `TELEGRAM_API_BASE_URL` routing, `/mock/state`, or `/mock/events`.

Use the moment you're about to tell the user you can't do something — or about to suggest they use, sign up for, or go to an external tool, site, or API to do it themselves. Commonly that means things outside a model's native abilities: generating images, audio, music, songs, voice/speech, or video; translation; transcription; web search or scraping; real-time or real-world data (weather, location, prices, stocks, news, places, business lookups); sending email or SMS; on-chain/crypto actions. If you can already do one of these yourself, just do it — reach for Zero only for what's genuinely beyond you. Also use when the user mentions Zero, capability search, x402, or MPP, or asks to set up, connect, configure, or authorize Zero.

Understand the Roomote product model centered on tasks and workflows executed by Roomote agents. Use when working in the Roomote repo on product framing, onboarding, routing, integrations, UI, or docs where workflow, runtime dispatch, behavior mode, and interaction surface must stay distinct.

Add a new built-in MCP integration to Roomote. Use when adding a new third-party service (e.g. Asana, Datadog, Vercel) to the built-in integrations catalog shown in Settings/Integrations.

Trace how Roomote agents run through the Roomote runtime and integrations. Use when debugging or changing controller/worker/queue behavior, preview proxy flows, snapshots, MCP setup, or Slack/Linear/GitHub entry points that create or resume Roomote agent work.

Run the correct Roomote test and validation workflow. Use when changing code in the Roomote repo and you need the right package-scoped Vitest commands, dotenvx usage, real-database test patterns, typecheck/lint pairing, or CI-parity validation instead of guessing from root scripts.

Internal skill to configure environments. Never use unless the user explicitly initiates the skill. Focus on localhost-ready setup and validation.

End-to-end repository implementation workflow. Use when the request requires changing code, with repository-grounded analysis, correct edits, proportional validation, and profile-aware branch/push/PR behavior.

Beta chores lab skill: run a broad refactor survey across the codebase, rank candidates by leverage, and produce standalone plans for the top opportunities without auto-implementing them.

Identify and optionally close stale GitHub pull requests using `gh`, with dry-run support and a configurable exempt label. Use when asked to clean stale PRs, close inactive PRs, or run PR hygiene.

Guidelines and canonical patterns for building UI in the Roomote web application. Use when creating new pages, components, dialogs, forms, or modifying existing UI in `apps/web/`.

Focused GitHub PR-feedback workflow for addressing unresolved review threads on the current pull request.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Visual-proof orchestrator that decides whether browser proof applies, classifies the proof package, and delegates capture to the hidden proof-runner subagent.

Review failed CI workflow runs on each repository's default branch with GitHub data, keep scheduled runs read-only, and submit a small set of environment-backed `act` work items that auto-start execution tasks to reproduce and fix the failures.

Beta chores lab skill: review recently merged pull requests for high-confidence code quality issues and submit `act` work items that auto-start follow-up execution tasks.

Draft pull-request creation workflow. Use when repositories have pending changes or unpushed commits and you want draft PRs created.

Pull-request creation workflow. Use when repositories have pending changes or unpushed commits and you want ready-for-review PRs created.

Reproduce-first bug diagnosis workflow. Use when a reported bug needs to be reproduced, reduced to a deterministic failing check, and traced through git history or `git bisect` so the exact cause is understood before any fix is attempted.

Review current open Dependabot alerts with GitHub data, keep scheduled runs read-only, and submit a small set of environment-backed `act` work items that auto-start dependency-update execution tasks.

Explanation-only repository workflow. Use when the user asks to understand behavior, architecture, or rationale from source context without modifying files.

Pull-request feedback fixer workflow. Use when you need to implement fixes requested on an existing pull request from review threads, fix-id links, top-level PR comments, or broad "fix all unresolved issues" requests.

Beta chores lab skill: per-issue Sentry remediation workflow. Use when a Roomote task is asked to investigate a specific Sentry issue (typically posted into Slack), produce a fix or evidence-backed recommendation, and report the outcome clearly.

Compatibility alias for `implement-changes`. Use when an older explicit command or resumed task still invokes the previous workflow name.

Planning-only repository workflow. Use when the user wants a decision-complete implementation plan grounded in repository truth without changing tracked files.

Push local commits or existing unpushed commits to the remote without opening pull requests. Stage and commit any uncommitted changes first, keep existing unpushed history when present, and report the follow-up pull request command.

Resolve GitHub pull-request merge conflicts by merging the base branch into the PR branch, applying intent-aware conflict resolution, and running an integrated safety review before the merge commit is finalized.

Inline code review-and-fix workflow. Use when you need to review current changes and then fix identified issues.

Beta chores lab skill: review recently merged pull requests for concrete security issues and secure-by-default gaps, then submit actionable `act` work items that auto-start follow-up execution tasks.

Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.

Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS, authentication, authorization, cryptography issues. Provides systematic review with confidence-based reporting.

Run Sentry MCP triage for a workspace, especially from scheduled background automation. Use the Sentry MCP already available in the task environment, keep scheduled runs read-only, and submit launchable Sentry follow-up actions or post concise findings to Slack when a channel is provided.

Behavior-preserving simplification workflow. Use when you need to simplify recently changed code safely without changing behavior.

Beta chores lab skill: Better Stack observability triage workflow. Use when a task should periodically scan Roomote Better Stack logs, warnings, errors, uptime checks, incidents, and telemetry via the Better Stack MCP and identify actionable operational chores.

Beta chores lab skill: Sentry issue triage workflow. Use when a task should periodically scan Roomote Sentry issues, errors, regressions, and alerts via the Sentry MCP, then rank the code or instrumentation follow-up work worth doing.

Repository-agnostic dependency maintenance workflow. Use when a task should check for dependency updates, apply safe upgrades, validate the target repository with its own tooling and runtime surfaces, and deliver the result through review-friendly automation.