Claude Skills by rome-os

Add a new Rome-managed OAuth integration for a third-party service so a user can delegate access by clicking Connect, and Rome can act on the service with the delegated token (the GitHub/Slack model — brokered by Pantheon, NOT Composio). Use when asked to "add an integration / connector for <service>", "let users connect their <service>", or "delegate <service> access to Rome". NOT for Composio-managed toolkits (those are a declarative catalog entry only — see rome_apps/connector), and NOT fo...

Audit a design system's color palette against measurable color-science disciplines — WCAG/APCA contrast of declared token pairs, perceptual (OKLCH) ramp uniformity, color-blindness safety of status/categorical sets, token architecture (primitives → semantic → components), dark-mode integrity, and hue budget — and produce evidence-cited findings with concrete fixes. Use this skill whenever the user asks to review, evaluate, or fix design-system colors, palettes, ramps/scales, themes, or dark m...

Hold an interactive session to create or revise an ideal-state doc, or to slice it into approved repository milestones.

Autonomously compute the gap between an ideal-state doc and the codebase, then file the next work issues — or a loop-complete or loop-needs-discussion report.

Release a new Rome runtime image by pushing a `vX.Y.Z` tag — pick the version, verify main is releasable, push the tag, and confirm the image published to Docker Hub. Covers the `v*` runtime-image tag only, not the desktop app (`desktop-v*`) and not npm packages (`ui-v*`, `app-runtime-v*`).

Triage and answer automated code-review findings on a PR without growing its scope. Use when the user asks to "handle / address / respond to review feedback", "go through the bot comments", or after the RomeOS review bots (zoolsher, Jessie-QingYu) post findings on a PR. Classify every finding before writing any code — most findings deserve a reply, not a diff. NOT for requesting a review (that is /code-review) and NOT for reviewing someone else's PR.

Audit the subordinate copy in a UI — section descriptions, field helper text, hints, card subtitles, empty-state body copy, tooltip bodies — against the secondary-text ruleset, and emit a per-string keep/rewrite/delete verdict table a coding agent can apply. Use this skill whenever the user asks to review, tighten, trim, or clean up UI copy, microcopy, descriptions, helper text, subtitles, hints, or empty states; asks "is this copy necessary?", "does this description earn its place?", "why is...

Turn the remaining todos of the current conversation into a GitHub project of task-spec issues wired with native blocked-by dependencies.

Audit an existing UI/UX design (React/JSX/TSX components, HTML, or generated app code) against a tiered ruleset of verifiable UX principles, and produce structured, evidence-cited findings that a coding agent can act on to fix the design. Use this skill whenever the user asks to review, evaluate, critique, audit, or lint a UI, screen, view, form, dialog, dashboard, or frontend codebase for UX quality, design problems, redundancy, confusing labels, missing states, or accessibility of status in...

Validate a Rome-managed OAuth integration end-to-end — prove a user can click Connect and Rome ends up holding a delegated token it can use to call the provider's API. Use when asked to "validate / test the <service> OAuth connector", "check that a user can connect <service>", or "verify the OAuth round-trip". This is the validation half of the GitHub/Slack model (brokered by Pantheon, NOT Composio). For *building* a new integration, run the add-oauth-integration skill first; this skill assum...

Turn a plain-language "do this automatically" request into a routine — either event-triggered ("text me when I get an email from my landlord") or scheduled ("remind me every Friday at 9am"). For third-party events (Gmail, GitHub, Slack…) it confirms with the guardian and then subscribes to the connector trigger so the event actually fires, even one that has never fired before. Ask for any missing detail, then confirm with a card. Reach for this first whenever the guardian wants something to h...

Route browser automation tasks to specialized Rome apps first, then use OpenCLI help discovery when no specialized Rome app is available.

Scaffold a brand-new Rome app from a bundled template into an independent, git-versioned source directory and install it from there. Use for genuinely **app-shaped** software — something with its own user-edited data model, several distinct operations, or a conversational/long-lived agent. FIRST apply the litmus in "Is this an app, or a workflow?" below: most "build me something that does X" requests are pipelines, not apps — if the work is inputs → a sequence → a result (a summary, digest, d...

Create a new Rome app from an App Store source, already installed or identified by a pinned Store version. Copy installed code locally or download and extract a Store bundle without installing the source. Never edit or overwrite an existing source app.

Verify a newly created or newly installed Rome app after `coding:app_creation` or `coding:workflow_creation` finishes installing it. Use only as a second-pass verifier: receive the app id, source root, expected behavior, and local dashboard/API base URL from the creator, then visit the installed app, exercise its safe paths, and report pass/fail evidence. Do not use for scaffolding, implementation, or editing.

Build a new Rome **workflow app** — one action whose body is a single async function that implements its control flow in plain TypeScript (`await`, `if`, `for`, `Promise.all`) and calls existing actions (including `system:summon`). Use whenever the user describes a multi-step automation OR asks an LLM to produce something from inputs: "read X then do Y", "pull from A, B, C and combine", "monitor … and notify me", "for each item, if … then …", "turn my X into Y", "write/draft/summarize me a … ...

Help users operate the published Composio CLI to find the right tool, connect accounts, inspect schemas, execute tools, subscribe to trigger events with `composio listen`, script workflows with `composio run`, and call authenticated app APIs with `composio proxy`. Use when the user asks how to do something with `composio`, wants to run a known tool slug, needs to discover a slug with `composio search`, fix a missing connection with `composio link`, inspect tool inputs with `--get-schema` or `...

Import a Rome skill from a URL, a pasted SKILL.md, or a plain-language description — validate it against Rome's frontmatter parser, preview the final file, and install it into the user-skills carrier app after the guardian confirms.

Turn a guardian's plain-language automation into a runnable Rome workflow app, in one conversation. Use whenever the guardian wants to build, create, set up, or design an automation or workflow ("every morning summarize my unread emails", "when I save a link, fetch and summarize it", "for each new ticket, look up the customer and draft a reply"). You shape the idea into a short spec, get the guardian's approval, then build and install the workflow yourself — no separate planner or builder.

File one GitHub issue from a description the user gives — classify it as a bug report, feature request, or task spec, gather what the body needs from the tracker and the code, ask the user only for what those cannot answer, draft it in the repo's issue format, and create it with `gh` after a go-ahead. Use when the user says "file an issue / bug / feature request / task for <description>".