ably

Run a full code review of the current change — fan out every relevant review concern across independent subagents (the local review skills plus the ably-skills code-review-* plugin) and synthesise one consolidated report. Read-only; never edits code.

Audit whether the demos under demo/ are still current with a change — they compile against and use the changed public API correctly, showcase new or renamed capabilities, and keep their e2e test coverage current. Read-only; produces a conformance report and never edits code.

Review documentation for accuracy, completeness, and conformance to the project's doc standards — whether a code change left docs/ stale or incomplete, or as the review half of the docs writing loop. Read-only; produces a conformance report and never edits code or docs.

Audit whether changed code conforms to the project's own rules in .claude/rules/ and the conventions in CLAUDE.md. Read-only; produces a conformance report and never edits code.

Audit whether the .claude/rules/* guidance still matches the code after a change — stale conventions, drifted examples, rules describing removed behaviour, or new conventions the change introduces that a rule should capture. Read-only; produces a conformance report and never edits code or rules.

Write or improve markdown documentation for the AI Transport SDK. Follows the project's doc principles (atomic pages, problem-first framing, one path then depth) and the established style from the docs that received positive feedback.

Generate a commit message for the current staged changes and commit

Stage and commit all uncommitted changes as a series of logical, well-ordered commits

Scaffold new CLI commands with tests for the Ably CLI (oclif + TypeScript). Use this skill whenever creating a new command, adding a subcommand, migrating a command, or scaffolding a command with its test file — even if described casually (e.g., 'I need an ably X Y command', 'can you build ably rooms typing subscribe', 'we should add a purge command to queues'). Do NOT use for modifying existing commands, fixing bugs, or adding tests to existing commands.

Review the entire Ably CLI codebase against the standards and conventions defined in the ably-new-command skill. Use this skill whenever asked to audit, review, check alignment, verify compliance, or find deviations from the command creation patterns — even casually (e.g., 'review the codebase', 'check if commands follow patterns', 'audit the codebase', 'find deviations', 'how well do we follow conventions'). Do NOT use for creating new commands or fixing individual bugs.

Review the current branch's changes against the standards and conventions defined in the ably-new-command skill. Use this skill whenever asked to review current changes, check a branch, review a PR, or validate work-in-progress — even casually (e.g., 'review my changes', 'does this branch look good', 'check my work', 'review before PR'). Do NOT use for full codebase audits (use ably-codebase-review instead), creating new commands, or fixing individual bugs.

Write or refresh an Ably documentation page in this repo. Use when creating a new MDX page, rewriting an existing one, or applying the page-design principles to docs work. Captures the principles, page-type templates, writing standards, and code-accuracy checks distilled from the April 2026 wireframe workings used for the AI Transport refresh.

Translates inline JavaScript example code to Swift

ALWAYS use when diagnosing Ably issues — messages not arriving, presence not updating, connection failures, auth errors (40101, 40142, 40160), channel lifecycle problems, push notification issues, Chat room issues, Spaces member/cursor issues, or any Ably error code. Provides Ably CLI commands to observe live traffic, inspect state, and simulate clients. Not for building new Ably integrations (use using-ably skill instead).

ALWAYS use when building realtime features with Ably — messaging, chat, collaboration, presence, or AI token streaming. Covers product and SDK selection (Pub/Sub vs Chat vs Spaces vs LiveObjects), authentication (JWT, token auth, authUrl), channel design, React integration, and critical mistakes like missing Chat attach(), client-side API key exposure, and creating Ably clients inside components. Fetches current docs from ably.com/llms.txt before generating code. Not for general WebSocket or non-Ably realtime libraries.

Translate the UTS pseudocode test specs in a whole module directory into runnable Swift tests in the ably-cocoa UTS test target. Takes a UTS module directory (e.g. <cloned-ably-specification-repo-path>/uts/objects), validates its structure, resolves the target test directories, lets you pick a tier (unit/integration/proxy) and which specs, then derives a Swift test per spec. Usage: /uts-to-swift <path-to-uts-module-directory>

Generate a commit message for the current staged changes and commit