braket-tickets

Use when reviewing a pull request for bugs, CLAUDE.md compliance, Convex backend correctness, and Angular frontend best practices. Triggers on "review PR", "code review", or a PR number/URL.

Use when running E2E tests, checking if E2E tests pass, or validating changes with Playwright tests. Covers affected-only runs (preferred), full suite, parallel execution, and port isolation for concurrent runs.

Use when a PR needs finishing — CI is failing, code review comments are pending, or a PR opened by an autonomous agent needs human-quality polish before merge. Also use when user says "go-pr-finish" followed by a PR number or URL.

Use when a less powerful model (Sonnet, Haiku) needs to implement a feature or bugfix with safety rails — always works from an isolated worktree and new branch, submits a PR to develop instead of merging directly. Also use when user says "go-pr" followed by a task description.

Use when starting a feature, bugfix, or task that needs the full development cycle — brainstorm through landed commit on develop. Also use when user says "go" followed by a task description.

Use when starting a cross-layer feature touching frontend, backend, and tests simultaneously, or when user says "go team". Uses Agent Teams for parallel coordinated implementation instead of subagents.

Use when autonomously testing a running web app via Playwright MCP for extended unattended sessions using Agent Teams — exploratory QA, smoke tests, regression hunts, and filing bugs to Linear with maximum browser throughput

Use when working with color naming, color theory, color spaces, color definitions, or any task involving color knowledge - palettes, ramps, gradients, conversions, accessibility, perceptual matching, pigment mixing, print-vs-screen color, CSS color syntax, or historical color terminology. Use this skill whenever the user is choosing, comparing, generating, naming, converting, or explaining colors, even if they do not explicitly ask for "color theory."

Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration

Use when a Convex design spec needs review before implementation — covers best practices, security, performance, and code quality in four sequential audit passes with findings applied between each

How to create, structure, and publish self-contained Convex components with proper isolation, exports, and dependency management

Designs and builds Convex components with isolated tables, clear boundaries, and app-facing wrappers. Use this skill when creating a new Convex component, extracting reusable backend logic into a component, building a third-party integration that owns its own tables, packaging Convex functionality for reuse, or when the user mentions defineComponent, app.use, ComponentApi, ctx.runQuery/runMutation across component boundaries, or wants to separate concerns into isolated Convex modules.

Plans and executes safe Convex schema and data migrations using the widen-migrate-narrow workflow and the @convex-dev/migrations component. Use this skill when a deployment fails schema validation, existing documents need backfilling, fields need adding or removing or changing type, tables need splitting or merging, or a zero-downtime migration strategy is needed. Also use when the user mentions breaking schema changes, multi-deploy rollouts, or data transformations on existing Convex tables.

Schema migration strategies for evolving applications including adding new fields, backfilling data, removing deprecated fields, index migrations, and zero-downtime migration patterns

Audits and optimizes Convex application performance across hot-path reads, write contention, subscription cost, and function limits. Use this skill when a Convex feature is slow or expensive, npx convex insights shows high bytes or documents read, OCC conflict errors or mutation retries appear, subscriptions or UI updates are costly, functions hit execution or transaction limits, or the user mentions performance, latency, read amplification, or invalidation problems in a Convex app.

Initializes a new Convex project from scratch or adds Convex to an existing app. Use this skill when starting a new project with Convex, scaffolding with npm create convex@latest, adding Convex to an existing React, Next.js, Vue, Svelte, or other frontend, wiring up ConvexProvider, configuring environment variables for the deployment URL, or running npx convex dev for the first time, even if the user just says "set up Convex" or "add a backend."

Sets up Convex authentication with user management, identity mapping, and access control. Use this skill when adding login or signup to a Convex app, configuring Convex Auth, Clerk, WorkOS AuthKit, Auth0, or custom JWT providers, wiring auth.config.ts, protecting queries and mutations with ctx.auth.getUserIdentity(), creating a users table with identity mapping, or setting up role-based access control, even if the user just says "add auth" or "make it require login."

Use when reviewing implementation diffs, PRs, commits, branches, or working-tree changes before handoff, merge, or follow-up implementation

Use when the user asks to commit, finish, land, or save only the current session's changes while unrelated working-tree changes may exist. Also use when the user says "go-commit".

Use when the user asks to merge a completed local worktree branch back to develop without a PR, mark an associated Linear issue done, and clean up the worktree and branch. Also use when the user says "go-merge".

Use when a design spec or implementation plan needs full-stack review — six sequential audit passes covering Convex best practices, security, performance, code quality, Angular best practices, and frontend design

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

Use when autonomously testing a running web app via Playwright MCP for extended unattended sessions — exploratory QA, smoke tests, regression hunts, and filing bugs to Linear

Use when verifying Linear issues tagged QA are actually fixed — fetches Done issues, follows reproduction steps via Playwright MCP, and updates Linear with pass/fail verdicts

Use when writing documentation from scratch, reviewing existing docs for technical writing quality, or rewriting text for clarity. Covers knowledge base articles, guides, tutorials, READMEs, and user-facing copy.