Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

Design durable workflows with Temporal for distributed systems. Covers workflow vs activity separation, saga patterns, state management, and determinism constraints. Use when building long-running processes, distributed transactions, or microservice orchestration.

Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for "review this", "code review", "review the last commit", "review my PR", "is this over-engineered", /ponytail-review.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

Feature flags, A/B tests, and gradual rollouts with Vercel Flags, in any app or framework. Use whenever the user is planning, adding, or changing a feature flag, toggle, kill switch, experiment, percentage rollout, or targeting rule, or wants to gate or hide a feature for some users, even before a library or provider is chosen. Covers choosing an integration (Flags SDK, `@vercel/flags-core`, OpenFeature), the Vercel dashboard, the `vercel flags` CLI (create, inspect, set, split, rollout, rules, segments, evaluations, archive), OIDC vs SDK keys, `FLAGS_SECRET`, and Flags Explorer overrides. For `flag()` declarations, adapters, precompute, and the Flags Explorer endpoint in Next.js or SvelteKit code, load the `flags-sdk` skill.

Manages and syncs AI CLI skills across 50+ tools from a single source. Use this skill whenever the user mentions "skillshare", runs skillshare commands, manages skills (install, update, uninstall, sync, audit, check, diff, search), or troubleshoots skill configuration (orphaned symlinks, broken targets, sync issues). Covers both global (~/.config/skillshare/) and project (.skillshare/) modes. Also use when: adding new AI tool targets (Claude, Cursor, Windsurf, etc.), setting target include/exclude filters or copy vs symlink mode, using backup/restore or trash recovery, piping skillshare output to scripts (--json), setting up CI/CD audit pipelines, or building/sharing skill hubs (hub index, hub add).

Add tasks, backlog items, bugs, chores, ideas, follow-ups, or draft issues to the Bangle 2 GitHub Projects board. Use when the user says "add a task", "put this on the board", "make a project task", "track this", "add a backlog item", or asks Codex to create a draft task in the bangle-io GitHub project.

Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling

Use when creating, extending, debugging or publishing a Lightweight Charts™ plugin — a custom series, a series primitive or a pane primitive — or when turning a chart idea ("I want the chart to show/draw X") into a working plugin. Covers choosing the plugin type, scaffolding with create-lwc-plugin, building on @tradingview/lwc-toolkit instead of hand-rolled helpers, which of the official plugin packages to read as the reference implementation, where the docs are, and the autoscale, whitespace, visible-range, hit-test and conflation mistakes every plugin author makes once. Reach for it whenever the user mentions a custom series, primitive, renderer, drawing on the chart canvas, lwc-plugin, plugin-examples, the toolkit, or the plugin catalog — even if they never say the word "plugin".

Analyze PostHog insights, dashboards, or teams beyond the current project by querying the prod Postgres replicas synced into the dogfood data warehouse (US project 2, "PostHog App + Website"). Use when asked to analyze insights across all teams or projects, another team's insights, or fleet-wide insight/dashboard usage — cases where `system.insights` only returns the current project's rows and the agent would otherwise report the data as inaccessible. Covers the synced table names for US and EU and the column-verification workflow.

Pull and interpret production experiment query-performance data from the staff-only `/api/debug_ch_queries` endpoints backing the `/experiments/staff` scene: slowest experiment queries, precompute read/build health, and preaggregation cache footprint. Covers prod-US and prod-EU via a `query_performance:read` personal API key, all query params, and response field semantics (exception codes, exposure paths, precompute skip reasons, job states). Use when investigating slow or failing experiment queries, precompute regressions, 307/159/241 errors, preaggregation table growth, or when asked how experiment query performance or the precompute rollout is doing in production.

Carries a code change through to a tested, verified and reviewed local change, loading the stage skill for each step: planning, test-first implementation, debugging, verification and review. Use when a request asks for code to change, whether it arrives as an approved ticket or a one-line message: a bug fix, a failing test or crash, a small feature or flag, a behavior change, or review comments to fix. Not for questions about the code, for merging or deleting a finished branch, or for deciding which review comments to accept without changing code. Use it whenever the work will change code, even when the user does not mention tests, review or a pull request.

Carries a code change through to a tested, verified and reviewed local change, loading the stage skill for each step: planning, test-first implementation, debugging, verification and review. Use when a request asks for code to change, whether it arrives as an approved ticket or a one-line message: a bug fix, a failing test or crash, a small feature or flag, a behavior change, or review comments to fix. Not for questions about the code, for merging or deleting a finished branch, or for deciding which review comments to accept without changing code. Use it whenever the work will change code, even when the user does not mention tests, review or a pull request.

Create a GitHub pull request with the project's PR template fully populated. Analyzes the branch diff, fills in "What changed", "Issue", "How to test", "A11y impact", "Definition of Done", and other sections. Use this skill whenever the user wants to create a PR, open a pull request, submit their branch for review, or says things like "make a PR", "open a PR", "submit this for review", or "I'm ready to create a pull request" — even if they don't use the exact phrase "pull request".

Review recent conversations with the CircleCI docs bot (Kapa) to find content gaps, wrong answers, and questions the bot could not answer. Fixes what can be fixed in docs by opening pull requests, and reports everything else with a category. Use when the user asks to review Kapa conversations, find docs gaps from the bot, run the weekly Kapa review, or check what the bot could not answer. Takes an optional period, such as "last 7 days" (default) or "last 6 weeks".

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

Shepherd an already-open pull request to a mergeable state — poll CI, triage review comments, verify each one against the source, push fixes, and keep the branch current. Use when the user asks to "babysit", "monitor", "watch", "shepherd", or "drive" a PR, asks you to "fix the CI on my PR", "handle the review comments", "get this PR green", or "wait for checks and address feedback". Picks up where the `create-pr` skill leaves off. Does not approve, merge, or close anything.

Turn an image of a poster, flyer, menu, banner or UI screenshot into a single editable HTML file — every text line becomes real editable text, every object (a product with everything on and around it, an illustration, a logo, an icon) is cut from the background as one movable piece, and the page has a built-in editor (drag, resize, edit text, layers panel, export). Use when the user sends an image and asks to make it editable, split it into layers/components, "convert to HTML", or "拆图层 / 转成可编辑的网页".