Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python version mismatch.

Triage failing @novu/agent-evals scenarios to decide whether a failure is real or flaky, and whether to fix the playbook/prompt or the test (grader, tape, scenario, or judge). Use when an agent-evals scenario fails, when the user asks why an eval is red, or when deciding whether to fix the test or the prompt.

Run e2e tests for the API service. Use when the user wants to run API E2E tests.

Add a new chat channel's layer-2 dashboard onboarding — the connected-state "What's next" / "FOR YOUR USERS" developer-rollout guide plus its connected details page — in apps/dashboard, following the existing Slack, MS Teams, and Telegram pattern. Use when a connected agent integration needs a per-provider "what's next" guide (recap + dev steps with @novu/react ConnectButton snippet), a <Channel>AgentConnectedDetails view, and the resolver/registry wiring under components/agents/agent-integration-guides.

Systematic code refactoring based on Martin Fowler's methodology. Use when users ask to refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells, or improve code maintainability. This skill guides through a phased approach with research, planning, and safe incremental implementation.

Three.js post-processing - EffectComposer, bloom, DOF, screen effects. Use when adding visual effects, color grading, blur, glow, or creating custom screen-space shaders.

Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.

Upgrade the pinned Flask-AppBuilder (FAB) dependency in the Apache Airflow FAB provider (`providers/fab/`). Bumps the exact `flask-appbuilder==` pin and its mirror constant, regenerates `uv.lock`, drives the `test_fab_alignment.py` drift tripwire, reviews the vendored security-manager `override.py` against the new upstream FAB, and conditionally re-vendors static assets / DB migrations. Use when asked to "upgrade FAB", "bump flask-appbuilder", or move the FAB provider to a newer Flask-AppBuilder release.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Add or update translations for the Apache Airflow UI. Guides through setting up locales, scaffolding translation files, translating with locale-specific guidelines, and validating results. Use when working with i18n tasks in airflow-core/src/airflow/ui/public/i18n/locales/.

Use this skill to triage the open PR queue before a release. Classifies every open PR into must-merge, candidate, superseded, or deferred; writes a working triage doc; and runs the merge loop end-to-end. Designed for the pre-release "PR speedrun" pass where a solo maintainer wants to clear the inbound backlog in a single session.

Wire syncable entity services into NestJS modules, create service layer and resolvers for Twenty entities. Use when registering builders, validators, and action handlers in modules, creating business services, or exposing entities via GraphQL API with proper exception handling.

Create validation logic and migration action builders for syncable entities in Twenty. Use when implementing business rule validation, uniqueness checks, foreign key validation, or building workspace migration actions for syncable entities. Validators never throw and never mutate.

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.

Run Remotion formatting and style checks until they pass. Use when the user asks to fix formatting or run the formatting command.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Support text resizing to 200%. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid images of text. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when auditing robots meta tags. Applies to any important landing page, article, or product page that should appear with a description in search results.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Use landmark regions correctly. Check native semantics first, then inspect keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Use when reviewing scripts, client components, bundles, or runtime behavior related to Prefer immutable data patterns. Inspect both source code and the browser execution path so fixes target the real bottleneck or bug.