Modern TypeScript conventions for library-agnostic code — strict mode, naming, type annotations, the type system (generics, utility types, conditional and mapped types), discriminated unions, error handling, async patterns, immutability, and project structure. Use when the user asks to "write TypeScript code", "create a TypeScript module", "define TypeScript types", "add type annotations", "use generics", "handle errors in TypeScript", "set up tsconfig" or "organize a TypeScript project", or whenever writing any TypeScript that is not tied to a specific library or framework. Does not cover React or other UI frameworks (react-best-practices, react-feature-sliced-design), CLI packaging and npm publishing (npx-package), plain JavaScript with no types, or service-specific APIs such as DynamoDB (aws-dynamodb-best-practices).

Insurance underwriting domain knowledge for building automated submission-processing systems. Use when designing or implementing underwriting pipelines, document-extraction agents, compliance workflows, HITL review systems, or decision-package assembly for insurance carriers or MGAs. Covers the submission-to-bind lifecycle, document extraction patterns, compliance gates (sanctions, licensing, clearance), human-in-the-loop design for regulated financial services, confidence calibration for extracted fields, operating-mode progression from manual to automated, and evidence traceability. Domain knowledge only — for LangGraph and AgentCore implementation patterns see langgraph-agentcore.

Modern TypeScript conventions for library-agnostic code — strict mode, naming, type annotations, the type system (generics, utility types, conditional and mapped types), discriminated unions, error handling, async patterns, immutability, and project structure. Use when the user asks to "write TypeScript code", "create a TypeScript module", "define TypeScript types", "add type annotations", "use generics", "handle errors in TypeScript", "set up tsconfig" or "organize a TypeScript project", or whenever writing any TypeScript that is not tied to a specific library or framework. Does not cover React or other UI frameworks (react-best-practices, react-feature-sliced-design), CLI packaging and npm publishing (npx-package), plain JavaScript with no types, or service-specific APIs such as DynamoDB (aws-dynamodb-best-practices).

Provides up-to-date FastMCP API patterns for tools, resources, prompts, server composition, authentication, and deployment. Use when the user asks to "create an MCP server", "build an MCP tool", "add an MCP resource", "define MCP prompts", "set up FastMCP", "run an MCP server", "expose tools via MCP", "mount MCP sub-servers", "configure MCP transport", "add authentication to MCP", "test an MCP server", "use the MCP client", or when writing any Python code that uses the fastmcp package. Does not cover the MCP protocol spec, the TypeScript MCP SDK, or configuring MCP servers in Claude Code settings.

Motion / animation context for the `use_figma` MCP tool — animating Figma nodes via manual keyframes, animation styles, easing, and timeline duration. Load alongside figma-use whenever a task involves adding, editing, or inspecting animation on a node. Also covers working with custom animation styles.

Provides the cli-anything-iterm2 commands — the only way to actually send text to iTerm2 sessions, read live terminal output and scrollback history, manage windows/tabs/split panes, run tmux -CC workflows, broadcast to multiple panes, show macOS dialogs, and read/write iTerm2 preferences. Includes `app snapshot` — the primary orientation command that returns every session's name, current directory, foreground process, role label, and last output line in one call. Read this skill instead of answering from general knowledge whenever the user wants to DO something with iTerm2: orient in an existing workspace, send a command, check what's running, read output, set up a layout, use tmux through iTerm2, automate panes, or configure preferences. Also read for questions about iTerm2 shell integration or scrollback. Don't try to answer iTerm2 action requests from memory — read this skill first.

Interview employees to identify recurring daily work, office workflows, and repetitive tasks that can be automated, co-piloted, or supported by AI. Use when the user wants to find what AI can take off their plate, map available tools such as ChatGPT/OpenAI, Claude, Microsoft Copilot, Excel or PowerPoint add-ins, Google Workspace, no-code/RPA tools, coding agents, or internal automation platforms, and write tool-aware specs with fallback paths.

Ships pull requests to open-source projects you don't maintain — CONTRIBUTING compliance, PR-size/scope checks, minimal-diff implementation, AI-disclosure PR descriptions, and rebase or bot-review replies. Use for 提 PR / 上游 PR / 贡献代码, "open a PR", "fix this upstream", "rebase against main", "respond to the bot review". Not for reviewing PRs as maintainer (use github-review-pr) or general GitHub CRUD (use github-ops).

Build and deploy a Coralogix dashboard for a given service from its logs, spans, metrics, and service specs. Discovers telemetry via cx CLI commands, emits importable Coralogix JSON, verifies every PromQL and DataPrime query live through the `cx` CLI, and creates or updates dashboards via `cx dashboards create` and `cx dashboards replace`. Use whenever the user asks to create, build, generate, deploy, update, replace, or modify a Coralogix dashboard, monitoring dashboard, or observability dashboard for a service, app, or pipeline.

Add a new built-in (pre-built) LLM classification evaluator to the Phoenix evals libraries, and optionally promote it to a server-side dataset evaluator. Use when working in the Phoenix repo and asked to add a new built-in eval, pre-built metric, builtin evaluator, or LLM-as-a-judge template that ships with arize-phoenix-evals / @arizeai/phoenix-evals, or to promote an existing one to the dataset evaluators UI. Do not use for writing a user's own custom evaluator for their app (use phoenix-evals).

Builds an eval plan for an AI feature - error analysis on real traces, failure-mode ranking, code checks and binary LLM judges validated against human labels, CI tests, production monitoring, and a launch bar. Use when you ask how do we eval this, how do I test an AI feature, our LLM outputs are inconsistent, are the evals good enough, LLM-as-judge, hallucinations, or what accuracy is good enough to launch. Draws on 41 Lenny's Podcast guests incl. Hamel Husain, Shreya Shankar and Sander Schulhoff.

Test-driven development and testing patterns for Rails applications. Drives implementation from tests using an outside-in approach with RSpec, Capybara, and FactoryBot. Use when building new features, writing or improving tests, adding test coverage, fixing bugs with a test-first workflow, or when the user mentions TDD, test-driven, test-first, outside-in, spec plan, RSpec, Capybara, system specs, model specs, testing patterns, writing tests, or improving test coverage.

Find and fix issues from Sentry. Use when asked to fix Sentry errors, debug production issues, investigate exceptions, or resolve bugs reported in Sentry. Methodically analyzes stack traces, breadcrumbs, traces, and context to identify root causes.

RoleModel's Rails conventions where they differ from what an agent writes by default: flash wording, the status for failed saves, Simple Form for every form, how route concerns pass the parent type, and two gotchas (`params.expect` with nested attributes, and Lexxy rich-text change events). Use when writing or reviewing a Rails controller, route, form, or view in a RoleModel app. Also use when the user says things like "add a controller for", "build the form for", "add routes for", "add comments to", "why isn't my nested form saving", or "review this controller".

Release vercel-plugin — run gates, bump version, generate artifacts, commit, and push. Use when asked to "release", "ship", "bump and push", or "cut a release".

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

Upgrade a project to a newer django-modern-rest (dmr) release. Use when bumping the django-modern-rest version, when a dependency update breaks imports from `dmr`, or when asked to migrate to a new dmr release. Applies the official migration prompt of every release in between, in order.

Migrate an existing Django auth API from dj-rest-auth to django-modern-rest, moving account flows onto django-allauth headless and rebuilding the transport layer with dmr controllers and auth classes. Use when replacing dj_rest_auth login/logout/registration/password/MFA/social views and their DRF serializers.

Migrate an existing Django API from django-ninja/ninja-extra to django-modern-rest while preserving routes, request/response contracts, auth, throttling, and test coverage. Use when replacing NinjaExtraAPI/api_controller/http_* handlers/ninja.Schema with dmr controllers/routers and typed DTOs.

Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right before walking into a meeting. Different from /minutes-prep — brief is the fast hook-fireable version that doesn't ask questions and doesn't set goals. Use brief when speed matters; use prep when the user wants to think hard about goals first.