Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.

Write and debug JavaScript or TypeScript that uses the compromise English NLP library to match text, extract entities or numbers, customize tagging, and transform sentences. Use when the user requests compromise or the project already uses it, especially for its match syntax, selection semantics, build tiers, and plugins.

Add TypeScript strict-mode code-style rules to AGENTS.md. The rule text ships inside this skill, so write it from here, not from memory. Use when the user asks for strict-mode style rules. Not for Deno projects (use setup-agent-code-style-deno).

Estimate total token usage and cost across conversation history, system prompts, and active rules. Use when the user asks how much context or how many tokens are in use, to audit context size, or to estimate session cost.

Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from this session — one IDE, fan-out, or model comparison. Relay the other runtime's stdout verbatim. Use on run in <ide>, compare <ide> vs <ide>, try on <model>, run across models.

Look up the current US import duty on one HTS product from one country — the HTS column rate (MFN, trade-agreement or column 2) plus the Section 301 and 232 duties in chapter 99 — from the live USITC Harmonized Tariff Schedule. Use when the user asks what the US charges today on a product from a specific country, including China tariffs and other additional duties.

Look up the applied tariff on one HS6 product imported by one country from another (MFN, partner-specific preferential, and the best available applied rate), from UNCTAD TRAINS via World Bank WITS. Use when the user asks what duty a specific product pays between two specific countries.

Best practices for HarmonyOS application development with ArkTS and ArkUI, covering components, state management, resources, layout, lifecycle, and accessibility. Use when writing .ets component files, using ArkUI decorators like @Component/@State/@Prop/@Link, building layouts with Column/Row/Stack/List, managing HarmonyOS app resources with $r(), or handling component lifecycle and accessibility on HarmonyOS.

Best practices for building AI agents with Google's Agent Development Kit (ADK) in Python, covering agent design, tools, sessions, memory, artifacts, evaluation, and deployment. Use when building LLM agents or multi-agent systems with ADK, defining ADK tools, wiring up sessions/state/memory, working with ADK artifacts, writing agent evals, or deploying ADK agents to Vertex AI Agent Engine or Cloud Run.

Orchestrate phased software implementation using a team of engineers. Delegates research, planning, implementation, code review, and QA validation to separate engineers following a pipeline defined in .planning/PLAN.md. Use when the user asks to execute a multi-phase implementation plan, run a team-based development workflow, or implement features using planning/implementation/review stages.

Strip AI-writing tells AND make prose clearer, stronger, and more concise. Use when editing or reviewing text to sound natural and human, or when writing or editing any prose humans will read: documentation, commit messages, pull request descriptions, error messages, UI copy, help text, comments, reports, or explanations. Detects and fixes AI patterns (inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, filler phrases) and applies Strunk's Elements of Style rules for clarity and concision (active voice, positive form, definite and concrete language, omitting needless words, parallel construction).

Use when writing a KQL query against this app's Azure Log Analytics workspace to investigate Container App backend/frontend logs — production incidents, request/response tracing, or any query returning a SYN0002 parse error, an empty result you didn't expect, or a count that looks too low for the time range.

Astro pages, layouts, content collections, hydration directives and integrations. Use when adding or changing Astro pages, components or content collections, or choosing a client: directive.

Conventions for HTTP endpoints, server actions and calls to external APIs: the contract, input validation, error shapes, status codes, versioning, pagination, retries and caching. Use when adding or changing an endpoint or server action, or wiring an external API.

WCAG 2.2 AA rules for HTML, CSS and React: contrast, keyboard, screen-reader semantics, voice access, forms and tables. Use when building or changing UI components, forms, navigation or any user-facing element.

Run a comprehensive on-page SEO audit or optimization pass covering title tags, meta descriptions, header structure, content quality, internal links, image optimization, URL hygiene, and on-page schema. Use this skill whenever the user asks to optimize a page, audit on-page SEO, fix titles or meta tags, review header structure, check internal linking, improve a single URL's search performance, or write SEO-friendly copy. Triggers on on-page SEO, page audit, title tag, meta description, H1, header structure, internal links, image alt, URL slug, page optimization, optimize this page, SEO this page. Also triggers for any single-page review where ranking, click-through, or relevance signal quality is the goal, even if the user does not say 'SEO' explicitly.

Run a competitive SEO analysis comparing the user's site to chosen competitors across SERP overlap, content depth, backlink profiles, technical posture, and brand presence. Use this skill whenever the user wants to analyze competitors, find content gaps, identify backlink opportunities, understand why competitors outrank them, or benchmark against the rest of their category. Triggers on competitor analysis, competitive analysis, SERP analysis, content gap, backlink gap, why is X ranking, who is winning the SERP, beat my competitor, benchmark, market positioning. Also triggers when planning a content strategy and the question 'what are competitors doing' is implicit.

Build a multi-quarter roadmap from a backlog of ideas, requests, and ongoing initiatives. Use this skill when planning the next quarter, sequencing dependent work, balancing build vs improve vs maintain, or making the case for what NOT to do. Triggers on roadmap, quarterly planning, what should we build next, sequencing, prioritization, OKR planning, capacity planning, what's on the roadmap, plan the year, what to ship next quarter. Also triggers when stakeholders are pulling in different directions and the team needs a defensible plan.

Build customer journey maps and service blueprints that visualize the end-to-end user experience including touchpoints, emotions, friction, and underlying systems. Use this skill whenever the user wants to map a customer journey, build a service blueprint, identify friction across an experience, align teams on the user experience, or visualize touchpoints and pain points. Triggers on customer journey, journey map, service blueprint, user journey, experience map, touchpoint analysis, friction map, journey audit, end-to-end experience, customer experience map. Also triggers when the team has departmental views of users but no shared map of what the experience actually feels like.

Build production-ready frontend components with accessible markup, sensible props, defined states, and tested behavior. Use this skill whenever the user wants to build a component from scratch, refactor an existing one, design a component API, or implement a UI element with proper states and accessibility. Triggers on build a component, create a button, create a modal, create a form input, component API, props design, component states, refactor component, accessible component. Also triggers when implementing UI from a design that needs to be reusable.