发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
review-integration
Review a meter or charger integration PR or file against project patterns and rules
ca-citation-verifier
Verifies that every citation in a generated answer or document corresponds to a real, current authority with the correct proposition and pinpoint, by independent retrieval. Use as a mandatory post-processing skill for any output containing legal citations or legal propositions that require authority.
ca-multilingual-translation
Translates client documents and communications between English, French, Spanish, Chinese, and other supported languages for non-evidentiary use, preserving legal meaning where feasible and expressly not replacing certified translation. Use whenever a non-English/French document is uploaded for review or client communication requires translation.
ca-securities-disclosure-assist
Assists with drafting and reviewing Canadian securities disclosure documents, including prospectuses, AIFs, MD&A, material change reports, and MI 51-102 / NI 41-101 compliance, grounded in comparable issuer filings and governing instruments. Use when the user works on Canadian securities disclosure.
doe-icp-home-services
ICP knowledge for selling web design services to home service business owners. Use when writing cold emails, sales briefs, or any outreach targeting local service business owners. Covers the Mike persona, email copy framework (Sav zero-risk offer + Loom CTA), language translations, lead red flags, pricing psychology, and seasonal timing. Pairs with doe-learnings (which OVERRIDES this skill when in conflict), cold-email, and copywriting skills.
shopify-baseline-kpi-fetch
Standardized extraction of Shopify KPIs (revenue, AOV, abandonment) via GraphQL for weekly reports
shopify-catalog-gap-analyzer
Read-only catalog audit of <STORE_NAME> - identifies products without sufficient tags and without a shipping block at the start of the description, prioritized by business impact
shopify-cultural-calendar
Planning and alerts for cultural events (read from cultural-events.json)
tdd-red-green-refactor
Provides practical patterns for practicing the TDD Red-Green-Refactor cycle. Covers use of a unit-test Agent, principles for designing testable code, and methods for managing test coverage. Intended for use when implementing new features from Phase C onward.
svg-precision
Deterministic SVG generation, validation, and rendering. Use for icons, diagrams, charts, UI mockups, or technical drawings requiring structural correctness and cross-viewer compatibility.
text-summarizer
Generate extractive summaries from long text documents. Control summary length, extract key sentences, and process multiple documents.
digital-twin-universe
Framework for building behavioral clones (digital twins) of third-party services. Covers API surface replication, state machines, chaos injection, and twin composition for validating at volumes and rates impossible against live services.
unity-coder
Use when implementing Unity C# code to follow proper coding guidelines, naming conventions, member ordering, and Unity-specific patterns
webshop-ux-expertise
This skill should be used when the user asks to "optimize webshop conversion", "improve e-commerce UX", "design product page", "build checkout flow", "add shopping cart", "integrate agentic commerce", "make webshop accessible", "improve mobile e-commerce", "create online store", or discusses building, improving, or reviewing any webshop or e-commerce feature. Provides comprehensive 2026 conversion data, agentic commerce patterns, accessibility requirements, and technical implementation guidance.
docuseal-cli
Manage DocuSeal e-signature workflows from the terminal via the DocuSeal CLI - create templates from PDF/DOCX/HTML, send documents for signing, track submissions, and update submitters. Use when the user wants to run DocuSeal commands in the shell, scripts, or CI/CD pipelines. Always load this skill before running `docuseal` commands.
dojo-integration-test
Use this skill when the user asks to "test dojo contracts", "run integration tests", "start dojo stack", "test with torii", "verify contract behavior", mentions integration testing for Dojo/Cairo contracts, or needs to set up local katana/torii infrastructure.
agent-tool-builder
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202
distributed-tracing
Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks. Use when debugging microservices, analyzing request flows, or implementing observability for distributed systems.
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup.
plan-writing
Structured task planning with clear breakdowns, dependencies, and verification criteria.
react-native-best-practices
React Native & Expo engineering standards.
bug-report-root-cause
Produce per-item root cause analysis from bug report input. Inputs source and target where source is pasted file or linear issue and target is env scope.
api-key-rotation
Autonomously rotate API keys with usage monitoring. Intelligently switches between primary and free API keys based on usage thresholds, with caching and transparent integration across workflows. Works in Claude Code, remote agents, and scheduled routines. Stdlib-only (no external dependencies).