Loading...
Loading...
Found 6,268 Skills
Payment gateway integration. Providers: SePay (Vietnamese: VietQR, bank transfer, cards), Polar (global SaaS: subscriptions, usage-based billing). SDKs: Node.js, PHP, Python, Go, Laravel, Next.js. Capabilities: checkout flows, subscription management, webhooks, QR code generation, benefit automation, tax compliance. Actions: integrate, implement, configure, handle payments/subscriptions/webhooks. Keywords: payment gateway, SePay, Polar, VietQR, bank transfer, subscription, usage-based billing, checkout, webhook, QR code, API key, OAuth2, product management, customer portal, tax compliance, MoR, recurring payment, invoice. Use when: integrating payment processing, implementing checkout, managing subscriptions, handling payment webhooks, generating payment QR codes, building billing systems.
When the user wants to add, optimize, or audit breadcrumb navigation. Also use when the user mentions "breadcrumbs," "breadcrumb trail," "breadcrumb nav," "breadcrumb links," "path navigation," "site breadcrumb," "BreadcrumbList schema," "location-based breadcrumb," "attribute-based breadcrumb," "site hierarchy display," "add breadcrumbs," or "breadcrumb SEO."
When the user wants to build an SEO data analysis system, monitor indexing/traffic/keywords/backlinks, or set up benchmarks. Also use when the user mentions "SEO data analysis," "SEO monitoring," "article database," "traffic benchmark," "penalty recovery," "SEO work document," "SEO dashboard," "keyword tracking," "ranking monitoring," "indexing report," or "backlink monitoring."
Architect programmatic SEO systems for 10K-100K+ pages with database-backed data layers, data sufficiency gating, incremental validation, crawl budget management, content enrichment pipelines, and edge delivery. Use when scaling beyond 10K pages, when builds are OOMing, when Google is not indexing all pages, or when the current in-memory architecture has hit its limits.
Build Account-Based Everything (ABX) GTM strategies for complex B2B sales. Use when working on ABM strategy, ICP scoring, messaging architecture, product launches, or pipeline acceleration for companies with <500 accounts, $100K+ deals, and 6+ month sales cycles.
Coordinate Claude Code Agent Teams through filesystem-based protocol. Use when orchestrating multiple Claude agents on parallel tasks, need task dependency management, multi-agent code review or implementation. Do not use when single-agent work suffices, task is not parallelizable.
Use the Docyrus CLI (`docyrus`) to interact with the Docyrus platform from the terminal. Use when the user asks to authenticate, list apps, query/manage data records (`ds`), manage dev app data source schema objects (`studio`), send API requests, switch environments/tenants/accounts, or discover OpenAPI specs via the `docyrus` command-line tool. Triggers on tasks involving docyrus CLI commands, terminal-based Docyrus operations, `docyrus ds list`, `docyrus studio`, `docyrus discover`, `docyrus auth`, `docyrus env`, or shell-based Docyrus workflows.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
SOPS and age encryption for secrets management in git repositories. Use when: (1) Setting up encrypted secrets in a project (initial .sops.yaml configuration) (2) Encrypting/decrypting YAML, JSON, ENV, or INI files with age keys (3) Managing age keys (generation, distribution, rotation) (4) Configuring path-based encryption rules for different environments (5) Integrating SOPS decryption in CI/CD pipelines (GitHub Actions, GitLab CI) (6) Troubleshooting SOPS decryption failures or key issues (7) Selective encryption with encrypted_regex patterns
Commerce Engine router. Use when user asks about building a storefront, setting up the SDK, authentication, products, cart, checkout, orders, webhooks, or Next.js e-commerce patterns. Automatically routes to the specific skill based on their task.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).