Loading...
Loading...
Found 1,885 Skills
Suggest improved text for changelog YAML files against current Elastic standards. Mirrors the pattern catalog from docs-review-changelog to provide consistent fixes. Includes type-title alignment, product/surface context for titles, description verb-tense (third-person present), and technical content assessment. Features repository-aware area validation and enhanced confidence scoring. Supports single files or directories. Fetches canonical guidance to stay in sync. Use after review identifies quality issues, or when drafting new changelogs.
Use when securing a Roblox experience against exploiters or designing its networking: RemoteEvent, RemoteFunction or UnreliableRemoteEvent design, validating remote arguments on the server, remote spam and rate limits, speed hacks, teleport or fly hacks, kill aura or hitbox abuse, hit validation under lag, network ownership and fling exploits, ProximityPrompt or ClickDetector abuse, honeypots, kick and ban policy, Server Authority (AuthorityMode) setup, bandwidth or payload size problems, or after an exploit (free items, infinite money, duplicated items).
Tests whether real visitors understand a site by simulating personas across the sophistication spectrum (expert to novice), reporting confusion, friction, and first impressions rather than technical correctness. Use before launch, after a redesign, or when a landing page needs clarity validation. Requires a running dev server and browser MCP tools.
Provisions BigQuery datasets, ingests staged Parquet files directly into native BigQuery tables by using bq load, and deploys already-translated views from local or Cloud Storage BigQuery Migration Service (BQMS) translation outputs. Use when provisioning target BigQuery datasets for warehouse migrations, batch loading staged Parquet files into native BigQuery tables by using bq load, auditing loaded table row counts, or deploying already-translated BigQuery views into a target dataset. Don't use for extracting source database catalog metadata, translating SQL queries, views, stored procedures, or DDL schemas to GoogleSQL (use bigquery-migration-sql-translator), exporting or unloading source database tables (such as Snowflake, Databricks, Teradata, or Oracle) to Parquet on Cloud Storage, or running post-migration cross-database data validation.
Retrieve engineering knowledge before implementation, architecture, troubleshooting, deployment, or risk-related changes; after a substantive engineering task is complete and the user confirms that validation passed, assess whether the result should be captured, checked, and reviewed through the relevant one of the four knowledge workflows, and wait for user authorization before publishing it.
Use when symfony form types validation
Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.
Converts Stitch designs into modular Vite and React components using system-level networking and AST-based validation.
Send an independent judge that is not the author: a fresh evaluator subagent that checks finished work against pass criteria written before it was built (evaluator mode), or audits a batch against its source of truth (audit mode), with evidence for every verdict and never a fix. Use when the owner asks for an evaluator, reviewer, auditor or judge, or says 'send a judge', 'evaluate this', 'check my work with a fresh agent', 'get a second agent to review this', 'audit this folder', 'audit my registry', 'verify this against the source of truth', or 'LLM-as-judge'. Runs only when asked; it does not fire on its own at the end of a task. Not for checks a machine can run (tests, schema validation, a search that must return zero), not for hundreds of identical units, and not for fixing anything.
Explicitly launch an independent outside-expert consultation via Codex. Use only when the user directly asks to run this workflow or asks another expert/agent for an independent second opinion. Do not infer it from ordinary review, feedback, validation, planning, or discussion about the skill itself.
Create, revise, embed, or troubleshoot accessible SVG diagrams and illustrations for slide decks, documents, and other static artifacts, with portable sizing, layout, style, and validation guidance.
Boas práticas, padrões de qualidade e validação para Dockerfile, imagens Docker e docker-compose. Use esta skill sempre que estiver escrevendo, revisando, otimizando ou validando Dockerfile, .dockerignore, docker-compose.yml, compose.yaml ou executando comandos docker/docker compose — inclui decisão de multi-stage, segurança, camadas, healthchecks, networks, volumes, orquestração local para desenvolvimento e um gate de validação com hadolint, build e execução em compose. Ativar mesmo quando o usuário não pedir explicitamente por 'boas práticas' ou 'validação', bastando que a tarefa envolva criar, revisar ou verificar artefatos Docker. O gate roda automaticamente sempre que artefatos Docker forem criados, alterados ou revisados, e a entrega termina num relatório de criação e validação com evidências por nível.