Results for “legenda”

Cria peças verticais 9:16 (story, reels, shorts, TikTok) respeitando as áreas seguras da interface do app, com guias, legendas acessíveis e verificação por screenshot.

Defines the LEND.AI assistant persona: identity, tone, and interaction rules for a Spanish-speaking senior mentor that teaches while working, questions decisions, and requires confirmation before acting.

Redux-Saga (generator-based) middleware for async side effects — yields declarative effects (call/put/select/takeLatest/delay) instead of imperative async code, watcher-per-slice composition, optimistic updates with rollback. Use when authoring per-slice operations.js, the rootSagas composer, or reviewing saga workers.

Establish durable brand and voice context for cross-skill consumption. Generates BRAND.md (audience, positioning, do/don't editorial rules, taboo phrases, competitor differentiation) and VOICE.md (existing persona JSON re-expressed as readable prose), both written to the project root. When present, all blog sub-skills auto-load these files before writing or reviewing. Pairs with blog-persona, which manages the structured persona JSON. Use when user says "blog brand", "create brand context", "brand voice doc", "BRAND.md", "VOICE.md", "establish editorial brand", "brand guidelines for blog".

Write and run analytical SQL queries against Redpanda SQL (Oxla), a distributed PostgreSQL-wire-compatible columnar database, including data loading, external sources, and type handling.

Create, configure, and manage AWS Lambda serverless functions for event-driven compute, including triggers, debugging, cold start optimization, and layers.

Data pipeline specialist for ML experiments. Use when the user asks to talk to Gekko, requests the data engineer, or needs DataLoader optimization.

Creates, updates, and deletes Salesforce records from Lightning Web Components using Lightning Data Service, covering record input shapes, error handling, and cache refresh strategies.

Expert en inference llama.cpp avancé (GGUF, quantization, local models, HTTP server, hardware)

Documents MariaDB-specific GRANT behavior, including privilege scope levels, implicit account creation, MariaDB-only privileges, roles, proxy grants, resource limits, and TLS options, to help write accurate GRANT statements.

Implements sibling communication between Lightning Web Components using Lightning Message Service (LMS) or the legacy pubsub utility, covering message channel definition, publish/subscribe patterns, and scope selection.

Expert en serverless (AWS Lambda, Cloudflare Workers, Vercel Edge, cold starts, contexte DZ)

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Build streaming data pipelines with Redpanda Connect using declarative YAML configs, Bloblang mappings, and component discovery. Covers running, linting, and dry-running pipelines.

Detect, validate, and generate Schema.org structured data in JSON-LD format for SEO and rich results.

WP-CLI operations via Lando — lando wp db export, lando wp db import, lando wp search-replace, lando wp search-replace --dry-run, lando wp user create, lando wp post list, lando wp plugin install, database management, maintenance mode, lando wp maintenance-mode activate, lando wp cache flush, lando wp cron event run, lando wp option update, lando wp transient delete, deploy checklist, preflight checks, destructive operations safety

Streams change data capture from PostgreSQL into Redpanda or Kafka using Redpanda Connect's postgres_cdc input, covering setup, snapshotting, and troubleshooting.

Mines SpecStory coding histories from any agent into a persistent corpus, surfaces reproducible workflows with corroborated evidence, and interactively forges chosen ones into skills installed across agent harnesses.

LongVA: Long Context Transfer from Language to Vision

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

Build a champion, do not just hope you have one. It identifies who inside the account can sell for you, arms them with the internal-sell narrative and a one-pager they can forward, and plans the multi-thread so the deal does not rest on one person. Built for B2B sales teams, customizable to your CRM and your deal process. Trigger on "who is my champion", "build a champion", "arm my champion", "this deal is single-threaded", "help them sell internally", or any multi-thread or champion-development request.

Comprehensive Stata reference for writing correct .do files. Covers syntax, options, gotchas, and idiomatic patterns. Use this skill whenever the user asks you to write, debug, or explain Stata code. Generates ready-to-run .do files for the user to execute manually.

Algorithm-first discipline: state Big-O, data structure, and algorithm family BEFORE writing loops, queries, or recursion. Catches O(n^2), N+1, and brute-force defaults.

Orchestrator — author the flow-anchored logical domain model (entities, state machines, events/commands, read models, policies, logical contracts) from an approved user-flow map, running one domain-modeling framework per session, before UX variation work

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Detect, validate, and generate Schema.org structured data. JSON-LD format preferred. Use when user says "schema", "structured data", "rich results", "JSON-LD", or "markup".

Improve, modernize, and optimize existing Stata code for performance, portability, and maintainability. Use when legacy patterns such as preserve/restore, cd,

Deploy and manage serverless functions on AWS Lambda, Cloudflare Workers, and Vercel Edge, with event-driven design and cold start optimization.

Guarda y consulta información en Engram automáticamente para mantener contexto entre sesiones, optimizando el uso de tokens y delegando exploración compleja.

Creates executable Polars dataframe contracts using Pandera's Polars backend for runtime validation of schemas, columns, and checks.

Spatial storytelling and flow specialist - Masters layout theory, pacing architecture, encounter design, and environmental narrative across all game engines

STATA code pattern library for empirical archival accounting research. Provides tested syntax from 126 peer-reviewed JAR (Journal of Accounting Research) replication files (2017-2025). Use when the user asks procedural questions like "How do I implement [method]?" or "Show me code for [technique]" — including: entropy balancing, propensity score matching (PSM), difference-in-differences (DiD), regression discontinuity (RDD), instrumental variables (IV), event studies (CAR/BHAR), survival analysis, Fama-MacBeth regressions, bootstrap, quantile regression, reghdfe/xtreg/areg, clustering standard errors, fixed effects, esttab/outreg2 table formatting, winsorization, leads/lags. Users can specify their variables (e.g., treatment, outcomes, controls) and receive adapted syntax. NOTE: This skill provides code patterns from published papers, not research design advice.