Skip to content

Recently active skills

Trending is calculated from star growth this site has recorded itself. No history is estimated or back-filled.

Not enough history yet: 3 of 7 days recorded. Until then this list is ordered by the most recent content change.

77104 skills

sdd-archiveLeandroBenjaminL/lend-aiClose the SDD cycle: sync delta specs to main specs, merge changes, update CHANGELOG, and persist final state. Consolidate, don't discard. Trigger: After successful sdd-verify. Never archive with open CRITICAL issues.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-designLeandroBenjaminL/lend-aiTraduce specs (QUÉ) en un plan técnico concreto (CÓMO). Documenta decisiones de arquitectura, data flow y cambios de archivos. Trigger: Después de sdd-spec para diseñar la implementación técnica.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-exploreLeandroBenjaminL/lend-aiInvestiga el código y el dominio del problema ANTES de proponer un cambio. Entender antes de actuar. Trigger: Investigar una idea, feature, bug o área del código antes de decidir si amerita un cambio formal.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-initLeandroBenjaminL/lend-aiInicializa el ciclo SDD en un proyecto — detecta stack, testing, convenciones y configura el backend de persistencia. Trigger: "sdd init", "iniciar sdd", o al arrancar un proyecto nuevo en el ecosistema.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-onboardLeandroBenjaminL/lend-aiGuía al usuario por un ciclo SDD completo de principio a fin usando su codebase real. Aprender haciendo. Trigger: Para hacer onboarding de un usuario nuevo en el ciclo SDD.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-proposeLeandroBenjaminL/lend-aiCrea la propuesta de cambio: el qué y por qué. Declaración de intención antes de invertir tiempo en specs y diseño. Trigger: Después de exploration o con input directo del usuario, para formalizar una idea como change proposal.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-specLeandroBenjaminL/lend-aiEscribe especificaciones técnicas en Given/When/Then. Describe QUÉ debe hacer el sistema, no CÓMO. Trigger: Después de sdd-propose para escribir o actualizar los specs del cambio.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-tasksLeandroBenjaminL/lend-aiDivide el cambio en tareas concretas, ordenadas por dependencia y agrupadas por fase. Cada tarea es accionable y verificable. Trigger: Después de sdd-design para desglosar el cambio en tareas.Stars: 0Updated Claude CodeCodexVerifiedInstall
sdd-verifyLeandroBenjaminL/lend-aiQuality gate del ciclo SDD. Verifica que la implementación sea completa, correcta y cumpla los specs. Tests REALES, no análisis estático. Trigger: Después de sdd-apply para verificar el cambio antes de archivar.Stars: 0Updated Claude CodeCodexVerifiedInstall
security-auditorLeandroBenjaminL/lend-aiAuditoría de seguridad automatizada — SAST, DAST, escaneo de dependencias, secretos, hardening de contenedores y compliance. Trigger: Antes de cada deploy, al integrar dependencias nuevas, o al detectar prácticas inseguras en el código.Stars: 0Updated Claude CodeCodexVerifiedInstall
senior-orchestratorLeandroBenjaminL/lend-aiOrquestación profesional del ecosistema — modelo routing, delegación de agentes, arquitectura y decisiones técnicas. Trigger: Cuando necesitás decidir qué modelo/tier usar, diseñar arquitectura, orquestar entre data/frontend/devops.Stars: 0Updated Claude CodeCodexVerifiedInstall
shared-api-integrationLeandroBenjaminL/lend-aiConsumo de APIs REST con Python — requests, httpx, manejo de autenticación, rate limiting, paginación y errores. Trigger: Cuando necesitás traer datos de APIs, hacer requests HTTP, o integrar servicios externos.Stars: 0Updated Claude CodeCodexVerifiedInstall
shared-git-dataLeandroBenjaminL/lend-aiGit for data science — versioning notebooks, datasets, and pipelines. DVC, nbstripout, .gitignore, and reproducible data workflows. Trigger: When working with git in data science projects, committing notebooks, managing datasets, or setting up a data repo.Stars: 0Updated Claude CodeCodexVerifiedInstall
skill-creatorLeandroBenjaminL/lend-aiCrea nuevas skills para el ecosistema siguiendo el estándar Agent Skills. Template, estructura de carpetas y registro automático. Trigger: Cuando querés crear una skill nueva, agregar instrucciones para la IA, o documentar patrones.Stars: 0Updated Claude CodeCodexVerifiedInstall
skill-registryLeandroBenjaminL/lend-aiGestiona el registro central de skills — sync skills/ con AGENTS.md y registry/AGENT_REGISTRY.md, detecta skills huérfanas o faltantes. Trigger: "update skills", "skill registry", "actualizar skills", o después de instalar/remover skills.Stars: 0Updated Claude CodeCodexVerifiedInstall
sql-analysisLeandroBenjaminL/lend-aiAnálisis de datos con SQL — joins, window functions, CTEs, subqueries. Consultas eficientes y legibles para extraer insights directamente de la DB. Trigger: Cuando necesitás consultar bases de datos, hacer análisis en SQL, joins, subqueries, o window functions.Stars: 0Updated Claude CodeCodexVerifiedInstall
statistical-testingLeandroBenjaminL/lend-aiTests de hipótesis con SciPy — elige el test correcto según los datos, interpretá p-values con cuidado, y evitá falsos positivos. Trigger: Cuando necesitás hacer tests de hipótesis, validar significancia estadística, o comparar grupos.Stars: 0Updated Claude CodeCodexVerifiedInstall
streamlitLeandroBenjaminL/lend-aiDashboards interactivos con Streamlit — de 0 a app en minutos. Visualizaciones en vivo, filtros, carga de archivos y despliegue. Trigger: Cuando necesitás crear dashboards, apps web interactivas, o visualizar datos con Streamlit.Stars: 0Updated Claude CodeCodexVerifiedInstall
time-series-analysisLeandroBenjaminL/lend-aiAnálisis de series temporales — tendencia, estacionalidad, forecasting con Prophet, statsmodels, y Machine Learning. Trigger: Cuando trabajás con datos de fecha/hora, tendencias, estacionalidad, forecasting, o series de tiempo.Stars: 0Updated Claude CodeCodexVerifiedInstall
web-scrapingLeandroBenjaminL/lend-aiExtracción de datos de sitios web — requests + BeautifulSoup, Selenium, y respeto por robots.txt y rate limiting. Trigger: Cuando necesitás scrapear sitios web, extraer datos de HTML, o automatizar navegación.Stars: 0Updated Claude CodeCodexVerifiedInstall
youtube-transcriptLeandroBenjaminL/lend-aiExtrae y procesa transcripciones de YouTube — obtiene el texto completo de subtítulos y genera resúmenes estructurados. Trigger: Cuando necesitás entender el contenido de un video de YouTube, extraer su texto, o generar un resumen estructurado.Stars: 0Updated Claude CodeCodexVerifiedInstall
agent-browseravibebuilder/claude-primeBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.Stars: 127Updated Claude CodeCodexVerifiedInstall
askavibebuilder/claude-primeAnswer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why', 'what does this do', 'what is the purpose of', 'explain', 'what's the difference', 'compare', or 'what are the tradeoffs' — even when referencing specific files, code snippets, or inline code. The key signal is the user wants to UNDERSTAND something, not change it. Do NOT trigger for requests to build, fix, plan, review, research, or add/modify code.Stars: 127Updated Claude CodeCodexVerifiedInstall
cookavibebuilder/claude-primeImplement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a search/filter, or any other hands-on coding task. This is the default skill for all 'build this', 'add this', 'create this', 'wire up', 'implement' requests. Covers the full cycle: clarify requirements, plan if needed, write code, verify, and review. Do NOT use for pure research, debugging, documentation, or explanation — only when the user wants working code delivered.Stars: 127Updated Claude CodeCodexVerifiedInstall
create-docavibebuilder/claude-primeUse when the user wants to save knowledge as a file so others don't have to rediscover it — "turn this into a doc", "write this up", "document how X works", "we figured this out and want to capture it", "nobody should have to figure this out again". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).Stars: 127Updated Claude CodeCodexVerifiedInstall
diagnoseavibebuilder/claude-primeInvestigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden unexplained changes in metrics or behavior, works locally but not in staging/production, inconsistent or intermittent failures, correct code producing wrong results, operations succeeding but having no effect, environment-specific failures, duplicate executions, stale data, or any "why did this change?" or "why is this happening?" situation. Covers infrastructure anomalies (cache hit rates dropping, latency spikes, queue behavior shifts) as well as code bugs. The key signal is confusion about root cause, not a request to implement a known fix. Do NOT use for feature requests, known fixes, planning, or documentation tasks.Stars: 127Updated Claude CodeCodexVerifiedInstall
discussavibebuilder/claude-primeBrainstorms and debates approaches, then drives toward an actionable decision. Use whenever someone needs a thinking partner for a decision they're facing: 'discuss', 'debate', 'brainstorm', 'weigh options', 'tradeoffs', 'should I do X or Y', 'help me decide', 'I'm torn between', 'sanity check my thinking', or 'what do you think about'. The user must be asking for help reasoning through a choice — not asking to build, fix, evaluate, plan, or modify something (even if the topic involves this skill itself). Picks the right decision lens, surfaces tradeoffs and blind spots, pushes back when reasoning is genuinely weak, and never implements.Stars: 127Updated Claude CodeCodexVerifiedInstall
docs-seekeravibebuilder/claude-primeFetch up-to-date documentation for any library, framework, API, or service into context. Use when the user wants to look up API references, check function signatures or required fields, find feature-specific docs, or verify how an external tool actually works. Triggers for queries about third-party libraries like Stripe, SQLAlchemy, Tailwind, FastAPI, shadcn, Drizzle, Hono, Better Auth — any time the answer lives in official docs rather than in the project codebase. Use this instead of guessing from trained knowledge, which is stale.Stars: 127Updated Claude CodeCodexVerifiedInstall
fixavibebuilder/claude-primeFix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.Stars: 127Updated Claude CodeCodexVerifiedInstall
frontend-designavibebuilder/claude-primeBuilds distinctive, production-grade UIs that avoid generic AI aesthetics. Use whenever the user wants to build, restyle, or give visual direction to any interface — pages, dashboards, landing pages, components, onboarding flows, mobile screens, or design systems — even without an explicit 'design' request. Also triggers for: picking an aesthetic direction, improving the look of a dull/generic existing page, adding visual personality, or choosing colors/typography. Includes a bundled design intelligence database for concrete guidance across web (React, Next.js, Vue, Tailwind) and mobile (React Native, Flutter, SwiftUI).Stars: 127Updated Claude CodeCodexVerifiedInstall