Directorio de skills

Descubre skills reutilizables para AI agents.

Busca skills reales de GitHub por tarea y revisa stars, confianza, auditoría, categoría y ruta de instalación antes de utilizarlos.

Cada recomendación conserva un vínculo claro con su repositorio, auditoría y ruta de instalación.

Resultados de búsqueda: filesystem

Directorio en inglés

A Unified Virtual Filesystem For AI Agents

3.3K
Stars
73/100
Confianza
Categoría: agent-frameworksAuditoría

kubectl port-forward manager and reverse tunnel (ngrok-like) for exposing local services publicly, with TLS termination, HTTP traffic inspection, UDP forwarding, multi-hop proxy routing through k8s clusters, stateful config via filesystem or git - GUI and TUI available

1.5K
Stars
80/100
Confianza
Categoría: devopsAuditoría

A coding agent CLI hook that acts as a safety net, catching destructive git and filesystem commands before they execute. Supports Codex, Claude Code, OpenCode, Gemini CLI, Copilot CLI, Kimi Code and Pi.

1.4K
Stars
78/100
Confianza
Categoría: coding-agentsAuditoría

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

359
Stars
71/100
Confianza
Categoría: agent-skillsAuditoría

A flexible developer tool that runs processes and responds to filesystem changes

3.0K
Stars
72/100
Confianza
Categoría: coding-agentsAuditoría

Markdown filesystem for agents and teams.

686
Stars
67/100
Confianza
Categoría: document-processingAuditoría

Install, manage, and share skills across every major coding agent — Claude Code, Cursor, Copilot, and more.

253
Stars
69/100
Confianza
Categoría: coding-agentsAuditoría

A filesystem designed for agents, with SOTA retrieval, automatic memory profiles, sync engine. Drop any file type (pdf, images, videos), and grep through them.

451
Stars
69/100
Confianza
Categoría: agent-frameworksAuditoría

Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation and clean repository ownership. Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows. Reuse existing code before creating files, keep one source of truth, prevent parallel implementations and junk directories, justify every new file or dependency, and audit the current change before completion.

4.5K
Stars
67/100
Confianza
Categoría: securityAuditoría

How to work in a Personal CRM project (the `entity-vault` starter pack, GBrain-compatible): a typed-entity vault of people, companies, meetings, and concepts, each a dossier with a rewritable summary plus an append-only timeline. Read when the project has these folders, OR when asked to capture notes about a person or company, log a meeting, prep for an upcoming meeting, or answer who someone is and what was last said. Carries the dossier convention and entity-extraction behaviors so that guidance does not live inside template bodies or folder descriptions. Complements the platform `open-knowledge` skill; does not replace it.

3.6K
Stars
74/100
Confianza
Categoría: design-creativeAuditoría