Paquetes portátiles
Instala skills para el agente elegido en este proyecto. Los hooks del host son una integración separada.
npx skills add i-9-ai/skills --yesCrea, evalúa y evoluciona skills de agentes. Una responsabilidad. Un resultado revisable.

Conserva lo que funciona. Cambia una responsabilidad a la vez.
Define la tarea. Investiga el dominio. Crea un paquete completo.
skill-authoringEvalúa comportamiento, seguridad y compatibilidad declarada.
skill-evaluatorAudita lo que existe. Conserva evidencia. Evoluciona el menor cambio útil.
skills-auditElige un paquete aprobado y una distribución deliberada.
skill-publicationPaquetes enfocados para todo el ciclo de vida de una skill de agente.
Los nombres y las descripciones originales de los paquetes están en inglés, según el catálogo fuente.
24 skills
Use to author or revise a focused skill package from a goal and design, coordinating discovery, synthesis, and evaluation through companion skills. Use skills-discovery for search alone.
CrearUse to resolve a skill's responsibility, interface, and design tradeoffs from a brief or merge plan before authoring. It does not discover sources or implement the package.
CrearUse to research one proposed skill's subject, reconciling process-owner facts, reviewed skill claims, and current authoritative web sources into a bounded evidence dossier.
CrearUse to evaluate a skill package against frozen behavioral cases and a baseline, returning evidence and a readiness verdict. It does not author fixes or publish the skill.
EvaluarUse to collect, normalize, and preserve bounded evidence about one skill or skill collection for a later evaluation, lifecycle, or evolution decision. It does not judge or change the target.
EvolucionarUse to update one existing skill from new evidence while preserving its responsibility, provenance, compatibility, and a reviewable change record.
EvolucionarUse to design or refresh a distinct, accessible SVG icon for one skill package from its responsibility and visual constraints. It does not redesign other package content.
CrearUse to install one approved skill package at an immutable source revision into a selected agent environment and return an auditable installation receipt.
DistribuirUse to determine the lifecycle state and next justified transition for one skill from current evidence without editing or publishing the package.
EvaluarUse to migrate one skill package between collections while preserving behavior, provenance, history, compatibility, and an auditable handoff.
DistribuirUse to select or review a skill's canonical name, grouping related skills by domain and checking scope, cardinality, and known collisions. Return a naming decision without renaming files.
CrearUse to improve one skill through scored rollouts, bounded candidate edits, and held-out validation. It does not discover sources, author unrelated skills, or publish changes.
EvolucionarUse to publish one approved skill package through an authorized distribution channel after exact-revision release gates have passed.
DistribuirUse to decide whether a task should activate one skill, an ordered set of skills, or no skill from supplied catalogs. It recommends a route but does not invoke, install, or modify skills.
GestionarUse to review one skill package for secrets, private data, unsafe instructions, dangerous scripts, dependencies, permissions, and disclosure risk.
EvaluarUse to audit a collection of installed or authored skills for inventory, provenance, validation, policy, and drift, producing one findings report.
GestionarUse to create, synchronize, or validate a repository or global catalog from installed SKILL.md metadata. It maintains inventory and summaries but does not choose a skill for a task.
GestionarUse to combine explicit skill catalogs into a local searchable index, synchronize their change history, or record evidenced evolution operations. It does not maintain source catalogs or choose a skill.
GestionarUse to discover and qualify existing skills for a specific task, returning pinned candidates and evidence. It does not install, merge, or author a skill.
CrearUse to verify declared repository-local aliases for a canonical skill collection and return a bounded structural compatibility report.
EvaluarUse to turn an approved recurring maintenance goal for a bounded skill collection into an approval-ready schedule proposal. It does not configure a scheduler or execute maintenance.
GestionarUse to turn an audit of an existing skill collection into a bounded decomposition and reorganization plan without editing the packages.
GestionarCreate, verify, list, restore, and explicitly prune deterministic snapshots of a caller-selected skill collection or package. Use before risky skill maintenance; do not use to install or refactor skills.
GestionarUse to synthesize useful contributions from two or more reviewed skills into one coherent synthesis plan. It does not search for candidates, write the final package, or certify its quality.
CrearPrueba otra responsabilidad o borra los filtros.
Skills portátiles, un plugin para el host o la CLI del toolkit. Elige lo que necesitas.
Instala skills para el agente elegido en este proyecto. Los hooks del host son una integración separada.
npx skills add i-9-ai/skills --yesSkills, hook de sesión y MCP del catálogo. Requiere Codex CLI y Node.js 24+.
codex plugin marketplace add i-9-ai/skills --ref main
codex plugin add i9-skills@i9-skills
codex plugin listEjecuta comandos de catálogo y gestión de skills con Node.js 24+.
npx --yes @i-9.ai/skills catalog overviewPaquete publicado en el registro; ejecutar la CLI es distinto de instalar skills.
Referencia de comandosMarkdown Agent Skills y recursos incluidos en el paquete.
Las verificaciones estructurales y los pilotos de proveedores cubren cosas distintas.
Sin promesa de compatibilidad universal o calidad de producción.
Los pilotos de plugins de Codex y Claude prueban rutas nativas específicas. La evidencia de Copilot CLI cubre descubrimiento MCP y llamadas directas de un plugin legado efímero, sin turno de modelo ni instalación persistente. Los iconos y hooks dependen del host.