LeandroBenjaminL/lend-ai / skills/content-engine
content-engine
VerifiedTrigger: After significant sessions, when you need to analyze Engram, track improvements, update docs, or generate LinkedIn content. Meta-skill que analiza Engram, trackea mejoras en proyectos, actualiza documentacion y genera contenido para LinkedIn. Se ejecuta despues de sesiones significativas.
Content Engine
Proposito
Analizar Engram constantemente para entender que se hizo, detectar patrones de mejora, mantener la documentacion al dia, y generar contenido profesional (LinkedIn posts, case studies, tips tecnicos).
LEND Workflow
1. ANALIZAR
Leer Engram: mem_context, mem_search, git log. Identificar mejoras, bugs fixeados, aprendizajes, cambios de arquitectura.
2. OFRECER/DELEGAR
Decidir que accion tomar: documentar, generar contenido, o ambos. Elegir formato segun el tipo de logro.
3. HACER
Ejecutar la documentacion o creacion de contenido. Actualizar CHANGELOG, AGENTS.md, README, ARCHITECTURE si corresponde.
4. VERIFICAR
Guardar todo en Engram: que se documento, que contenido se creo, ideas pendientes. Preguntar antes de publicar.
Ciclo (alternativo)
1. LEER ENGRAM
├── mem_context → actividad reciente
├── mem_search → patrones, bugs, decisiones
└── git log → commits del proyecto
2. ANALIZAR MEJORAS
├── ¿Qué se construyó? (features, skills, agents)
├── ¿Qué se arregló? (bugs, fixes, refactors)
├── ¿Qué se aprendió? (descubrimientos, patrones)
└── ¿Qué cambió? (arquitectura, config, docs)
3. SINTETIZAR
├── Timeline de progreso
├── Logros destacados
└── Áreas de mejora continua
4. DOCUMENTAR (si detectás cambios no documentados)
├── CHANGELOG → agregar entry si falta
├── AGENTS.md → actualizar si hay skills nuevas
├── README → reflejar estado actual
└── ARCHITECTURE → si cambió estructura
5. GENERAR CONTENIDO
├── LinkedIn post: logro, aprendizaje o tip técnico
├── Case study: problema → solución → resultado
└── Thread: secuencia de aprendizajes
6. GUARDAR TODO EN ENGRAM
├── Qué se documentó
├── Qué contenido se creó
├── Ideas pendientes para después
└── Próximos pasos sugeridos
Tipos de contenido que genera
| Tipo | Formato | Cuándo |
|---|---|---|
| Post técnico | 300-500 chars, hook + valor + CTA | Después de un fix o feature significativo |
| Case study | Problema → Solución → Resultado | Después de resolver un problema complejo |
| Thread educativo | 3-5 tweets, hilo con aprendizajes | Después de una investigación o exploración |
| Tip rápido | 1 párrafo, consejo con código o analogía | Después de un discovery o learning |
| Progreso semanal | Resumen de avances, métricas, próximos pasos | Semanal o después de sesión larga |
Reglas
- NO publicar nada — solo generar borradores y guardarlos
- Preguntar antes de publicar o postear en serio
- Siempre incluir qué proyecto/repo está relacionado
- Usar tono profesional pero cercano (no corporativo)
- Incluir hashtags relevantes (#opensource #AI #dev)
Arsenal
| Skill | Archivo | Cuándo |
|---|---|---|
lend-ai-docs | skills/lend-ai-docs/SKILL.md | Para escribir/actualizar documentación |
commits-real | skills/commits-real/SKILL.md | Para commits convencionales |
lend-ai-engram | skills/lend-ai-engram/SKILL.md | Para gestionar memoria Engram |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |