linkedin-post

Menulis posting LinkedIn berdasarkan temuan riset atau topik tertentu. Gunakan keterampilan ini saat diminta membuat konten LinkedIn, posting profesional, atau pemikiran…

npx skills add https://github.com/langchain-ai/langgraph-101 --skill linkedin-post

LinkedIn Post Skill

Format

  • Hook: Start with a bold opening line that grabs attention (this appears before the "see more" cut)
  • Body: 3-5 short paragraphs, each 1-2 sentences
  • Use line breaks between paragraphs for readability
  • Include 1-2 relevant emojis per paragraph (don't overdo it)
  • End with a call-to-action or question to drive engagement
  • Add 3-5 relevant hashtags at the bottom

Tone

  • Professional but conversational
  • Share insights, not just information
  • Use "I" statements and personal perspective where appropriate
  • Avoid jargon unless the audience expects it

Length

  • Ideal: 150-300 words
  • LinkedIn truncates after ~210 characters, so the first line must hook the reader

Template

[Bold hook / surprising stat / question]

[Context -- why this matters]

[Key insight 1]

[Key insight 2]

[Key insight 3 or personal takeaway]

[Call to action / question for engagement]

#hashtag1 #hashtag2 #hashtag3

Example

Most AI agents fail not because of the model -- but because of context management.

After researching the latest agent frameworks, one pattern keeps emerging:
the best agents treat their context window like a scarce resource.

Here's what separates good agents from great ones:

1. They offload intermediate results to a filesystem instead of keeping everything in context
2. They delegate to subagents for isolation -- the main agent only sees summaries
3. They use progressive disclosure -- loading instructions only when relevant

The shift from "bigger context window" to "smarter context management" is where
the real breakthroughs are happening.

What patterns have you seen work best in your agent architectures?

#AIAgents #LangChain #LangGraph #ContextEngineering

Lebih banyak skill dari langchain-ai

deepagents-thread-inspector
langchain-ai
Periksa dan jelaskan percakapan di penyimpanan sesi SQLite Deep Agents Code lokal. Gunakan sebagai cadangan saat alat pelacakan LangSmith tidak tersedia, untuk…
deepagents-python-quickstart
langchain-ai
Buat kerangka minimal Deep Agent lokal dalam Python dengan mengikuti panduan memulai resmi, menggunakan pencarian web bawaan penyedia alih-alih Tavily. Gunakan saat pengguna ingin…
deepagents-typescript-quickstart
langchain-ai
Buat kerangka Deep Agent lokal minimal dalam TypeScript dengan mengikuti quickstart resmi, menggunakan pencarian web native penyedia alih-alih Tavily. Gunakan saat pengguna…
eval-engineering
langchain-ai
Periksa repositori agen dan trace opsional dari pengguna secara iteratif, wawancarai pengguna, lalu buat, jalankan, dan audit eval Harbor satu per satu. Gunakan untuk…
LangChain RAG Pipeline
langchain-ai
GUNAKAN KETERAMPILAN INI saat membangun sistem retrieval-augmented generation (RAG) apa pun. Mencakup pemuat dokumen, RecursiveCharacterTextSplitter, embeddings (OpenAI),…
LangChain Structured Output & HITL
langchain-ai
langchain-structured-output-&-hitl — sebuah skill yang dapat diinstal untuk agen AI, diterbitkan oleh langchain-ai/langchain-skills.
LangSmith Datasets
langchain-ai
PANGGIL KETERAMPILAN INI saat membuat dataset evaluasi dari jejak ATAU mengunggah dataset ke LangSmith ATAU menanyakan dataset. Mencakup tipe dataset (final_response,…
langsmith-evaluator
langchain-ai
GUNAKAN KETERAMPILAN INI saat membangun pipeline evaluasi untuk LangSmith. Mencakup tiga komponen inti: (1) Membuat Evaluator - LLM-as-Judge, kode kustom; (2)…