social-media

Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write…

npx skills add https://github.com/langchain-ai/deepagents --skill social-media

Social Media Content Skill

Research First (Required)

Before writing any social media content, you MUST delegate research:

  1. Use the task tool with subagent_type: "researcher"
  2. In the description, specify BOTH the topic AND where to save:
task(
    subagent_type="researcher",
    description="Research [TOPIC]. Save findings to research/[slug].md"
)

Example:

task(
    subagent_type="researcher",
    description="Research renewable energy trends in 2025. Save findings to research/renewable-energy.md"
)
  1. After research completes, read the findings file before writing

Output Structure (Required)

Every social media post MUST have both content AND an image:

LinkedIn posts:

linkedin/
└── <slug>/
    ├── post.md        # The post content
    └── image.png      # REQUIRED: Generated visual

Twitter/X threads:

tweets/
└── <slug>/
    ├── thread.md      # The thread content
    └── image.png      # REQUIRED: Generated visual

Example: A LinkedIn post about "prompt engineering" → linkedin/prompt-engineering/

You MUST complete both steps:

  1. Write the content to the appropriate path
  2. Generate an image using generate_image and save alongside the post

A social media post is NOT complete without its image.

Platform Guidelines

LinkedIn

Format:

  • 1,300 character limit (show more after ~210 chars)
  • First line is crucial - make it hook
  • Use line breaks for readability
  • 3-5 hashtags at the end

Tone:

  • Professional but personal
  • Share insights and learnings
  • Ask questions to drive engagement
  • Use "I" and share experiences

Structure:

[Hook - 1 compelling line]

[Empty line]

[Context - why this matters]

[Empty line]

[Main insight - 2-3 short paragraphs]

[Empty line]

[Call to action or question]

#hashtag1 #hashtag2 #hashtag3

Twitter/X

Format:

  • 280 character limit per tweet
  • Threads for longer content (use 1/🧵 format)
  • No more than 2 hashtags per tweet

Thread Structure:

1/🧵 [Hook - the main insight]

2/ [Supporting point 1]

3/ [Supporting point 2]

4/ [Example or evidence]

5/ [Conclusion + CTA]

Image Generation

Every social media post needs an eye-catching image. Use the generate_social_image tool:

generate_social_image(prompt="A detailed description...", platform="linkedin", slug="your-post-slug")

The tool saves the image to <platform>/<slug>/image.png.

Social Image Best Practices

Social images need to work at small sizes in crowded feeds:

  • Bold, simple compositions - one clear focal point
  • High contrast - stands out when scrolling
  • No text in image - too small to read, platforms add their own
  • Square or 4:5 ratio - works across platforms

Writing Effective Prompts

Include these elements:

  1. Single focal point: One clear subject, not a busy scene
  2. Bold style: Vibrant colors, strong shapes, high contrast
  3. Simple background: Solid color, gradient, or subtle texture
  4. Mood/energy: Match the post tone (inspiring, urgent, thoughtful)

Example Prompts

For an insight/tip post:

Single glowing lightbulb floating against a deep purple gradient background, lightbulb made of interconnected golden geometric lines, rays of soft light emanating outward. Minimal, striking, high contrast. Square composition.

For announcements/news:

Abstract rocket ship made of colorful geometric shapes launching upward with a trail of particles. Bright coral and teal color scheme against clean white background. Energetic, celebratory mood. Bold flat illustration style.

For thought-provoking content:

Two overlapping translucent circles, one blue one orange, creating a glowing intersection in the center. Represents collaboration or intersection of ideas. Dark charcoal background, soft ethereal glow. Minimalist and contemplative.

Content Types

Announcement Posts

  • Lead with the news
  • Explain the impact
  • Include link or next step

Insight Posts

  • Share one specific learning
  • Explain the context briefly
  • Make it actionable

Question Posts

  • Ask a genuine question
  • Provide your take first
  • Keep it focused on one topic

Quality Checklist

Before finishing:

  • Post saved to linkedin/<slug>/post.md or tweets/<slug>/thread.md
  • Image generated alongside the post
  • First line hooks attention
  • Content fits platform limits
  • Tone matches platform norms
  • Has clear CTA or question
  • Hashtags are relevant (not generic)

Mehr Skills von langchain-ai

langgraph-docs
langchain-ai
We need to translate the given English text into German, preserving the name "langgraph-docs" if it appears. The text is a description of an agent skill. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "langgraph-docs" does not appear in the source text, so we should not include it. Also, do not add labels like "description" etc. Just translate the text. The text: "Access LangGraph documentation to build stateful agents and multi-agent workflows. Fetches official LangGraph Python docs covering state machines, graph-based agent design, and human-in-the-loop patterns Prioritizes relevant documentation by query type: implementation guides for how-to questions, concept pages for theory, tutorials for end-to-end examples, and API references for technical details Automatically selects 2–4 most relevant documentation URLs and retrieves their content to answer..." Note: There is a missing period after "patterns" and before "Prioritizes". Also the last part seems cut off:
official
langgraph-human-in-the-loop
langchain-ai
Pausiere die Graph-Ausführung für menschliche Überprüfung, Genehmigung oder Validierung und setze sie dann mit deren Eingabe fort. Erfordert drei Komponenten: einen Checkpointer (InMemorySaver oder PostgresSaver), eine Thread-ID in der Konfiguration und JSON-serialisierbare Interrupt-Payloads. interrupt(value) pausiert und zeigt Daten an; Command(resume=value) setzt fort und gibt diesen Wert an den pausierten Knoten zurück. Der gesamte Code vor interrupt() wird bei Fortsetzung erneut ausgeführt, daher müssen Seiteneffekte idempotent sein (upsert verwenden, nicht insert). Unterstützt Genehmigungs-Workflows,...
official
web-research
langchain-ai
Verwenden Sie diese Fähigkeit für Anfragen im Zusammenhang mit Web-Recherche; sie bietet einen strukturierten Ansatz zur Durchführung umfassender Web-Recherchen.
official
langchain-oss-primer
langchain-ai
BEGINNE HIER IMMER für jedes LangChain-, Deep Agents- oder LangGraph-Agent-Bauprojekt. Erforderlicher Ausgangspunkt, bevor andere Fähigkeiten ausgewählt oder Code geschrieben wird…
official
skill-creator
langchain-ai
Leitfaden zur Erstellung effektiver Skills, die die Fähigkeiten eines Agenten durch spezialisiertes Wissen, Workflows oder Tool-Integrationen erweitern. Verwenden Sie diesen Skill, wenn der Benutzer…
official
social-media
langchain-ai
Erstellt plattformspezifische Social-Media-Beiträge mit recherchierten Inhalten und generierten Begleitbildern. Unterstützt LinkedIn-Beiträge (1.300 Zeichen mit professionellem Ton) und Twitter/X-Threads (280 Zeichen pro Tweet im 1/🧵-Format). Erfordert die Delegierung der Recherche an einen Unteragenten vor dem Schreiben, gefolgt vom Lesen der Ergebnisse, um Genauigkeit und Relevanz sicherzustellen. Generiert automatisch auffällige Social-Bilder mit dem generate_social_image-Tool mit kräftigen, kontrastreichen Kompositionen, optimiert für kleine...
official
deep-agents-memory
langchain-ai
We need to translate the given English text into German. The text describes a pluggable memory and file backends system for Deep Agents. It mentions four backend types and a FilesystemMiddleware with six file operation tools. The name "deep-agents-memory" is not in the text, so we don't include it. We must preserve technical terms like "StateBackend", "StoreBackend", "FilesystemBackend", "CompositeBackend", "FilesystemMiddleware", and the tool names (ls, read_file, etc.). Also preserve "Deep Agents" as is? It's a product name, so keep it. Translate the rest naturally. Let's translate: "Pluggable memory and file backends for Deep Agents with ephemeral, persistent, and hybrid routing options." -> "Steckbare Speicher- und Datei-Backends für Deep Agents mit flüchtigen, persistenten und hybriden Routing-Optionen." "Four backend types: StateBackend (thread-scoped, ephemeral), StoreBackend (cross-session persistent), Filesystem
official
deep-agents-orchestration
langchain-ai
Orchestriere Unteragenten, plane mehrstufige Aufgaben und fordere menschliche Genehmigung für sensible Vorgänge an. Delegiere Arbeit an spezialisierte Unteragenten über das Aufgabenwerkzeug; benutzerdefinierte Unteragenten unterstützen isolierte Werkzeugsätze und Systemaufforderungen, während der standardmäßige "Allzweck"-Unteragent die Hauptagentenkonfiguration übernimmt. Plane und verfolge komplexe Arbeitsabläufe mit write_todos, organisiere Aufgaben in den Status "ausstehend", "in Bearbeitung" und "abgeschlossen"; erfordert eine thread_id für die Beständigkeit über Aufrufe hinweg. Implementiere...
official