social-media-posting
Create, adapt, and schedule social media content across platforms with platform-specific formatting, engagement hooks, and strategic posting cadence. Use when the user requests social media posting or provides relevant inputs for this workflow.
git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills /tmp/social-media-posting && cp -r /tmp/social-media-posting/marketing-and-seo/social-media-posting ~/.claude/skills/social-media-postingSKILL.md
# Social Media Posting This skill enables an AI agent to create and manage social media content across major platforms — Twitter/X, LinkedIn, Instagram, and Facebook. The agent adapts messaging to each platform's unique format constraints, audience expectations, and algorithmic preferences. It handles copy writing, hashtag strategy, scheduling, and content calendar creation to maintain a consistent and engaging social media presence. ## Workflow 1. **Define the campaign objective and audience.** Clarify the goal for the social content: brand awareness, engagement, lead generation, event promotion, or product launch. Identify the target audience segment and which platforms they are most active on. A B2B product launch prioritizes LinkedIn and Twitter/X, while a D2C brand focuses on Instagram and Facebook. 2. **Draft platform-adapted copy.** Write distinct versions of each message tailored to platform constraints and norms. Twitter/X posts use concise hooks within 280 characters with 1–3 hashtags. LinkedIn posts can run 1,300+ characters with paragraph breaks, professional tone, and no more than 3–5 hashtags. Instagram captions support up to 2,200 characters and rely heavily on hashtags (up to 30) and emoji for discoverability. Facebook posts perform best at 40–80 words with a direct question or call-to-action. 3. **Craft engagement hooks and CTAs.** Open every post with an attention-grabbing first line — a surprising statistic, a bold claim, or a direct question. The first line is the only part visible before "see more" on most platforms. End with a clear call-to-action: comment, share, click link, or tag someone. Use line breaks and whitespace to improve readability on mobile. 4. **Build a hashtag and mention strategy.** Research trending and niche hashtags relevant to the content topic. On Twitter/X, use 1–3 targeted hashtags inline. On LinkedIn, place 3–5 hashtags at the end of the post. On Instagram, use a mix of high-volume (>500K posts), medium (50K–500K), and niche (<50K) hashtags for maximum reach. Tag relevant accounts, partners, or influencers to extend organic visibility. 5. **Schedule posts at optimal times.** Use platform engagement data to determine the best posting windows. General benchmarks: Twitter/X peaks at 8–10 AM and 12–1 PM weekdays; LinkedIn performs best Tuesday–Thursday 7–9 AM; Instagram engagement peaks Wednesday and Friday 11 AM–1 PM; Facebook sees highest reach Tuesday–Friday 9 AM–12 PM. Adjust for the target audience's timezone and test alternative windows quarterly. 6. **Create a weekly content calendar.** Plan 5–7 days of posts in advance, balancing content types: educational (40%), engaging/entertaining (30%), promotional (20%), and community/UGC (10%). Assign each post a platform, publish time, copy, media asset requirements, and campaign tag for tracking. ## Usage Provide the agent with the campaign goal, key message, target platforms, and any brand voice guidelines. The agent returns platform-specific post copy, hashtags, scheduling recommendations, and a weekly calendar. **Prompt:** `Create a social media campaign for the launch of our new AI writing assistant. Target platforms: Twitter/X, LinkedIn, and Instagram. Launch date: March 15. Tone: professional but approachable.` ## Examples ### Example 1: Multi-Platform Product Launch Campaign **Request:** Announce the launch of "FocusFlow," a productivity app for remote workers, across Twitter/X, LinkedIn, and Instagram. **Twitter/X (278 characters):** ``` Remote work is amazing — until your focus disappears by 10 AM. We built FocusFlow to fix that. 🎯 Smart time blocking 📊 Distraction tracking ⚡ Deep work streaks Free for the first 1,000 users → focusflow.app #RemoteWork #Productivity ``` **LinkedIn (642 characters):** ``` After 2 years of remote work, our team noticed a pattern: the hardest part isn't collaboration — it's protecting deep focus time. So we built FocusFlow. It's a lightweight productivity app that helps remote workers: → Block time for deep work automatically → Track and reduce digital distractions → Build streaks that reinforce daily focus habits We're opening it up to the first 1,000 users for free. If you lead a distributed team or struggle with context switching, I'd love your feedback. Try it here: focusflow.app #ProductLaunch #RemoteWork #Productivity #DeepWork #FocusFlow ``` **Instagram Caption (with image post):** ``` Your focus is your superpower. 🎯 Meet FocusFlow — the app that helps remote workers protect their deep work time and eliminate distractions. ✨ What you get: → Smart time blocking that adapts to your schedule → Real-time distraction tracking → Focus streaks to keep you motivated Link in bio to get early access (free for the first 1,000 users!) . . . #focusflow #productivitytips #remotework #deepwork #focustime #workfromhome #timemanagement #productivityhacks #remoteworklife #startuplife #techlaunches #newapp #wfhlife #digitalwellbeing ``` ### Example 2: Weekly Social Media Content Calendar **Request:** Plan one week of posts for a B2B marketing agency's LinkedIn and Twitter/X accounts. | Day | Platform | Type | Topic | Post Summary | Time | |-----|----------|------|-------|-------------|------| | Mon | LinkedIn | Educational | SEO tip | "3 on-page SEO fixes that take 10 minutes and move the needle" | 8:00 AM ET | | Mon | Twitter/X | Engagement | Industry poll | "What's the #1 channel driving leads for your B2B in 2025?" (poll) | 12:00 PM ET | | Tue | LinkedIn | Case study | Client win | "How we helped [client] increase organic traffic 140% in 90 days" | 7:30 AM ET | | Tue | Twitter/X | Educational | Thread | "5 LinkedIn ad mistakes we see in every audit (thread)" | 9:00 AM ET | | Wed | LinkedIn | Thought leadership | Industry trend | "AI won't replace marketers. Marketers who use AI will." | 8:00 AM ET | | Wed | Twitter/X | Engaging | Meme/humor | Relatable marketing meme with commentary | 1:00 PM ET | | Thu | LinkedIn | Promotional
Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.
Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.
Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.
Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.
Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.
Design and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.