What does this skill do, and when should you use it?
This is the social media sub-skill of the AI Marketing Suite for Claude Code (ai-marketing-claude), triggered via `/market social <topic/url>`. It first establishes brand context — audience, voice, products, competitors — then selects 2-3 primary platforms and builds a day-by-day 30-day schedule around five content pillars (educational, behind-the-scenes, social proof, engagement, promotional). Every post comes with a platform-appropriate hook, full copy, and a tiered hashtag set, written to SOCIAL-CALENDAR.md. It also includes a 1-to-10 repurposing framework that turns one long-form piece into ten posts, plus a process for adapting trending formats.
1) Accepts a topic or URL; if a URL, fetches the site to understand brand, audience, and content themes. 2) Recommends 2-3 platforms from six (LinkedIn, Twitter/X, Instagram, TikTok, YouTube, Facebook) based on business type and audience. 3) Defines 4-5 content pillars with a 40/20/15/15/10 mix ratio. 4) Generates posts per platform with hook formulas (e.g., LinkedIn contrarian openers, TikTok first-3-seconds hooks), full post text, and tiered hashtags (niche/medium/broad/branded). 5) Schedules engagement tactics: open-ended questions, native polls, debate posts, storytelling. 6) Builds a two-week repurposing schedule from one pillar piece into 10 posts. 7) Writes the full 30-day calendar to SOCIAL-CALENDAR.md and prints a condensed content-mix summary to the terminal.
- A solopreneur planning a month of social posts for their own product without hiring a content strategist
- An agency delivering an actionable 30-day social schedule to a client right after signing
- A B2B/SaaS team building a thought-leadership line on LinkedIn at 3-5 posts per week
- An e-commerce or consumer brand mixing carousels, Reels, and short video on Instagram and TikTok
- A content creator turning one blog post or podcast episode into ten cross-platform posts on a two-week cadence
- A social media manager taking over a new account who needs a ready-made voice, hashtag system, and posting cadence baseline
How do you install this skill?
- The skill covers only English-language global platforms (LinkedIn, X, Instagram, TikTok, YouTube, Facebook); Chinese platforms (WeChat, Xiaohongshu, domestic Douyin) are unsupported, limiting fit for mainland-China users.
- The skill does not state whether an existing SOCIAL-CALENDAR.md will be overwritten; back up or confirm before running.
- When a URL is supplied, the skill fetches external web content; avoid providing URLs containing sensitive or internal information.
- The 'ready to publish' claim is unverified by execution; review generated calendars manually before publishing.
- Publisher identity is unverified; maintenance responsibility and update path are unclear.
- No version number or changelog exists for this skill; behavior may change with repository updates.
- Network access
- Local filesystem
The skill ships as part of the ai-marketing-claude suite. One-command install: curl -fsSL https://raw.githubusercontent.com/zubair-trabzada/ai-marketing-claude/main/install.sh | bash, or clone the repo and run ./install.sh. Uninstall with ./uninstall.sh. The suite is MIT licensed. The source does not document installing this sub-skill standalone.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/zubair-trabzada/ai-marketing-claude.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/market-social" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
In Claude Code, run /market social <topic/url>, e.g., /market social https://calendly.com. With a URL the skill fetches the site to extract brand context; with a topic it builds strategy around the topic. It integrates with other suite artifacts: if BRAND-VOICE.md, COMPETITOR-REPORT.md, or EMAIL-SEQUENCES.md exist, it aligns tone and messaging with them. Read the generated SOCIAL-CALENDAR.md when done.
What are this skill's strengths and limitations?
- Output is day-by-day, platform-specific full copy that can be published directly or handed to a social media manager
- Methodology is concrete and inspectable: pillar ratios, hook formulas for six platforms, and tiered hashtag strategy are all written out
- Built-in 1-to-10 repurposing framework is especially useful for teams with limited content capacity
- Integrates with suite outputs (brand voice, competitor reports, email sequences) for consistent messaging
- Trend handling offers only evergreen formats plus a manual adaptation process — no real-time trend fetching
- Posting times and platform benchmarks in the calendar carry no cited data validation
- Cross-skill integration depends on specific sibling files existing; those benefits vanish when used alone
- The repo provides no tests or sample outputs for this skill, so real-world quality must be verified by trial
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Market Social — 30-Day Social Media Calendar Generator this page | 48 · Use with care | ★ 2.8k | 7mo ago | MIT |
| Brand Voice Dossier Builder | 59 · Recommended | ★ 3k | 11d ago | Apache-2.0 |
| Blog Repurpose | 50 · Use with care | ★ 2.4k | 11d ago | MIT |
| HumanAI — Text Humanization Engine | 52 · Use with care | ★ 38 | 3mo ago | MIT |
| Email Marketing Bible | 60 · Recommended | ★ 342 | 12d ago | MIT |
How did FollowSkills review this skill?
Pure prompt-based skill: generates content and writes a single file SOCIAL-CALENDAR.md; no destructive defaults, no credential handling, no network side effects beyond optionally fetching a user-supplied URL for brand context, with fairly transparent data flow. Deductions: no overwrite/rollback policy for an existing file of the same name, undisclosed boundaries on how fetched external data is used, publisher identity unverified.
Instructions are well-structured and self-consistent with explicit phase flow and output templates; the happy path (topic input) is plausibly reproducible. Deductions: no tests, no handling of edge inputs (invalid URL, thin topic, missing brand context), thin failure feedback; behavior when cross-referenced files like BRAND-VOICE.md are absent is only briefly noted.
Trigger condition is clear (/market social <topic/url>), audience and scenarios are defined, and the 30-day calendar format is concrete. Deductions: no declared non-fit boundaries; content targets English-language global platforms only, with no support for Chinese users or Chinese platforms (WeChat, Xiaohongshu, domestic Douyin), and advice depends on overseas platform ecosystems that may be unreachable from mainland China.
Documentation is well layered (discovery → strategy → hooks → hashtags → calendar → repurposing) with cross-skill references; repo provides MIT license and uninstall script. Deductions: no version number or changelog for this skill, no declared maintenance responsibility or update path, unverified publisher, known limitations (platform algorithm volatility) not disclosed.
Promises a directly publishable 30-day calendar with detailed templates (hooks, hashtags, timing, content mix), offering real marginal value over manual planning. Deductions: static review cannot verify actual generation quality or the 'ready to publish' claim; quality for non-marketing or non-English topics is unknown, and output depends on model writing rather than reproducible scripts.
Only author claims and a README sample output exist (showing the audit command, not this skill); no test suite, no CI, no third-party execution evidence. Deductions: key claims ('ready to publish', platform best-practice figures) lack external corroboration; facts and inferences are not separated.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →