by Hao0321
A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day content calendar. Mega-viral validated: 80K reach / 448 likes / 500 comments on first post. Includes Day 2 flop postmortem.
# Add to your Claude Code skills
git clone https://github.com/Hao0321/claude-skill-social-postGuides for using ai agents skills like claude-skill-social-post.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T16:57:21.245Z",
"npmAuditRan": true,
"pipAuditRan": true
}claude-skill-social-post is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Hao0321. A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day content calendar. Mega-viral validated: 80K reach / 448 likes / 500 comments on first post. Includes Day 2 flop postmortem. It has 625 GitHub stars.
Yes. claude-skill-social-post passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/Hao0321/claude-skill-social-post" and add it to your Claude Code skills directory (see the Installation section above).
claude-skill-social-post is primarily written in Python. It is open-source under Hao0321 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh claude-skill-social-post against similar tools.
No comments yet. Be the first to share your thoughts!
Based on votes and bookmarks from developers who liked this skill
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
一個可安裝到 Codex 或 Claude Code 的社群內容 Skill:學習本機聲線、規劃內容、撰寫平台化貼文、經確認後發布,並把跨平台洞察保存成可驗證的結構化資料。
目前版本:v2.2.0。
corrections.jsonl:修正發布時間、片長或舊快照時,不再覆寫歷史 event。metric_qualifiers:rounded、upper_bound、visual_estimate 等平台顯示精度會一路保留到 summary。git clone https://github.com/Hao0321/claude-skill-social-post.git
Codex(Windows PowerShell):
New-Item -ItemType Directory -Force "$env:USERPROFILE\.codex\skills" | Out-Null
Copy-Item -Recurse ".\claude-skill-social-post\social-post" "$env:USERPROFILE\.codex\skills\social-post"
Claude Code:把目的地改成 .claude\skills\social-post。macOS/Linux 可複製到 ~/.codex/skills/social-post/ 或 ~/.claude/skills/social-post/。
首次使用先建立只存在本機的個人檔:
cd social-post
Copy-Item style_profile.example.md style_profile.md
Copy-Item content_plan.example.md content_plan.md
再把 voice_quick.md 與 current_brief.md 的 placeholder 換成自己的方向。
| Mode | 用途 |
|---|---|
| P0 Plan | 規劃內容與實驗 |
| P1 Learn Voice | 從已授權樣本學本機聲線 |
| P2 Draft/Publish | 撰稿;當輪確認後才發布 |
| P3 Log Outcome | 保存貼文、快照、帳號總覽與 corrections |
| P4 Optimize Patterns | 對齊 maturity 後做跨篇/跨平台比較 |
$env:PYTHONUTF8='1'
python scripts/log_outcome.py references/outcome-bundle.example.json
python scripts/self_test.py
python scripts/social_data.py validate
python scripts/social_data.py summary --series demo-series
正式寫入時才加 --write。修正既有 event 可參考 correction-bundle.example.json。
公開 repo 只收 schema、工具、匿名規則與明示為 fictional 的例子。不要提交:
style_profile.md、content_plan.md、drafts/;data/*.jsonl 的真實 outcome/correction;python social-post/scripts/self_test.py
python social-post/scripts/social_data.py validate
MIT。Copyright holder:Hao0321 contributors。