Self-Media Content Production Workflow
An end-to-end creator workflow that runs topic planning, evidence research, platform-native drafts, short-video packages, publishing kits, and performance reviews as one resumable loop.
Content & WritingIntermediate★ 473⑂ 65AI score 9/10Last updated: Aug 23, 2026
What it does
- Routes each request (single post, channel strategy, trend/competitor research, short video, analytics review, archiving) to only the modules that are actually needed.
- Forces a creative brief first — positioning, audience, goal, core claim, evidence, tone, no-go zones — before any body copy is written.
- Writes genuinely platform-native versions instead of mechanical truncations: separate titles, hooks, evidence order and CTAs per channel. It generates 6–8 headlines internally and shows only the 3 strongest.
- Keeps an explicit state machine (clarify → direction approval → research → platform approval → preflight → drafting → title approval → assets → QA → final approval → publish → review) with five mandatory human gates; final-draft approval is explicitly not publish authorization.
- Separates fact / opinion / inference / recommendation, demands sources for key numbers, and never mass-sends: it only produces drafts and manual publishing kits.
Who it's for
- Solo creators and newsletter writers repurposing one topic across several channels.
- Content marketers who need version control, QA gates, and post-publish attribution rather than bulk AI output.
- Teams that want an auditable content pipeline with clear stop-and-ask points.
Examples
- "Write about topic X for my blog and social" → brief card, direction confirmation, three verifiable evidence items, one primary plus up to two secondary platforms, then distinct drafts per platform.
- "Turn this post into a short video" → spoken script, shot list, subtitles, cover, and publish-field package (digital-human production only after you confirm likeness/voice rights).
- "Do the monthly review" → compares same platform, same content type, similar timing, then outputs conclusions, attribution, next actions, and hypotheses to test.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/yanhua1010/self-media-content-workflow/HEAD/skills/self-media-content-workflow/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/self-media-content-workflow folder from the GitHub repo yanhua1010/self-media-content-workflow into my ~/.claude/skills/self-media-content-workflow/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/yanhua1010/self-media-content-workflow.git /tmp/smcw && mkdir -p ~/.claude/skills && cp -r /tmp/smcw/skills/* ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal.
- Clone the repo:
git clone https://github.com/yanhua1010/self-media-content-workflow.git /tmp/smcw. - Make sure the skills folder exists:
mkdir -p ~/.claude/skills. - Copy everything over:
cp -r /tmp/smcw/skills/* ~/.claude/skills/— this also installs the companion sub-skills if the repo ships them. - Verify with
ls ~/.claude/skills/self-media-content-workflow; you should seeSKILL.md, areferences/folder and anassets/folder. - Restart Claude Code and try: "Help me plan and write content for my channel about ...".
- Output defaults to a
self-media/directory in your workspace; specify a different path up front if you prefer. - Note: the skill text is in Chinese and assumes China-centric platforms (WeChat, Xiaohongshu, Bilibili). State your actual platforms so it adapts, and edit
references/platforms.mdif needed.
View source on GitHub ↗License: MIT