Social writer
Skill vikynofebriputra-creator/Orkas-Awesome-AgentSkills/creation/skills/social-writer
Access a curated library of high-quality agents and modular skills for Orkas and other agent frameworks to accelerate task automation and development.From the repository description
npx -y skills add vikynofebriputra-creator/Orkas-Awesome-AgentSkills --skill social-writerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
6.0 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it
Social Writer
When to Use
Use this skill when the user wants to create, improve, plan, or respond with social media content.
Use for:
- creating Chinese social drafts for Xiaohongshu, WeChat Official Account, Zhihu, Douyin/Kuaishou, Weibo, and similar platforms.
- creating global single posts for X, LinkedIn, Instagram, TikTok, and similar platforms.
- optimizing an existing social draft before posting.
- planning weekly, monthly, or campaign content calendars.
- drafting replies to negative comments, complaints, misunderstandings, and public social issues.
Do not use this skill to operate platform backends, save drafts, click publish, upload media, or perform final legal/public-relations approval.
Choose The Mode
| Mode | Use when | Output |
|---|---|---|
create | user wants a new post, note, answer, article, caption, or script | platform-native draft |
optimize | user has an existing draft | score, diagnosis, rewrites, checklist |
calendar | user wants a week/month/campaign plan | content calendar with topics and production needs |
respond | user asks how to reply to comments, complaints, or crisis content | risk level, response draft, escalation plan |
Workflow
- Identify platform and mode:
- Chinese platforms: Xiaohongshu, WeChat Official Account, Zhihu, Douyin/Kuaishou, Weibo, Bilibili.
- Global platforms: X, LinkedIn, Instagram, TikTok.
- If no platform is specified, ask for the target platform or produce a platform comparison.
- Confirm content inputs:
- topic, audience, goal, brand voice, source material, product claims, forbidden claims, media availability, and desired action.
- for existing drafts: current title, body, cover/visual description, tags, and performance data if available.
- for calendars: date range, cadence, pillars, key dates, resource constraints, review capacity.
- for responses: original comment/complaint, context, platform, history, support facts, and risk indicators.
- Run a fact and safety pass:
- do not invent personal experience, customer reviews, test results, screenshots, income, health results, legal outcomes, or third-party endorsements.
- mark data, claims, prices, policies, and references that need verification.
- high-risk domains need human review.
- Generate platform-native output:
- Xiaohongshu: title, cover text, hook, short sections, save/comment CTA, 5-10 tags.
- WeChat: title, opening, 3-5 sections, full body, closing, share/follow CTA.
- Zhihu: answer directly, reason carefully, include evidence and caveats, avoid hard-sell tone.
- Douyin/Kuaishou/TikTok: first 1-3 seconds, spoken script, screen text, scene notes, caption, tags.
- Weibo/X: concise point, clear hook, native topic/tag use, low-friction interaction.
- LinkedIn: first two lines, story or insight, transferable lesson, CTA, 3-5 tags if useful.
- Instagram: visual-first caption, save/share CTA, relevant hashtags.
- For
optimize:- score title/first screen, visual/cover, structure, platform fit, interaction/CTA.
- identify the top 3 issues and give concrete rewrites.
- For
calendar:- balance pillars, platform rhythm, key dates, flexible slots, and production capacity.
- create specific topics, not vague labels.
- For
respond:- classify as complaint, fair criticism, misunderstanding, bad-faith attack, coordinated attack, or legal/safety/privacy/regulatory issue.
- rate severity: low, medium, high, critical.
- draft only for human approval; do not publish.
Return Formats
For new social content:
## Draft: [platform]
### Title / Hook Options
1. ...
2. ...
3. ...
### Body / Script / Caption
...
### CTA
...
### Tags
...
### Visual Or Video Suggestions
- ...
### Needs Verification
- ...
For optimization:
# Optimization Report: [platform]
## Score
| Dimension | Score / 10 | Notes |
|---|---:|---|
## Top Issues
1. ...
2. ...
3. ...
## Rewrites
- Title:
- Opening:
- CTA:
## Publish Checklist
- [ ] ...
For calendar:
# Social Calendar: [date range]
## Overview
- Platforms:
- Cadence:
- Pillar mix:
- Main assumptions:
## Plan
| Date | Platform | Pillar | Format | Topic / hook | Target action | Assets |
|---|---|---|---|---|---|---|
## Flexible Slots
- ...
## Production Risks
- ...
For response/crisis:
# Response Plan
## Assessment
Type:
Severity:
Need to respond:
Main risks:
## Draft Reply
...
## Escalation
- Owner:
- Questions:
- Forbidden automatic actions:
## Monitoring
- ...
Dependencies
- No external tool is required by default.
- Current trends, platform rules, pricing, policies, public facts, and competitor posts require separate lookup when they matter.
- Brand voice, product claims, account performance, and approved statements should come from the user or source files.
Limits
- Do not promise reach, interaction, ranking, conversion, followers, revenue, or moderation results.
- Do not fabricate experience, reviews, evidence, or platform data.
- Do not publish, schedule, save drafts, or operate platform UI. Use
social-publishfor browser-based draft preparation. - Crisis, legal, refund, privacy, safety, regulatory, media, and minors-related content requires human approval.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most docs writing skills give in ~1.3k tokens
Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-07
- Announce the skill at startin 54 of 1637, across 26 files
- Convert legacy doc files before editingin 45 of 1637, across 7 files
- Predict questions readers might askin 42 of 1637, across 4 files
- Generate clarifying questions for initial contextin 42 of 1637, across 3 files
- Create document scaffold with placeholder textin 42 of 1637, across 3 files
- Brainstorm content options for each sectionin 42 of 1637, across 3 files
- Test the document with a fresh context-less instancein 42 of 1637, across 3 files
- Include exact file paths in every taskin 42 of 1637, across 15 files
- Ask interview questions one at a timein 42 of 1637, across 27 files
- Apply surgical edits during refinementin 41 of 1637, across 2 files
- Offer structured workflow or freeformin 40 of 1637, across 1 file
- Ask for document meta-contextin 40 of 1637, across 2 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.