agentleFS
Fable-ForgeFable-Forge/xiaohongshu-copywriter/SKILL.md

xiaohongshu-copywriter

Skill0 starsChanged 2 months agoMITView on GitHub

Create, rewrite, localize, diagnose, and package Xiaohongshu or RED posts in Chinese for products, personal brands, lifestyle notes, tutorials, reviews, launches, and community growth. Use when Codex is asked to write Xiaohongshu copy, RED note copy, seed-style posts, post titles, cover text, hashtags, comment prompts, or to adapt raw notes into a platform-ready Chinese post while preserving authenticity and avoiding exaggerated claims.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. Fable-Forge/fableforge-agent-skills★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to turn rough ideas, product notes, transcripts, outlines, or existing drafts into Xiaohongshu-ready Chinese copy.

    line 10
  2. Distinctive:

    If details are missing, make conservative assumptions and state them briefly.

    line 24
  3. Distinctive:

    Add interaction design: comment question, save cue, follow cue, or soft CTA only when it fits the user goal.

    line 32
  4. Distinctive:

    Add hashtags that mix category, scenario, audience, and intent.

    line 33
  5. Distinctive:

    Run a quick quality check for authenticity, claim safety, readability, and platform fit.

    line 34
  6. Distinctive:

    When creating a complete post, provide the final answer in Chinese with these sections:

    line 38
  7. Distinctive:

    When rewriting an existing draft, provide:

    line 47
  8. Distinctive:

    Do not invent certifications, clinical effects, income results, review counts, discounts, celebrity endorsements, or platform policy claims.

    line 71
  9. Distinctive:

    If the user asks for deceptive tactics, fake reviews, impersonation, misleading before/after claims, or watermarked-content evasion, refuse …

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Xiaohongshu Copywriter

Overview

Use this skill to turn rough ideas, product notes, transcripts, outlines, or existing drafts into Xiaohongshu-ready Chinese copy. Optimize for usefulness, lived-in specificity, scannability, and a natural Chinese voice rather than empty hype.

For detailed patterns, read references/playbook.md when the task requires titles, hooks, structures, compliance checks, or multiple variants.

Intake

First identify:

  • Goal: traffic, saves, comments, conversion, launch, review, tutorial, personal branding, or community trust.
  • Audience: who the note is for, their pain point, context, and sophistication level.
  • Source material: product facts, personal experience, screenshots, before/after details, constraints, and proof.
  • Tone: sincere, expert, friendly, sharp, diary-like, minimalist, or commercial.
  • Required output: title options, full note, cover text, tags, comment prompts, rewrite, critique, or content calendar.

If details are missing, make conservative assumptions and state them briefly. Ask only when legal, medical, financial, pricing, efficacy, or brand claims would otherwise be invented.

Workflow

  1. Extract the real value: convert features into user outcomes, scenes, objections, and proof points.
  2. Choose the post type: experience note, tutorial, checklist, review, comparison, story, mistake log, launch note, or Q&A.
  3. Draft the title and opening hook first. Make the promise clear within one screen.
  4. Build the body with short paragraphs, bullets, and concrete examples. Keep each section useful enough to justify a save.
  5. Add interaction design: comment question, save cue, follow cue, or soft CTA only when it fits the user goal.
  6. Add hashtags that mix category, scenario, audience, and intent. Avoid stuffing unrelated hot tags.
  7. Run a quick quality check for authenticity, claim safety, readability, and platform fit.

Output Format

When creating a complete post, provide the final answer in Chinese with these sections:

  • Title options: 5-10 Chinese title options with different angles.
  • Cover copy: 2-4 short Chinese overlay lines.
  • Post body: final Chinese post body.
  • Hashtags: 8-15 Chinese hashtags.
  • Comment prompts: 1-3 natural Chinese prompts.
  • Strategy notes: brief note on the strategy, only if useful.

When rewriting an existing draft, provide:

  • Diagnosis: the highest-impact issues.
  • Rewrite: one polished Chinese version.
  • Optional titles: 3-5 Chinese options.
  • Further optimization: concise next steps or missing info.

Voice Rules

Prefer:

  • Specific scenes, sensory details, time spans, prices, steps, mistakes, tradeoffs, and who the advice is not for.
  • Natural Chinese punctuation and short paragraphs in the generated post.
  • Honest qualifiers equivalent to "better suited for", "in my own experience", or "if you have this problem too".
  • Concrete CTAs such as asking readers to comment with their budget, save a checklist, or share their situation.

Avoid:

  • Fabricated data, fake personal experience, fake scarcity, medical or financial guarantees, and unverifiable "number one on the internet" claims.
  • Overused hype such as "juejuezi", "ceiling-level", "buy with eyes closed", or "rush now", unless the user explicitly wants that voice.
  • Hashtag stuffing, keyword walls, and generic openings that could fit any product.

Compliance

Do not invent certifications, clinical effects, income results, review counts, discounts, celebrity endorsements, or platform policy claims. For regulated areas such as healthcare, supplements, finance, education outcomes, cosmetics efficacy, weight loss, or minors, soften claims and ask for proof before making strong statements.

If the user asks for deceptive tactics, fake reviews, impersonation, misleading before/after claims, or watermarked-content evasion, refuse that part and offer an ethical alternative.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.