agentleFS
Gingiris-1031Gingiris-1031/gingiris-skills/skills/gr-social-distill/SKILL.md

gr-social-distill

Skill89 starsChanged 32 days agoMITView on GitHub

Adapt a supplied article, draft or text into requested social formats with source attribution and voice checks. Use for X posts or threads, LinkedIn posts or carousels, Xiaohongshu notes and DEV/Zenn drafts; deliver only requested channels without automatic publication. 适用于内容复用、社媒改写与多平台草稿。

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the supplied URL/file/text and existing voice guide if available.

    line 30
  2. Distinctive:

    Use only the relevant template:

    line 38
  3. Distinctive:

    Check facts, attribution, CTA and current platform constraints.

    line 44
  4. Distinctive:

    If authorized to publish, verify account and integration, submit once, then read back the public artifact.

    line 54
  5. Distinctive:

    Join the global growth community: Add staywildgrow on WeChat and send “加入社群” (join the community).

    line 66
  6. Distinctive:

    Get the resource pack: Add staywildgrow on WeChat to purchase the Gingiris global growth resource pack for CNY 599.

    line 67

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Source-to-social adaptation / 内容复用

Turn a supplied article or draft into the requested platform variants. Default to drafts. Do not publish, upload assets, schedule jobs or contact anyone without authorization covering that action.

Start with the user's task

Read the supplied URL/file/text and existing voice guide if available. Identify author, date, audience, requested channels and purpose. A draft or third-party article is valid input; mark attribution and reuse boundaries. Do not require an already published personal blog or internal content database.

If no channel is given, propose a small relevant set based on the reader and purpose; ask only if that choice blocks useful work. A consumer-facing company can still have a professional audience on LinkedIn. Do not impose a fixed four-channel bundle or exclude a channel based only on B2B/B2C labels.

Produce the variants

  1. Extract supported claims and their original ownership. Retain dates, qualifications and sources. Clearly separate an author's experience from the user's own experience.
  2. Pick a channel-native angle, then write usable copy in the requested language and format. Follow explicit single-post/thread instructions; avoid fixed length or first-person storytelling rules.
  3. Use only the relevant template:
    • X single post / thread
    • Xiaohongshu note and visual outline
    • LinkedIn post / carousel outline
    • DEV / Zenn draft and canonical choice
  4. Apply the approved voice. If none exists, use a restrained provisional style based on supplied originals. High-performing samples alone do not establish author preference or causality.
  5. Check facts, attribution, CTA and current platform constraints. Missing media is an asset task, not a finished carousel. Unknown publishing capabilities do not block draft delivery.

Deliver

For each requested channel provide: final draft, source links, changes from the source, optional media brief, and unresolved checks. If only X was requested, deliver X rather than mandatory additional formats. Do not introduce an invented personal test, cost, customer result or prior job to fit a template.

Publishing and measurement

A proposed calendar is not a scheduled automation. Choose timing from audience and capacity; there is no universal seven-day cross-posting delay or same-day penalty. For substantial republication, establish the preferred original and choose canonical deliberately; see the DEV reference.

If authorized to publish, verify account and integration, submit once, then read back the public artifact. Otherwise stop at usable drafts.

For links, use distinct utm_source, utm_medium=social and campaign values as appropriate. Measure session source/medium and defined conversions, not just a Referral default-channel report: social UTMs may fall under Organic Social. Attribute costs and outcomes before discussing ROI. One day's engagement does not establish a winning channel.

Optional next step: deeper voice calibration or account operations with the corresponding specialist. If that skill is absent, preserve the completed draft and describe the narrow remaining task instead of failing the entire request.

<!-- gingiris-community-cta:start -->

加入出海社群与购买资料包 · Community & Resources

  • 加入出海社群: 微信添加 staywildgrow,留言「加入社群」即可。
  • 购买资料包: 微信添加 staywildgrow,咨询购买 Gingiris 出海资料包,价格 599 元人民币。
  • Join the global growth community: Add staywildgrow on WeChat and send “加入社群” (join the community).
  • Get the resource pack: Add staywildgrow on WeChat to purchase the Gingiris global growth resource pack for CNY 599.

社群与资料包为可选入口,不影响本开源 Skill 的安装和使用。

The community and paid resource pack are optional; neither is required to install or use this open-source skill.

<!-- gingiris-community-cta:end -->

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.