X Insight Cards Agent Skill

Run scheduled or manual creator curation that turns recent high-quality X posts into verified image-and-caption packs for Douyin and…

Context cost
6.8k tokensestimated from the bundle, loaded when it triggers
Bundle
17 of 18 fileshanded out here; the rest is at its source
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Run scheduled or manual creator curation that turns recent high-quality X posts into verified image-and-caption packs for Douyin and Xiaohongshu review, with optional private delivery to a pinned WeChat iLink bot review chat or confirmed File Transfer Assistant self-chat. Use when Codex needs to discover, verify, rank, deduplicate, translate, render, quality-check, resume, or privately deliver posts about wealth, life, goals, habits, attention, freedom, or long-term thinking while keeping sources auditable, Chinese typography accurate, recipient-safe, and platform publishing manual.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

social media
Filed under

Sales & CRM

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md6.5 kB · preview
--- name: x-insight-cards ---
6# X Insight Cards
7
8Automate the preparation of Douyin and Xiaohongshu content packs from public X posts. Produce a small, source-auditable set of post images and copy-ready Chinese captions. Optimize for insight quality, faithful attribution, natural Chinese typography, and human review—not volume.
9
10## Workflow
11
121. Read [references/workflow.md](references/workflow.md) before running a daily curation job.
132. For a scheduled daily job, first apply the catch-up policy in [references/workflow.md](references/workflow.md): when the scheduled time has passed and the daily completion record or final assets are missing, run the missed preparation immediately once network access is available. The catch-up mechanism must be independent of opening the Codex app.
143. Check the user's history file and existing output folders. Deduplicate by canonical URL and normalized English-text SHA-256.
154. Discover posts from the last 24 hours. Expand to 72 hours only when necessary; then use unused evergreen posts.
165. Verify each candidate's URL, author, handle, real profile avatar URL, exact English text, publication date, and views when views are material to selection. A candidate without a verified real author avatar is incomplete.
176. Reject politics, stock tips, medical advice, course sales, unattributed reposts, pure motivational filler, and unverifiable content.
187. Score candidates using [references/scoring.md](references/scoring.md). Select no more than five, sorted by score. Never pad below 75/100.
198. Translate faithfully. Preserve paragraphs, quotation marks, dashes, parentheses, and tone.
209. Render one card per selected post with the verified real author avatar. Initials, generated portraits, and generic placeholders are not acceptable fallbacks. For an English source, first estimate the full bilingual card at 1200 px width: keep both languages when the estimated height is at most 1200 px; when it exceeds 1200 px, omit the English body and show only the faithful Chinese translation with a small 译自英文原帖 label. Never shrink type to force a long post into bilingual mode. Use scripts/render_card.py for reconstructed cards and label the record rearranged-render.
2110. Write one concise Chinese caption per card: normally one sentence, at most two, followed by 3–5 relevant hashtags. Do not copy the translation.
2211. Run the checks in [references/qa-checklist.md](references/qa-checklist.md) and mark accepted items READY_FOR_REVIEW.
2312. When the user has configured private delivery, read [references/private-delivery.md](references/private-delivery.md). For a fresh macOS installation, use the one-time setup binding and wechat_ilink_listener_service.sh flow documented there. Prefer the pinned iLink robot helper for unattended delivery when configured: its headless listener accepts only the exact command 发今日素材 from the pinned user, replies with safe usage guidance for other nonempty text from that same user, derives the current review-ready manifest from private history, preflights the fresh context, then sends each PNG and matching caption with checkpointed, stable message IDs. Use the verified integrated-main-window helper only for a separately configured File Transfer Assistant destination. Never upload or publish to a content platform.
24
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md880 words
Files17
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈160
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
6,665
on trigger
The instruction body and 16 supporting files, read only when the skill fires.
3.4%
of a 200k window
Ten skills this size would take about 34% of the window before you open a file.
050k100k150k200k context window

6.8k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

The download carries 17 of the 18 files in its source folder; the list here names 17 files, 111.9 kB on disk. Mostly text — the instructions the model reads — with 8 scripts in it that your client would run only if the instructions tell it to. The other one is not in the download — listed after these, with why.

  • SKILL.md6.5 kB
  • agents/openai.yaml0.3 kB
  • assets/demo-post.json1.1 kB
  • references/candidate-schema.md1.9 kB
  • references/private-delivery.md7.1 kB
  • references/qa-checklist.md2.7 kB
  • references/scoring.md1.0 kB

Not in the download

Not carried is a type a skill download does not hold. Marked read: its SKILL.md or scripts name the file, so without it the skill works only in part. Take it from its source.

  • scripts/wechat_main_window_delivery.swiftread · not carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 8 scripts beside the text, so the download is 17 files — not the whole of its source: 1 file is left out, and the skill reads it. It is listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# X Insight Cards · 6.8k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/x-insight-cards/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/x-insight-cards" ] && { [ ! -e .claude/skills/x-insight-cards ] || { mv .claude/skills/x-insight-cards "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/x-insight-cards" .claude/skills/ && echo "Installed .claude/skills/x-insight-cards"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add ljunnan24-hash/x-insight-cards

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/x-insight-cards/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/x-insight-cards/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/x-insight-cards" ] && { [ ! -e ~/.claude/skills/x-insight-cards ] || { mv ~/.claude/skills/x-insight-cards "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/x-insight-cards" ~/.claude/skills/ && echo "Installed ~/.claude/skills/x-insight-cards" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/x-insight-cards/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. Not in this download: 1 file of its source, which its SKILL.md or scripts read (which one, and why). Take it from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceljunnan24-hash/x-insight-cards

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

LH
ljunnan24-hash

Publishes on mcprush.

0 servers listed1 skill listed
Profile
Publisher
Servers0