What is weibo-personality?

A skill that creates an entertainment-style personality report from a Weibo user's profile and recent posts. It fetches the public data, applies a report template, and returns a Chinese JSON result with a readable summary.

It helps resolve a user's Weibo ID, collect profile and post data, and produce sections such as strengths, weaknesses, relationship or money predictions, pickup lines, and a roast.

It turns scattered social-media information into a fixed report format, while making clear that the predictions and personality reading are for entertainment.

weibo-personality — Skill for Claude Code and Codex by qinyuanpei

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add qinyuanpei/mcp-server-weibo --skill weibo-personality

Clone the repo

git clone --depth 1 https://github.com/qinyuanpei/mcp-server-weibo

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qinyuanpei/mcp-server-weibo/weibo-personality/github.svg)](https://agentmods.dev/skills/qinyuanpei/mcp-server-weibo/weibo-personality)

Your own site

<a href="https://agentmods.dev/skills/qinyuanpei/mcp-server-weibo/weibo-personality"><img src="https://agentmods.dev/badge/skills/qinyuanpei/mcp-server-weibo/weibo-personality/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qinyuanpei/mcp-server-weibo/weibo-personality"><img src="https://agentmods.dev/badge/skills/qinyuanpei/mcp-server-weibo/weibo-personality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 660 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00086	$0.00660
Opus 5.5	$0.00034	$0.00264
Sonnet 5.5	$0.00017	$0.00132
Haiku 4.5	$0.00009	$0.00066

Measured 1mo ago against content hash b2105e4450af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

weibo-personality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/weibo-personality/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weibo Personality Report

Turn a Weibo user's public profile and recent posts into an entertainment-grade personality report: strengths, weaknesses, love/money/health predictions, pickup lines, roast, and more. You are the LLM - no API key, no backend service. Data comes from the Weibo CLI, reasoning comes from you.

Prerequisites

weibo-cli installed and working. Install and command basics are in the Weibo CLI skill.
Read both reference files before generating:
- references/prompt-template.md - the prompt to follow, with fill-in slots
- references/output-schema.md - exact JSON keys and field rules

Workflow

Resolve the UID. If the user gives a nickname instead of a UID, find it with weibo-cli users "<name>" -n 5. Verify by description and follower count; confirm with the user when ambiguous.
Fetch the profile.
```
weibo-cli profile <uid>
```
Fetch posts.
```
weibo-cli feeds <uid> -n 50 --no-include-pics
```
- Prefer each item's raw_text; otherwise strip HTML tags from text.
- Known limit: guest sessions return only the ~10 most recent posts. For a deeper report, ask the user to run weibo-cli login (QR scan), then retry with -n 50.
- If the user asks for a time window (e.g. last six months), drop older posts after fetching and say how many posts survived.
Generate the report. Fill the template's profile and tweets slots with the fetched data, follow the output schema exactly, and write all generated content in Chinese.
- name, avatar_hd, description, profile_url, follow_count, followers_count must be copied from the fetched profile. Never invent them.
Deliver. Present a readable formatted report first. Offer the raw JSON as a follow-up (save to file or inline) rather than dumping it by default.

Guardrails

This is horoscope-style entertainment, not a psychological assessment. Say so when delivering the report.
Only analyze public accounts. Refuse locked/private accounts.
The roast should be edgy and witty about the persona's expressed traits - never slurs, never attacks on protected characteristics.
Ground every claim in the fetched posts. If the sample is small (fewer than ~15 posts), say so and note the report is based on a thin sample.

Read the full file on GitHub · 45 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 45 lines · 86 tokens per session scan A b2105e4450af

Subscribe to this mod's changes

weibo-personality is a skill published in the GitHub repository qinyuanpei/mcp-server-weibo (68 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 660 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-17.

Creative and media mcp-server model model-context-protocol sina-weibo socal-media weibo

weibo-personality next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
weibo-personalityqinyuanpei/mcp-server-weibo	Skill	68	1mo ago	MIT	A	86	Claude Code, Codex
opik-diagnosecomet-ml/opik-mcp	Skill	226	3d ago	Apache-2.0	A	187	Claude Code
qmclaw-workbenchxi-zhao/OpenQuantum	Skill	72	yesterday	MIT	A	124	Codex
cortex-explore-memorycdeust/Cortex	Skill	76	2d ago	MIT	A	91	Claude Code
quantum-groverxi-zhao/OpenQuantum	Skill	72	yesterday	MIT	A	62	Claude Code, Codex
quantum-algorithmsxi-zhao/OpenQuantum	Skill	72	yesterday	MIT	A	34	Claude Code, Codex
alicebob-cat-circuitsxi-zhao/OpenQuantum	Skill	72	yesterday	MIT	A	51	Claude Code, Codex