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.
npx skills add qinyuanpei/mcp-server-weibo --skill weibo-personalitygit clone --depth 1 https://github.com/qinyuanpei/mcp-server-weiboWrote 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.
[](https://agentmods.dev/skills/qinyuanpei/mcp-server-weibo/weibo-personality)<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.
<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>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 | $0.00043 | $0.00330 |
| Sonnet 5 | $0.00017 | $0.00132 |
| Haiku 4.5 | $0.00009 | $0.00066 |
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 today.
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.
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-cliinstalled 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 fromtext. - 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.
- Prefer each item's
-
Generate the report. Fill the template's
profileandtweetsslots 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_countmust 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.
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.
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.
- today First seen · 45 lines · 86 tokens per session scan A b2105e4450af
weibo-personality is a skill published in the GitHub repository qinyuanpei/mcp-server-weibo (61 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 660 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
delegacion-local
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
event-staffing-ordering
Order W-2 event staff for US/CA events through TempGuru.
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…