Maimai Hub

What it does

Example prompts

• “Maimai,”
• “Colleague Circle,”
• “Career Insights,”
• “/maimai-hub”

Requirements

• Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1URL provided by the user → extract with regex: webcid=([A-Za-z0-9]+)
2. 2Current user's company → visit https://maimai.cn/web/search_center, then execute JS
3. 3Company name matching → built-in script cache + dynamic ranking lookup (circle_rank command)

What it can do on your machine

Read from SKILL.md and the folder at commit ae8c5db. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • maimai.cn

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maimai Hub loads about 1.2k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 296 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~122

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 296 words, ~1,247 tokens.

name

maimai-hub

description

Retrieves data from the Colleague Circle and Career Insights sections of Maimai (maimai.cn). Supports: posts from a specific company's Colleague Circle, the site-wide Career Insights feed (hot/latest/following), the Colleague Circle popularity ranking, and looking up a webcid by company name. This skill must be triggered whenever the user mentions "Maimai," "Colleague Circle," "Career Insights," "maimai," "maimai-hub," or any scenario that requires reading Maimai content.

1. browser_use set_user_agent → desktop_safari
2. browser_use navigate → https://maimai.cn/web/search_center
3. browser_use get_cookies → save to env file
4. Confirm that the env file contains COOKIE_CSRFTOKEN (otherwise, retry steps 2-3)

Colleague Circle page URL format:
https://maimai.cn/company/gossip_discuss?webcid=<WEBCID>

Note: The old paths /web/gossip_discuss and /community/gossip_discuss now both return 404.
You must use /company/gossip_discuss.

1. browser_use navigate → https://maimai.cn/company/gossip_discuss?webcid=<WEBCID>
2. Scroll multiple times to load more content (scroll down × 4~6, 800px each time)
3. Extract post text with browser_use get_readable or execute_js:
   document.querySelectorAll('[class*="content"],[class*="text"],[class*="body"]')
   Filter criteria: length 15~800, exclude noise such as "Maimai", "illegal", and "Colleague Circle popularity"
4. Deduplicate the extracted results, then compile and summarize them

# Colleague Circle posts (must be an employee of that company)
python3 /var/minis/skills/maimai-hub/scripts/maimai.py gossip_circle \
  --webcid 9AG14xzt --count 20 --env <ENV_FILE>

# Look up a Colleague Circle by company name (automatically finds webcid)
python3 /var/minis/skills/maimai-hub/scripts/maimai.py gossip_circle \
  --company Ant Group --count 20 --env <ENV_FILE>

# Site-wide Career Insights feed
python3 /var/minis/skills/maimai-hub/scripts/maimai.py gossip_feed \
  --tab hot --count 20 --env <ENV_FILE>
  # tab: hot(Trending) | new(Latest) | follow(Following) | recommend(Recommended)

# Colleague Circle popularity ranking (gets popular company webcids)
python3 /var/minis/skills/maimai-hub/scripts/maimai.py circle_rank \
  --env <ENV_FILE>

# Look up webcid by company name
python3 /var/minis/skills/maimai-hub/scripts/maimai.py search_company \
  --name ByteDance --env <ENV_FILE>

© OpenMinis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in maimai-hub of OpenMinis/MinisSkills.

• SKILL.md
• scripts/maimai.py

Open the folder on GitHubat commit ae8c5db