tikhub-query
Skill4 starsChanged 3 months agoMITView on GitHub
Query TikTok video details through the company-internal metered TikHub HTTP gateway. Use when a user provides a TikTok video URL or asks for TikHub/TikTok data; the deterministic client reads the current lark-cli user's Feishu open_id and name and attaches them only for internal usage attribution.
In this repository22 other files it gives its agents.
- aihotSkill
- bilibili-creator-finderSkill
- douyin-scraperSkill
- feishu-cli-managerSkill
- funcinating-guidesSkill
- funcinating-newsSkill
- hot-topicsSkill
- humanizerSkill
- humanizer-zhSkill
- imap-smtp-emailSkill
- lark-base-replicaSkill
- oss-uploadSkill
- seedance-promptSkill
- shopifySkill
- skill-publisherSkill
- skill-vetterSkill
- slider-captchaSkill
- tiktok-scraperSkill
- video-downloadSkill
- wechat-scraperSkill
- weibo-scraperSkill
- xiaohongshu-scraperSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 8 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use scripts/tikhub_query.py.
- Distinctive: line 14
Run from this Skill directory:
- Very specific: line 21
Use --shop-region MX only when the user supplies or requests a region override.
- Distinctive: line 28
Follow the user's requested fields, ordering, language, and format when specified.
- Distinctive: line 29
Use only values present in the response.
- Distinctive: line 34
Treat Feishu identity as internal usage attribution, not verified authorization.
- Distinctive: line 35
Never print or request the VPS TikHub upstream Token.
- Distinctive: line 36
Never retry a failed paid query automatically.
- Distinctive: line 37
Never add a gateway override or arbitrary endpoint.
- Very specific: line 38
Run status to verify the current Feishu identity or doctor to check local dependencies.
- Very specific: line 39
If the identity is unavailable, follow the lark-shared user authorization flow and retry.
- Distinctive: line 41
Read references/protocol.md only when diagnosing request or response behavior.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
TikHub Query
Use scripts/tikhub_query.py; do not rebuild the HTTP request manually.
Query
Run from this Skill directory:
python3 scripts/tikhub_query.py query \
--url 'https://www.tiktok.com/@creator/video/7645609920322112798'Use --shop-region MX only when the user supplies or requests a region override. Return the business JSON and usage receipt from the command.
The client automatically calls lark-cli contact +get-user --as user --format json, adds the current employee's tenant_key, open_id, name, and original TikTok URL to the query, and creates one idempotency key. On first use, the server adds the employee to the Feishu Base personnel table with a default monthly limit of 1000; later calls use the administrator-maintained monthly limit and active state. It does not use a personal gateway Token, Keychain, approval card, PKCE, or local pending state.
Return result
- By default, lead with the five business metrics from the successful response: play, like, comment, collect, and share counts. Then include the gateway request ID and usage receipt concisely.
- Follow the user's requested fields, ordering, language, and format when specified. Reformat or select fields from the same response; never send another paid query only to change the presentation.
- Use only values present in the response. If a requested field is missing or null, say it is unavailable instead of guessing.
- Return the full business JSON only when the user explicitly asks for raw or complete JSON, or when it is necessary for diagnosis.
Safety boundary
- Treat Feishu identity as internal usage attribution, not verified authorization. The company network/IP allowlist is the access boundary; an internal caller could spoof another employee's identity.
- Never print or request the VPS TikHub upstream Token. It remains server-side.
- Never retry a failed paid query automatically. Ask before sending another query because the first result may be uncertain.
- Never add a gateway override or arbitrary endpoint. The client is fixed to the company-internal HTTP gateway.
- Run
statusto verify the current Feishu identity ordoctorto check local dependencies. - If the identity is unavailable, follow the
lark-shareduser authorization flow and retry.
Read references/protocol.md only when diagnosing request or response behavior.
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
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.