TikTok Research
Use this as the TikTok research entrypoint when the user wants public TikTok evidence for a growth, marketing, creator, audience, competitor, or paid creative decision.
TikTok music/archive download is not part of the released public surface.
Reference Index
Read only the one route reference matching the request. The local contract is optional detail when platform scope remains unclear.
First Question
Ask one question only when the answer changes platform, route, public/private boundary, first-pass scope, or output shape.
Do not ask for credentials, private exports, retry strategy, cookies, or music archive details.
Run Discipline
- Route the request with the table above.
- Read only the selected workflow reference.
- Run the narrowest collection chain that can answer the first pass.
- Stop after the first pass and report scope, evidence, limits, and next action.
Do not present a public sample as full TikTok truth. Do not use paid ads as organic creator evidence. Do not use organic videos as paid ad proof. Use only the filters shown by the selected route.
For local testing, optimize for a fast real first pass. Use the command selection below; do not inspect fixtures or product mappings.
Public Command Boundary
-
Choose the smallest matching command or workflow from the user input and run it directly.
-
Readiness diagnostics:
postplus doctor --skill tiktok-research. -
Inspect a route with
postplus research run <route> --helponly when its semantic flags are not already clear. -
Run
postplus research run <route> --<query/url/handle/hashtag flags> --limit <n> --wait --output <result.json>. -
Keep the first pass bounded; expand only after inspecting the first result.
-
If the CLI returns a quote-confirmation challenge, reuse existing explicit user approval only when it covers the challenge scope and maximum cost; otherwise obtain approval before running
postplus quote confirm --json --challenge-file <challenge.json>and retry with the returned token.
Command Selection
Only if platform scope or evidence interpretation remains unclear, consult platform contract [blocked]; it is not a preflight.
Evidence Quality
- Check whether results are organic videos, comments, profiles, or paid examples; never substitute one lane for another.
- Change one supported seed, market, or query when a completed result misses; collect comments only from relevant shortlisted video URLs.
- Allow at most two changed follow-up passes after successful but insufficient results, within approved scope and budget; do not repeat an identical request or hide a failed/pending operation.
- Stop when sufficient, at the bound, or when another pass would not help. Report useful evidence and uncertainty; preserve raw results and source links.
Captions and views are not audience voice or sales; preserve the paid/organic source and observed date.
Full machine fields belong to postplus research schema --route <route> --json;
consult it only when required for processing, not before every request.
Follow the CLI's structured result and reported next action; do not infer recovery from free-text messages. Reuse explicit user approval that already covers the requested scope and maximum cost; otherwise obtain approval before confirming a quote. Never infer spending authorization from a task alone. Resume the same operation through its returned checkpoint or action; never resubmit uncertain work, repeat exhausted recovery, or switch providers to bypass failure.
<!-- END GENERATED EXECUTION EXAMPLE -->