tiktok-ads
Skill1 starsChanged 51 days agoMITView on GitHub
Analyze and manage TikTok Ads through Windsor.ai. Use when the user asks about their TikTok Ads performance — pulling live campaign, ad group, or ad metrics (spend, impressions, clicks, conversions, CPA, ROAS), comparing date ranges, or finding top or underperforming campaigns — or when they want to pause or enable a campaign, ad group, or ad, or change a campaign or ad group budget. Do not use for TikTok organic (that's the TikTok Organic connector — no ad or cost data there), or other ad platforms (Meta/Facebook, Google, LinkedIn, Microsoft Ads).
8 other projects use a version of this.
Adopted by
Most recently taken up by
- gomarble-ai/marketing-agenttheir own version, first seen Oct 8, 2026
- vidual-labs/digital-marketing-skillstheir own version, first seen Oct 2, 2026
- sergeyizmailov/knowledge-delta-skillstheir own version, first seen Sep 28, 2026
- slilbudget/knowledge-delta-skillstheir own version, first seen Sep 28, 2026
- ruslan2027/adako-mcptheir own version, first seen Sep 28, 2026
- angelgabrieljacintohuayllasco/marketing-skillstheir own version, first seen Sep 20, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- hyperfx-ai/marketing-skills★ 112same name
- gomarble-ai/marketing-agent★ 15same name
- sergeyizmailov/knowledge-delta-skills★ 3same name
- slilbudget/knowledge-delta-skills★ 3same name
- vidual-labs/digital-marketing-skills★ 3same name
- ruslan2027/adako-mcp★ 1same name
- angelgabrieljacintohuayllasco/marketing-skills★ 0same name
- gmmh1/claude-paid-media-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- business-dataSkill
- crm-insightsSkill
- crm-manageSkill
- ecommerce-insightsSkill
- ecommerce-manageSkill
- facebook-adsSkill
- facebook-organicSkill
- finance-insightsSkill
- gohighlevelSkill
- google-adsSkill
- google-analytics-4Skill
- google-business-profileSkill
- google-merchant-centerSkill
- google-search-consoleSkill
- hubspotSkill
- instagram-publicSkill
- instagramSkill
- klaviyoSkill
- linkedin-adsSkill
- linkedin-pagesSkill
- microsoft-adsSkill
- social-media-createSkill
- social-media-insightsSkill
- tiktok-organicSkill
- web-analytics-insightsSkill
- windsor-connectSkill
- windsor-createSkill
- windsor-exportSkill
- windsor-get-startedSkill
- windsor-insightsSkill
- windsor-manageSkill
- windsor-optimizeSkill
- youtubeSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Reads are safe; writes change live ad spend: Only call execute_action after the user has confirmed the specific change.
- Very specific: line 24
Call get_connectors to see which TikTok Ads accounts are connected (each has an id and, usually, a name).
- Distinctive: line 30
If the user names an account, match it to a connected account id.
- Very specific: line 35
Call get_fields for tiktok to get valid field ids (e.g.
- Very specific: line 38
If the analysis needs attribution or segmentation controls, call get_options to see the connector's options and valid values.
- Distinctive: line 97
Write workflow — every time:
- Very specific: line 105
Only after an explicit yes, call execute_action and report the result.
- Distinctive: line 107
If the user says "pause the worst campaign", first do the read + ranking, then name the specific campaign and confirm before pausing — …
- Very specific: line 113
If a tool returns an error (unknown field/connector/account), call the relevant discovery tool (get_fields, get_connectors, list_actions) …
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
TikTok Ads via Windsor.ai
Windsor.ai exposes live TikTok Ads data (read) and a small set of campaign
management actions (write) through MCP tools. The connector id is tiktok.
Pass tiktok as the connector on every tool call; the Windsor.ai server
serves all connectors, so it is never implied.
Golden rules:
- Never guess field, account, action, or option names. They come from
get_fields,get_connectors,list_actions, andget_options. Call those first; do not invent identifiers. - Reads are safe; writes change live ad spend. Only call
execute_actionafter the user has confirmed the specific change. - Report numbers the user asked for, concisely. Don't dump raw rows unless asked.
1. Ground yourself first
Call get_connectors to see which TikTok Ads accounts are connected (each has
an id and, usually, a name). If none are connected, help the user connect one:
call get_connector_authorization_url (or get_connector_connect_info for the
auth type and steps) and give them the setup link — do not describe manual
dashboard navigation.
If the user names an account, match it to a connected account id. If several are connected and the request is ambiguous, ask which account.
2. Reading performance data
- Call
get_fieldsfortiktokto get valid field ids (e.g. campaign, ad_group, ad, date, spend, impressions, clicks, conversions, ROAS, CPA — use the exact ids returned, not these examples). - If the analysis needs attribution or segmentation controls, call
get_optionsto see the connector's options and valid values. - Call
get_datawith:fields: the ids you actually need (keep the set small).accounts: the target account id(s); omit for all connected accounts.- A date range: either
date_from/date_to("2026-07-01"), ordate_preset—last_7d,last_30d,last_Xd/last_Xw/last_Xm,this_month,this_year,last_year. AppendTto include today (e.g.last_7dT,this_monthT). options: only if get_options showed relevant ones.filters: optional conditions, e.g.[["spend", "gt", 100]]; combine with"and"/"or"and nest as needed.
Common requests → recipe:
- Overview / trend: fields
date+ the metrics, over a preset range. - By campaign: fields
campaign+ metrics; sort/aggregate in your answer. - Best / worst campaign: pull campaign + the metric, then rank; return only what was asked (e.g. just the campaign name) if the user constrained the output format.
- Efficiency: CPA = spend ÷ conversions; ROAS = conversion value ÷ spend. Compute from returned fields; note if conversions are zero.
Watch out: TikTok Ads money fields are in the account currency (state it if
known). If a field the user wants isn't in get_fields, say so rather than
substituting a different metric.
3. Managing campaigns (write actions)
TikTok Ads exposes a small set of write actions via list_actions /
execute_action. Always call list_actions first for the exact ids and JSON
schemas — treat the summary below as guidance, not gospel. They cover:
- Status:
pause_campaign/enable_campaign,pause_ad_group/enable_ad_group,pause_ad/enable_ad— each reversible via its counterpart. - Budget:
set_campaign_budget(needscampaign_idandamount) andset_ad_group_budget(needsad_group_idandamount). There is no ad-level budget action.
Budget mechanics:
- Amounts are in the account currency major unit, not a subunit —
100means one hundred, not cents or micros. - The budget type (daily, lifetime, or dynamic daily) is fixed when the campaign or ad group was created and is detected automatically; you only supply the new amount, not the type.
set_campaign_budgetandset_ad_group_budgetset an absolute value, not a delta. To "raise by 20%", read the current budget first (viaget_dataor the platform), compute the new absolute amount, and set that.- A campaign whose budget is unlimited (
BUDGET_MODE_INFINITE) or managed at the ad group level has no campaign budget to set — useset_ad_group_budgetinstead, and vice versa for an ad group whose budget is managed at the campaign level (Campaign Budget Optimization). The action reports this rather than silently doing nothing. - Lifetime budget changes take effect immediately. Daily and dynamic daily budget changes take effect from 00:00 the following day in the ad account's time zone — say so if the user expects an instant change.
Write workflow — every time:
- Resolve the campaign/ad group/ad to its id (via a
get_dataread on the corresponding name and id fields if the user gave a name). - Build the exact params from the
list_actionsschema. - Show the user the concrete change and ask them to confirm — e.g. "Pause campaign 'Summer Sale' (id 123…) on account 456…?" or "Set daily budget for ad group X to €50.00?".
- Only after an explicit yes, call
execute_actionand report the result.
If the user says "pause the worst campaign", first do the read + ranking, then name the specific campaign and confirm before pausing — don't pause on the strength of the aggregate alone.
4. Reference the user's data, don't fabricate
If a tool returns an error (unknown field/connector/account), call the relevant
discovery tool (get_fields, get_connectors, list_actions) and retry with
correct ids. Never fill gaps with made-up numbers or campaign names.
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.

