Skip to content
FunCoding

Search

Search docs, Skills and MCP

paid-ads-tiktok

Audit, diagnose, and safely operate connected TikTok Ads accounts through the NotFair MCP. Use for TikTok advertising, Spark Ads, short-form video ads, campaign or ad-group analysis, spend, conversions, targeting, creative, budgets, bids, creator briefs, campaign setup, or approved TikTok Ads changes.

AI 与智能体3.9kpaid-ads/paid-ads-tiktok/SKILL.md

Install

Send this to Claude Code, Codex or Cursor. The agent checks the Skill for safety first and installs it only after you confirm.

读取 https://funcoding.ai/skills/nowork-studio/notfair-plugin/paid-ads-tiktok/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

TikTok Ads

Read ../shared/operating-contract.md and ../shared/measurement-framework.md before acting. Use the live account data from the connected platform as the source of truth.

Establish the live scope

  1. Follow ../../docs/mcp-connection.md. Resolve ~~tiktok-ads to the live connection. Use its current instructions and capability descriptions to choose tools, and verify the requested platform and account from live data. Do not infer access from another connected platform.
  2. Confirm the selected advertiser with a harmless account/setup read. If the connector is missing or unauthorized, direct the user to connect or re-authorize TikTok Ads and stop before claiming live access.
  3. Record the advertiser currency, timezone, objective, conversion definition, attribution basis, and requested date window. Treat tracking gaps as limitations, not zero performance.

This is the TikTok Ads Marketing API v1.3 surface, distinct from creator and Shop APIs. Business membership, billing, payments, creator data, and TikTok Shop are not exposed by this Ads integration. Discover exact tool schemas before calling tools; advertiser_id is always the selected authorized account, and long IDs must be preserved as strings. The connector also exposes code-mode for batched account-scoped reads. Older clients may still reach a dedicated /api/mcp/tiktok_ads route; do not add that as a second plugin MCP server.

Diagnose with one broad read

Pull the delivery entities and performance relevant to the question. Choose available read capabilities and batch related data when useful.

Interpret the platform correctly:

  • Budget and bid values are advertiser currency units, not micros or Meta cents.
  • API code must be zero even when HTTP is 200. Preserve request IDs for support.
  • Honor rate limits; Basic quotas vary by endpoint. Reconnect on expired or revoked access.
  • Reports depend on advertiser timezone and may lag. Compare complete equivalent periods and name spend, impressions, CTR, conversions, CPA, or ROAS only when the returned fields support them.

Lead with the business decision: strongest contributor, largest material risk, likely cause supported by data, and the smallest useful next action. Separate measured facts from inference.

When the request is a creative or launch brief rather than an account mutation, keep the first seconds testable: a distinct hook, product demonstration or proof, native-format direction, CTA, and placement-safe crop. Verify creator rights, music licensing, testimonials, and price/result claims; label unknown proof needs_substantiation. Do not treat views or CTR as a conversion win without the named downstream measure.

Execute approved changes safely

Use a supported write capability and respect its current contract. Show the exact advertiser, entity, current value, proposed value, spend exposure, risk, and rollback before acting. Preview, obtain approval, apply once, then read back.

  • Previews are local validation only, not provider validation.
  • Never retry ambiguous writes automatically.
  • Prefer pause/enable over deletion.
  • Create delivery entities DISABLE unless activation is explicitly requested.
  • After an approved mutation, use the returned evidence or a fresh read to confirm the resulting state. Report partial failures plainly.

Finish with the confirmed action, observation window, success metric, and rollback trigger. A proposal remains ready_for_review; call it published only after the live connector confirms it.

Similar Skills

brand-guidelines
anthropics/skills180k

brand-guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

AI & agents

internal-comms
anthropics/skills180k

internal-comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

AI & agents

template-skill
anthropics/skills180k

template-skill

Replace with description of the skill and when Claude should use it.

AI & agents

mcp-builder
anthropics/skills180k

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

AI & agents

algorithmic-art
anthropics/skills180k

algorithmic-art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

AI & agents

academy-guide
anthropics/skills180k

academy-guide

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

AI & agents