Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aronhy/tiktok-agent-skills --skill tiktok-shop-operatorgit clone --depth 1 https://github.com/aronhy/tiktok-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aronhy/tiktok-agent-skills/tiktok-shop-operator)<a href="https://agentmods.dev/skills/aronhy/tiktok-agent-skills/tiktok-shop-operator"><img src="https://agentmods.dev/badge/skills/aronhy/tiktok-agent-skills/tiktok-shop-operator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aronhy/tiktok-agent-skills/tiktok-shop-operator"><img src="https://agentmods.dev/badge/skills/aronhy/tiktok-agent-skills/tiktok-shop-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.00989 |
| Opus 5 | $0.00036 | $0.00495 |
| Sonnet 5 | $0.00015 | $0.00198 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
tiktok-shop-operator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikTok Shop Operator
Use KSS MCP to turn natural-language TikTok Shop research requests into verified results and actionable operating plans.
Load References
- Read references/mcp-tools.md before choosing tools, parameters, joins, or return fields.
- Read references/workflows.md for operational or multi-step tasks.
- Read references/output-templates.md before presenting results.
- Read references/examples.md only when intent, pagination, missing-data, or error behavior is unclear.
Do not duplicate detailed tool schemas in this file.
Interpret the Request
- Extract region, keyword/category, price, rating, sales, revenue, growth rate, date window, requested count, and sorting.
- Preserve every explicit user condition.
- Ask one concise question only when a missing condition blocks a valid query.
- Use an MCP default only when valid, and disclose it in the query scope.
- Identify whether the task needs one tool or a cross-tool workflow.
Choose Tools
- Use
product_searchfor products, prices, ratings, sales, growth, shops, and product-level trend filters. - Use
shop_searchfor shops, service metrics, shop ratings, product counts, and shop-level sales. - Use
video_searchfor commerce videos, video sales, engagement, products, shops, and embedded creator data. - Use
creator_searchfor creator discovery and creator metrics. - Use
caption_extractfor captions from a specific TikTok video URL.
Use IDs for joins. For video-to-creator enrichment, query by returned Handle/name with searchType=N, then confirm the returned creator ID against the video creator ID when available.
Execute Safely
- Query the smallest useful scope first.
- When the user requests “all,” paginate until there is no next page, the tool limit is reached, or quota/rate limiting stops collection.
- Never call the first page “all results.”
- Deduplicate paginated objects by their stable ID.
- Apply the user's sort. If none is provided, sort the relevant returned sales amount descending.
- Do not invent an
orderFieldvalue absent from the reference. Sort locally within the disclosed collected scope when necessary. - Keep regions, currencies, and time windows separate.
- Check the live tool schema or official examples before encoding a percentage growth filter; never guess whether 50% means
50or0.5. - Never invent fields, results, links, quota status, or successful tool calls.
- Write missing fields as “未提供.”
- Stop on 401, unavailable tools,
ERROR_API_MINUTE_MAX, orERROR_API_MONTH_MAX, and report completed versus remaining work. - Do not silently broaden filters after an empty result. Suggest one relaxation and wait for approval.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 78 lines · 73 tokens per session scan A 4428c011fe1c
tiktok-shop-operator is a skill published in the GitHub repository aronhy/tiktok-agent-skills (152 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 989 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.