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 5.5 | $0.00029 | $0.00396 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (182 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 989 once invoked, about $0.0003 per session on Opus 5.5. 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.
tiktok-shop-operator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tiktok-shop-operatoraronhy/tiktok-agent-skills | Skill | 182 | 3mo ago | MIT | A | 73 | Codex |
| amazon-reviews-api-skillbrowser-act/skills | Skill | 6.3k | 2d ago | MIT | A | 124 | Claude Code, Codex |
| amazon-competitor-analyzerbrowser-act/skills | Skill | 6.3k | 2d ago | MIT | A | 48 | Claude Code, Codex |
| asc-subscription-localizationrorkai/app-store-connect-cli-skills | Skill | 1.1k | yesterday | MIT | A | 60 | Claude Code |
| food-orderBitterbot-AI/bitterbot-desktop | Skill | 2.5k | yesterday | MIT | A | 53 | Claude Code, Codex |
| external-purchasesrshankras/claude-code-apple-skills | Skill | 864 | 2d ago | MIT | A | 76 | Claude Code |
| Product Photoshoot Workflowjau123/MeiGen-AI-Design-MCP | Skill | 1.8k | yesterday | MIT | A | 111 | Claude Code |