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 krillinai/growth-skills --skill douyin-ads-auditgit clone --depth 1 https://github.com/krillinai/growth-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/krillinai/growth-skills/douyin-ads-audit)<a href="https://agentmods.dev/skills/krillinai/growth-skills/douyin-ads-audit"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/douyin-ads-audit/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/krillinai/growth-skills/douyin-ads-audit"><img src="https://agentmods.dev/badge/skills/krillinai/growth-skills/douyin-ads-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 42 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00088 | $0.01907 |
| Opus 5.5 | $0.00035 | $0.00763 |
| Sonnet 5.5 | $0.00018 | $0.00381 |
| Haiku 4.5 | $0.00009 | $0.00191 |
Grade A, and why
douyin-ads-audit 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Douyin Ads Audit
Audit supplied Douyin advertising evidence without logging into or changing an account. Separate Ocean Engine, Qianchuan, DOU+, Xingtu, organic Douyin, shop or livestream operations, platform attribution, and business outcomes. Return bounded findings and decision rules instead of importing international TikTok practices or inventing platform targets.
Read input-contract.md before requesting or validating exports. Read analysis-methods.md for platform-surface, delivery, creative, creator-rights, commerce, destination, measurement, economics, and change-diagnosis methods. Apply evidence-and-boundaries.md to every claim and action. Use playbook-sources.md for the pinned Growth Playbook basis and current official China platform references.
Select One Mode
| Mode | Use |
|---|---|
intake |
Build or validate the canonical local bundle and identify decision-critical missing evidence |
full |
Audit structure, delivery, creative, destinations, measurement, customer quality, and economics across explicitly separated surfaces |
creative |
Audit concepts, hooks, variants, formats, accounts, creators, livestream or product context, claims, fatigue signals, and rights |
commerce |
Audit supplied Qianchuan product or livestream delivery, attributed orders or GMV, refunds, commissions, fulfillment, contribution, and retained value |
measurement |
Audit conversion definitions, web, app, lead, shop or offline evidence, attribution, reconciliation, customer definitions, and incrementality |
performance |
Investigate a reported change without treating its timing, magnitude, or cause as verified |
out-of-scope |
Decline international TikTok use, live account access, credential or authorization-code handling, personal lead data, or external action |
Name one primary mode. A partial bundle can support a bounded creative, commerce, or measurement review; mark unsupported sections unavailable.
What ships with it
16 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.
- assets/input-bundle/ad-groups.template.csv 501 B
- assets/input-bundle/ads.template.csv 617 B
- assets/input-bundle/business-outcomes.template.csv 279 B
- assets/input-bundle/campaigns.template.csv 365 B
- assets/input-bundle/commerce-outcomes.template.csv 393 B
- assets/input-bundle/context.template.json 454 B
- assets/input-bundle/conversion-definitions.template.csv 484 B
- assets/input-bundle/creatives.template.csv 832 B
- assets/input-bundle/daily-performance.template.csv 505 B
- assets/input-bundle/destinations.template.csv 488 B
- references/analysis-methods.md 6.2 KB
- references/evidence-and-boundaries.md 3.3 KB
- references/input-contract.md 7.0 KB
- references/playbook-sources.md 1.6 KB
- scripts/test_validate_input_bundle.py 6.7 KB runs code
- scripts/validate_input_bundle.py 17 KB runs code
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 · 91 lines · 88 tokens per session scan A 44226d9d793a
douyin-ads-audit is a skill published in the GitHub repository krillinai/growth-skills (43 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,907 once invoked, about $0.0004 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 2026-09-03.
douyin-ads-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| douyin-ads-auditkrillinai/growth-skills | Skill | 43 | 2mo ago | MIT | A | 88 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |