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 amazing-fish/agent-skills --skill douyin-video-analysisgit clone --depth 1 https://github.com/amazing-fish/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/amazing-fish/agent-skills/douyin-video-analysis)<a href="https://agentmods.dev/skills/amazing-fish/agent-skills/douyin-video-analysis"><img src="https://agentmods.dev/badge/skills/amazing-fish/agent-skills/douyin-video-analysis/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/amazing-fish/agent-skills/douyin-video-analysis"><img src="https://agentmods.dev/badge/skills/amazing-fish/agent-skills/douyin-video-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.00785 |
| Opus 5 | $0.00026 | $0.00392 |
| Sonnet 5 | $0.00010 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
douyin-video-analysis 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 11d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
抖音视频分析
Overview
Turn a Douyin video link into an evidence-backed research report. Prefer parsed page copy, captions, local/free transcription, and key frames over unsupported inference.
Workflow
-
Resolve the input
- Extract the first URL from share text.
- Record the original URL, resolved URL, redirect chain, status code, and crawl method.
- If a compatible parser exists in the active workspace, prefer its documented CLI over ad hoc scraping. This Skill does not bundle a parser runtime. For a workspace that provides the
douyin_analyzerpackage, a compatible example is:python -m douyin_analyzer.cli analyze "<share text or URL>" --out "reports/douyin-video-analysis/<run-id>" --stt-backend auto
-
Collect evidence
- Extract page title, author, description, hashtags, captions, and video/media URLs.
- If HTTP parsing fails, use browser rendering/network capture and save diagnostics.
- Download media only when the source URL is accessible and allowed by the current session constraints.
- Use free/local speech-to-text first: page captions, then
faster-whisper, thenFunASR; do not use paid STT unless the user explicitly asks. - Extract 3-7 key frames across the video or around uncertain transcript sections.
-
Separate evidence from interpretation
- Treat transcript text, page metadata, frames, and network diagnostics as evidence.
- Mark low-confidence ASR, missing captions, blocked pages, or inferred claims.
- Never invent exact quotes, figures, interactions, claims, or visual details not present in evidence.
-
Analyze deeply
- Identify the video's thesis, argument structure, assumptions, examples, and implied framework.
- Compare page copy with transcript and frames; flag mismatches.
- For technical, financial, or trading videos, distinguish education, strategy rules, unverifiable claims, and risk warnings.
- Use key frames to adjudicate ambiguous transcript passages, especially charts, slides, formulas, or UI demonstrations.
What ships with it
2 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.
- 11d ago First seen · 57 lines · 52 tokens per session scan A 4accc9630e28
douyin-video-analysis is a skill published in the GitHub repository amazing-fish/agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 785 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…