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 judeyang/judeyang-skills --skill jude-cn-shortvideo-mastergit clone --depth 1 https://github.com/judeyang/judeyang-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/judeyang/judeyang-skills/jude-cn-shortvideo-master)<a href="https://agentmods.dev/skills/judeyang/judeyang-skills/jude-cn-shortvideo-master"><img src="https://agentmods.dev/badge/skills/judeyang/judeyang-skills/jude-cn-shortvideo-master/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/judeyang/judeyang-skills/jude-cn-shortvideo-master"><img src="https://agentmods.dev/badge/skills/judeyang/judeyang-skills/jude-cn-shortvideo-master.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 | $0.00064 | $0.02663 |
| Opus 5 | $0.00032 | $0.01332 |
| Sonnet 5 | $0.00013 | $0.00533 |
| Haiku 4.5 | $0.00006 | $0.00266 |
Grade A, and why
jude-cn-shortvideo-master 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jude 中文短视频主控
Core Contract
After platform and quantity confirmation, produce exactly three human-facing files under outputs/final/:
| File | Reader | Must contain |
|---|---|---|
01-<project>-主编操盘手全局总控.md |
主编/操盘手 | source lock, selection logic, counts, publishing order, source evidence, platform decisions, risks, final go/no-go |
02-<project>-执行团队拍摄发布脚本.md |
拍摄/剪辑/运营 | production specs, item-specific shots, props, subtitles, covers, publish-ready platform copy, pre/post-publish checks |
03-<project>-余教授本人提词表演稿.md |
出镜人 | exact spoken lines, performance cues, forbidden wording, professional blockers |
No fourth human entry file. Process logs are created only when the user asks and stay under outputs/review/ or outputs/editor/.
Role Purity
01 主编只看
Keep strategy, source choices, essential heat evidence, editorial tradeoffs, compliance summary, publishing order, and cross-role approval here. Add calendar dates or posting times only after the chief editor explicitly confirms them.
02 执行团队只看
Keep camera, action, props, subtitles, cover, platform fields, naming, delivery, publishing, and data collection here.
State shared rules once. Do not repeat the same privacy, subtitle, CTA, delivery, or compliance sentence under every item.
Every final 02 must include:
## 拍摄与交付规范## 发布前检查## 发布后回收
03 余教授只看
Keep only:
- what to say
- how to say it
- what not to say
- what professional wording needs his confirmation
Every final 03 must include ## 不能说.
Never put these in 03:
- source links or local paths
- heat numbers
- source-fit or replication scores
- rewrite rationale
- shooting, editing, or publishing instructions
结构模型 / 改写口径 / 参考原视频 / 热度依据
Statuses
| Status | Meaning |
|---|---|
待平台确认 |
source read, platform/form not confirmed; do not write final files |
待生成数量确认 |
platform confirmed, main-video/Vlog counts missing; do not write final files |
待人工审查 |
three draft files exist; human blockers remain |
待修改 |
human feedback returned and must be applied |
修改完成待确认 |
feedback applied; reviewers have not all confirmed |
待最终数量确认 |
reviewers clear; final counts not reconfirmed |
最终执行稿 |
blockers clear and final counts explicitly confirmed |
What ships with it
15 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.
- agents/openai.yaml 306 B
- references/compliance-cn-medical-beauty.md 1.5 KB
- references/delivery-quality-gate.md 4.3 KB
- references/platform-tone.md 1.5 KB
- references/prepublish-checklist.md 2.0 KB
- references/transcript-replication-rules.md 1.0 KB
- scripts/audit_delivery_quality.py 14 KB runs code
- scripts/audit_duration.py 5.2 KB runs code
- scripts/audit_sensitive_claims.py 2.9 KB runs code
- scripts/build_editor_source_trace.py 3.4 KB runs code
- scripts/make_prepublish_checklist.py 3.7 KB runs code
- scripts/sync_teleprompter_to_shooting.py 5.4 KB runs code
- test-prompts.json 2.8 KB
- tests/test_audit_delivery_quality.py 15 KB runs code
- tests/test_sensitive_claims.py 1.7 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.
- 12d ago First seen · 268 lines · 64 tokens per session scan A 0590b5f00c83
jude-cn-shortvideo-master is a skill published in the GitHub repository judeyang/judeyang-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 2,663 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…