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 liuluhaixiu/DaVinci-AutoEdit-Agent --skill viral-video-writergit clone --depth 1 https://github.com/liuluhaixiu/DaVinci-AutoEdit-AgentWrote 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/liuluhaixiu/davinci-autoedit-agent/viral-video-writer)<a href="https://agentmods.dev/skills/liuluhaixiu/davinci-autoedit-agent/viral-video-writer"><img src="https://agentmods.dev/badge/skills/liuluhaixiu/davinci-autoedit-agent/viral-video-writer/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/liuluhaixiu/davinci-autoedit-agent/viral-video-writer"><img src="https://agentmods.dev/badge/skills/liuluhaixiu/davinci-autoedit-agent/viral-video-writer.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 | $0.00068 | $0.00574 |
| Opus 5 | $0.00034 | $0.00287 |
| Sonnet 5 | $0.00014 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
viral-video-writer 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 13d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viral Video Writer
Write from the approved brief and material review. Do not invent visuals, quotes, people, events, locations, or claims.
Intake
Use already supplied information. Ask only for missing topic, platform, audience, duration, language, tone, narration policy, and constraints.
Develop Direction
Before drafting, internally test:
- One memorable core idea
- Two or three supporting ideas
- Evidence available in the footage
- Audience tension or curiosity
- Emotional curve
- Point of view and voice
- Hook, turn, climax, and aftertaste
- Natural interaction prompt, when appropriate
Present 2-3 distinct story directions with tradeoffs. Obtain the user's choice before drafting the full script.
Draft
Match language density to the edit:
- Do not narrate what the viewer can already understand.
- Leave room for dialogue, action, natural sound, music, and silence.
- Use short speakable sentences for voiceover.
- Mark factual uncertainty instead of smoothing it over.
- Tie each narrated beat to approved visual evidence or label it as a non-visual contextual statement requiring user verification.
Include:
- selected core idea
- scene/section sequence
- narration or dialogue intent
- visual evidence references
- emotional and rhythm notes
- five title/hook options when platform publishing is part of the request
Show the complete draft in chat. Write it only after explicit approval.
Platform Adaptation
Treat platform variants as rewrites, not truncations:
- Long-form video: sustain questions, progression, callbacks, and breathing room.
- Short-form vertical: immediate context, one idea, rapid evidence, clean payoff.
- Documentary: protect ambiguity, observed detail, and factual confidence.
- Tutorial/explainer: optimize comprehension, examples, and visual demonstrations.
- Brand/event: preserve required facts without turning every line into a slogan.
Quality Bar
- Specific beats generic.
- Human cadence beats slogan density.
- Emotional force must come from observed detail and structure.
- A strong line should clarify the idea, not merely sound quotable.
- The script must remain editable when TTS is disabled.
What ships with it
3 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.
- 13d ago First seen · 76 lines · 68 tokens per session scan A b6acc1bcf186
viral-video-writer is a skill published in the GitHub repository liuluhaixiu/DaVinci-AutoEdit-Agent (456 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 574 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 2026-08-30.
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…