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 jykim/claude-obsidian-skills --skill remotion-narrated-video-essaygit clone --depth 1 https://github.com/jykim/claude-obsidian-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/jykim/claude-obsidian-skills/remotion-narrated-video-essay)<a href="https://agentmods.dev/skills/jykim/claude-obsidian-skills/remotion-narrated-video-essay"><img src="https://agentmods.dev/badge/skills/jykim/claude-obsidian-skills/remotion-narrated-video-essay/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/jykim/claude-obsidian-skills/remotion-narrated-video-essay"><img src="https://agentmods.dev/badge/skills/jykim/claude-obsidian-skills/remotion-narrated-video-essay.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 | $0.00056 | $0.00901 |
| Opus 5.5 | $0.00022 | $0.00360 |
| Sonnet 5.5 | $0.00011 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
remotion-narrated-video-essay 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remotion Narrated Video Essay
Build a polished video around the recorded narration while preserving the speaker's pace and point of view.
Editorial shape
- Keep the talking-head shot as the default visual. Prefer contextual media as an overlay rather than cutting away repeatedly.
- Use full-screen material sparingly: reserve it for a visually rich event or a sustained screen capture that needs attention.
- Match each overlay to the actual speaking beat. When narration is shortened, derive every B-roll cue from the same original-to-edited timeline mapping rather than shifting timings by guesswork.
- If cleaning a recorded talk, remove only clear filler, dead air, or repeated explanation at sentence boundaries. Preserve natural breaths and any cut that would create a visible pose or gaze jump.
- Never alter the camera original. Create a separately named proxy or edited narration track.
Narration phrasing and timing
- Before generating narration, audit long lists, parallel clauses, comparisons, and closing triads for phrases that the voice may run together. When the user limits the edit by priority, change only the approved priority tier and preserve every word; punctuation-only approval does not authorize rewriting.
- Regenerate only the affected narration IDs, use versioned filenames, and keep unrelated visuals and audio unchanged except for timing adjustments required by the new duration.
- Do not assume commas or periods created an audible pause. Check the selected WAV with word timestamps and
silencedetect, and record the pause at every edited high-priority boundary. - Base scene safety on the final spoken-word end rather than the container duration. Leave at least 0.5 seconds before the next narration, music entry, transition overlap, or scene end. For a music cue triggered by a mention, measure from the end of the mentioned phrase.
Layout and visual hierarchy
- Inspect the speaker frame before placing an overlay. Put cards opposite the face and change side when the speaker's position changes later in the recording.
- Keep overlays clear of the eyes, face, and important gestures. Use a consistent card size, corner treatment, and restrained shadow.
- Remove redundant eyebrow labels and tiny descriptive captions. A card should usually contain one large title and one legible explanatory line or two.
- Match card colors to the camera's actual palette rather than imposing a disconnected theme. Preserve enough contrast for small-screen viewing.
- For a tall analytics or dashboard screenshot, use a full-screen still and animate a slow, continuous vertical scroll across the useful content. Do not add browser chrome, ads, or unrelated page areas.
- Clearly distinguish real footage from reconstructed or AI-generated interface concepts. Do not imply that a concept visual is a real product capture.
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.
- 1mo ago First seen · 48 lines · 56 tokens per session scan A 7c9bff550959
remotion-narrated-video-essay is a skill published in the GitHub repository jykim/claude-obsidian-skills (50 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 901 once invoked, about $0.0002 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 2026-09-22.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…