demo-video-builder

demo-video-builder is a skill for Claude Code from ahmedawan-oracle/fde_demo_builder. It costs 166 tokens per session (1,996 once invoked), scanned A, original, MIT.

A workflow for turning a real screen recording into a narrated MP4 demo video. It removes pauses, hides private information, and can add an animated opening or ending.

In plain words
What is it for?
Use it to define screen-recording sections, narration, privacy masks, zooms, freezes, and optional opener or outro scenes, then build the finished video.
Why use it?
Raw recordings often contain loading delays, sensitive details, and narration that does not match the action on screen. This workflow organizes those fixes without requiring a video editor.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fde-demo-builder plugin — 1 skill, 2 commands, 1 agent shipped together

Good fit Use it to define screen-recording sections, narration, privacy masks, zooms, freezes, and optional opener or outro scenes, then build the finished video.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ahmedawan-oracle/fde_demo_builder/demo-video-builder
Install

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.

Any agent
npx skills add ahmedawan-oracle/fde_demo_builder --skill demo-video-builder
Clone the repo
git clone --depth 1 https://github.com/ahmedawan-oracle/fde_demo_builder

Made for: Claude Code.

Or install fde-demo-builder, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 1 agent.

Wrote 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.

agentmods badge for demo-video-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahmedawan-oracle/fde_demo_builder/demo-video-builder/github.svg)](https://agentmods.dev/skills/ahmedawan-oracle/fde_demo_builder/demo-video-builder)
Your own site
<a href="https://agentmods.dev/skills/ahmedawan-oracle/fde_demo_builder/demo-video-builder"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/fde_demo_builder/demo-video-builder/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.

agentmods 80×15 button for demo-video-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/ahmedawan-oracle/fde_demo_builder/demo-video-builder"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/fde_demo_builder/demo-video-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00166 $0.01996
Opus 5 $0.00083 $0.00998
Sonnet 5 $0.00033 $0.00399
Haiku 4.5 $0.00017 $0.00200

Measured 6d ago against content hash 8fd46161ccbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

demo-video-builder 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 6d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/assemble.example.sh, scripts/build.py, scripts/demo_config.example.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/demo-video-builder/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Demo Video Builder

Turn one screen recording into a polished, narrated, privacy-clean demo video — fully scripted, no video editor.

Operating principles (read first)

  • Use the real screen, never mock-ups. Every frame comes from the actual recording. Do not fabricate UI, type-ins, or numbers. If a number is spoken in VO, it must be visible on screen at that moment.
  • Privacy is non-negotiable and easy to miss. Real recordings bake in leaks: address-bar URLs with tokens/tenancy IDs, personal bookmarks, browser-extension badges (e.g. Grammarly), usernames, avatars, and internal engineer/customer names typed into fields. Every shipped frame must be scrubbed. See references/privacy-scrubbing.md.
  • Original framing by default. Keep each screen at its native scale; only cover the browser chrome. Reframe/crop only when asked. Use a gentle push-in zoom for readability, not a permanent crop.
  • Sync VO to the action. Fit each beat's footage to its narration so words land on what's on screen.
  • Cut the dead air. Remove "thinking…" / spinner / loading lags — they're the difference between a 3:30 slog and a tight 3:00.
  • One source of truth. demo_config.py holds the beats and their narration. gen_vo.py and build.py both read it. Change the config, re-run — never hand-edit intermediate files.
  • QA until clean. A demo isn't done until an adversarial pass finds no privacy leak, no VO-sync drift, and clean playback. Use the demo-qa-reviewer agent.

The pipeline (7 phases)

  1. Map the recording into beats. Watch/scrub it; note the start/end seconds of each meaningful action (setup, question typed, answer rendered) and every lag to cut. → references/map-and-cut.md
  2. Cut lags — a beat's spans list concatenates only the kept ranges; the gaps (thinking/loading) are dropped automatically. → references/map-and-cut.md
  3. Scrub privacy — cover the browser chrome with a color-matched bar; drawbox-mask any residual leak (subtitle names, extension badges, usernames). Use time-gated masks when content scrolls mid-beat. → references/privacy-scrubbing.md
  4. Frame & zoom — keep native scale (cover chrome, don't crop); add a slow push-in zoompan on dense answers for readability. → references/framing-and-zoom.md
  5. Voiceover — write tight, domain-accurate narration per beat in demo_config.py; gen_vo.py renders one MP3 per beat with edge-tts. → references/voiceover-and-sync.md
  6. Assemble & syncbuild.py time-fits each beat's footage to its VO (freeze-hold if footage is short), overlays the VO, and concatenates with the opener/outro. → references/voiceover-and-sync.md
  7. QA — decode integrity, silence gaps, contact sheet, then the demo-qa-reviewer agent. Fix, rebuild. → references/qa-checklist.md

Read the full file on GitHub · 117 lines

Changes

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.

  1. 6d ago Changed · +30 lines · +77 tokens per session 8fd46161ccbf
  2. 11d ago First seen · 87 lines · 89 tokens per session scan A 34f9fd51a2a2

Subscribe to this mod's changes

demo-video-builder is a skill published in the GitHub repository ahmedawan-oracle/fde_demo_builder (4 stars, last pushed 6d ago), licensed MIT. It adds 166 tokens to every session and 1,996 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens