Agent skill

To Narration

by sugarforever in sugarforever/boring-video-studio

A skill your agent uses when writing or revising spoken narration from complete, lineage-valid video beats, including scripts that must remain open to later visual direction.

MITAuto-check passedMedia & Creative

Install To Narration

skills CLI
$ npx skills add sugarforever/boring-video-studio --skill to-narration -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sugarforever/boring-video-studio to-narration --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sugarforever/boring-video-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/boring-video/to-narration .claude/skills/to-narration && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
to-narration
GitHub stars
168
Token cost
~821 tokens
SKILL.md length
394 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing or revising spoken narration from complete, lineage-valid video beats, including scripts that must remain open to later visual direction.

  • Works in 5 steps: Read BEATS.md, its approved… → Write for the ear: one thought per… → Let visuals carry visible structure,… → …
  • Revising spoken narration from complete
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Lineage-valid video beats

What it does

To Narration is an agent skill from sugarforever/boring-video-studio. Use when writing or revising spoken narration from complete, lineage-valid video beats, including scripts that must remain open to later visual direction.

Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Text to speech and voice. The repository describes itself as: 小木头的个人视频流水线 Agent Skill - VerySmallWoods Video. The licence is MIT.

When your agent uses it

  • Revising spoken narration from complete
  • Lineage-valid video beats
  • Including scripts that must remain open to later visual direction

Example prompts

  • “/to-narration”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read BEATS.md, its approved content/ARTICLE.md source, the cited evidence needed for accuracy, and the resolved voice sources recorded by…
  2. Write for the ear: one thought per sentence, concrete subjects and verbs, spoken transitions, and terminology explained at first use…
  3. Let visuals carry visible structure, comparison, and transformation. The narration supplies meaning the image cannot communicate alone.
  4. Mark paragraph-to-beat boundaries without adding visual instructions. Put unresolved pronunciation or factual questions in an Open checks…
  5. Write NARRATION.md

What it can do on your machine

Read from SKILL.md and the folder at commit f3445d6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

To Narration loads about 821 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 394 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~821

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sugarforever/boring-video-studio at commit f3445d6, republished under its MIT licence (© sugarforever). 394 words, ~821 tokens.

Download SKILL.mdSave it as .claude/skills/to-narration/SKILL.md (or your agent's skills folder).
name
to-narration
description
Use when writing or revising spoken narration from complete, lineage-valid video beats, including scripts that must remain open to later visual direction.

To narration

Turn BEATS.md into NARRATION.md: the spoken version of the approved article and video structure. This pass changes language for the ear; it does not establish the author's argument for the first time.

Process

  1. Read BEATS.md, its approved content/ARTICLE.md source, the cited evidence needed for accuracy, and the resolved voice sources recorded by the article. Recompute the article approval digest and beats artifact digest; require them to match the stored article approved_digest, beats source_digest, and beats artifact_digest. Load every applicable writing-style skill or document that is available. Preserve each beat's job, claim, and handoff.
  2. Write for the ear: one thought per sentence, concrete subjects and verbs, spoken transitions, and terminology explained at first use. Preserve the author's voice while adapting reading prose into speech.
  3. Let visuals carry visible structure, comparison, and transformation. The narration supplies meaning the image cannot communicate alone.
  4. Mark paragraph-to-beat boundaries without adding visual instructions. Put unresolved pronunciation or factual questions in an Open checks section.
  5. Write NARRATION.md:
markdown
---
source: BEATS.md
source_digest: sha256:<BEATS artifact_digest>
content_source: content/ARTICLE.md
content_digest: sha256:<ARTICLE approved_digest>
artifact_digest: sha256:<digest>
status: draft
target_duration: ...
---

## B01 — Title

<a id="b01-p01"></a>
Spoken paragraph.

Compute artifact_digest as SHA-256 of the complete narration file after removing only the artifact_digest: line. Downstream stages must recompute it before use.

  1. Give every paragraph a stable <beat-id>-pNN anchor. Preserve anchors when rewriting that paragraph; assign a new anchor when inserting one.
  2. Read it aloud or estimate at the user's known speaking rate. Revise until every beat fits its budget and the full draft fits the target.

Every material fact, viewpoint, and conclusion must trace through its beat to the approved article. When speech needs content the article does not establish, immediately return content/ARTICLE.md to status: draft and revise it there; return content/TOPIC.md to draft too when the change affects a locked topic decision. Renew the approvals defined by those upstream files, update BEATS.md to match, and only then use the content in narration. BEATS.md has no separate approval state in this workflow.

Show full SKILL.md (82 more words)Show less

REQUIRED SUB-SKILL: Use artifact-preview for NARRATION.md before declaring it complete and after every later source change. Present it for inspection without starting or replacing HyperFrames' later voice-review loop.

The draft is complete when it is ready for visual planning, every material sentence traces to both a beat and the approved article, no later visual has been prematurely prescribed, and the artifact-preview completion criterion is satisfied for NARRATION.preview.html. The shared HyperFrames project owns review timing and the voice-ready narration version once /to-scenes begins.

© sugarforever, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/boring-video/to-narration of sugarforever/boring-video-studio.

Open the folder on GitHubat commit f3445d6

Compare with similar skills

To Narration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

To Narration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
To Narration this skillsugarforever/boring-video-studio168—~821Automated safety check: PassMIT
MoneyPrinterTurbo Video Generatorharry0703/MoneyPrinterTurbo129k—~2.1kAutomated safety check: WarnMIT
HyperFrames Media Useheygen-com/hyperframes60k—~2.4kAutomated safety check: PassApache-2.0
Openspec OnboardSAP/e-mobility-charging-stations-simulator22725 repos~3.5kAutomated safety check: PassMIT
Blog AudioAgriciDaniel/claude-blog2.3k1 repos~2.2kAutomated safety check: NotesMIT
Musictadaspetra/loop2962 repos~827Automated safety check: PassMIT

Similar skills

  • MoneyPrinterTurbo Video Generator

    harry0703/MoneyPrinterTurbo

    Installs and runs MoneyPrinterTurbo to turn a topic or script into a finished short video with voice-over, subtitles, stock footage and music.

    129k GitHub stars~2.1k tokensUpdated today
    Media & CreativeAuto-check: warnings
  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    60k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed
  • Openspec Onboard

    SAP/e-mobility-charging-stations-simulator

    Official

    Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

    227 GitHub starsUsed in 25 repos~3.5k tokens
    Media & CreativeAuto-check passed
  • Blog Audio

    AgriciDaniel/claude-blog

    Generate audio narration of blog posts using Google Gemini TTS.

    2.3k GitHub starsUsed in 1 repo~2.2k tokens
    Media & CreativeAuto-check: notes
  • Music

    tadaspetra/loop

    Generate music using ElevenLabs Music API. An agent skill from tadaspetra/loop.

    296 GitHub starsUsed in 2 repos~827 tokens
    Media & CreativeAuto-check passed
  • Create News Video

    hoquanghai/Auto-Create-Video

    Tạo video tin tức ngắn 9:16 (~60s) từ URL bài báo hoặc file .txt tiếng Việt.

    319 GitHub starsUsed in 1 repo~3.7k tokens
    Media & CreativeAuto-check passed

More from sugarforever/boring-video-studio

All 12 skills in this repo
  • Boring Video

    sugarforever/boring-video-studio

    A skill your agent uses when developing a content-driven video from a topic, research bundle, article, or draft, or when routing an existing script or non-argument video into HyperFrames production.

    168 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Develop Topic

    sugarforever/boring-video-studio

    A skill your agent uses when a content-driven video has a candidate topic but still needs research, experiments, a defensible thesis, or user-approved scope before an article or video beats can be…

    168 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Setup Boring Video Skills

    sugarforever/boring-video-studio

    A skill your agent uses when installing, validating, or repairing the Boring Video planning skill set before its first use.

    168 GitHub stars~449 tokensUpdated today
    Auto-check passed
  • To Article

    sugarforever/boring-video-studio

    A skill your agent uses when an approved content topic, research bundle, and evidence need to become a complete platform-independent article before video beats or publication adaptation.

    168 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Artifact Preview

    sugarforever/boring-video-studio

    A skill your agent uses when an artifact-owning skill requires a durable Markdown file to be presented for user review in a coding agent.

    168 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • To Spec Beats

    sugarforever/boring-video-studio

    A skill your agent uses when an approved content article needs to be reorganized into the factual and narrative architecture for a narrated video.

    168 GitHub stars~977 tokensUpdated today
    Auto-check passed

Questions about To Narration

What does To Narration do?

A skill your agent uses when writing or revising spoken narration from complete, lineage-valid video beats, including scripts that must remain open to later visual direction. To Narration is an agent skill from sugarforever/boring-video-studio. Use when writing or revising spoken narration from complete, lineage-valid video beats, including scripts that must remain open to later visual direction.

When should I use To Narration?

To Narration fits situations like: revising spoken narration from complete; lineage-valid video beats; including scripts that must remain open to later visual direction.

How do I install To Narration in Claude Code?

Run `npx skills add sugarforever/boring-video-studio --skill to-narration -a claude-code`. Or copy the skill folder (skills/boring-video/to-narration in sugarforever/boring-video-studio) into .claude/skills/to-narration in your project. Claude Code loads it when a task matches its description.

How do I install To Narration in Codex?

Run `npx skills add sugarforever/boring-video-studio --skill to-narration -a codex`. Or copy the skill folder (skills/boring-video/to-narration in sugarforever/boring-video-studio) into .agents/skills/to-narration in your project. Codex loads it when a task matches its description.

Can I use To Narration in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sugarforever/boring-video-studio --skill to-narration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/to-narration, .gemini/skills/to-narration, .github/skills/to-narration and .opencode/skills/to-narration in your project.

What does To Narration need to run?

SKILL.md names no scripts, command-line tools or credentials: To Narration is instructions for the agent only.

Does To Narration access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is To Narration safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does To Narration use?

To Narration is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does To Narration use?

About 821 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to To Narration?

Skills that share tags, products or a category with To Narration: MoneyPrinterTurbo Video Generator (harry0703/MoneyPrinterTurbo, 129k stars), HyperFrames Media Use (heygen-com/hyperframes, 60k stars), Openspec Onboard (SAP/e-mobility-charging-stations-simulator, 227 stars) and Blog Audio (AgriciDaniel/claude-blog, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains To Narration?

sugarforever (a GitHub user) maintains it in sugarforever/boring-video-studio, which has 168 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 9, 2026.

Source: sugarforever/boring-video-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.