Agent skill

Skill Captions

by Pluviobyte in Pluviobyte/rnskill

Renders, previews, validates and burns in production subtitles from QC-passed caption timing, with fixed dark or light caption styles scaled to the video size.

Custom licenceAuto-check passedMedia & Creative

Install Skill Captions

skills CLI
$ npx skills add Pluviobyte/rnskill --skill skill-captions -a claude-code

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

GitHub CLI
$ gh skill install Pluviobyte/rnskill skill-captions --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/Pluviobyte/rnskill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-captions .claude/skills/skill-captions && 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
skill-captions
GitHub stars
1.6k
Token cost
~1.3k tokens
SKILL.md length
429 words
Files
81 (incl. scripts, references, assets)
Skills in repo
45
Repo updated
First seen
Licence
Custom licence

At a glance

Renders, previews, validates and burns in production subtitles from QC-passed caption timing, with fixed dark or light caption styles scaled to the video size.

  • Works in 8 steps: Lock the final narration audio or final… → Run ra-audio-to-subtitles unless the… → Require caption-qc.json to report… → …
  • Burning consistent subtitles into a finished video from real word timestamps
  • SKILL.md covers Required workflow, Registered styles, Commands and Hard rules, plus 1 more section
  • Calls python3

What it does

The skill separates subtitle timing from subtitle appearance. A companion skill, `ra-audio-to-subtitles`, owns speech recognition, phrase grouping, timestamps, SRT and VTT files and a `caption-qc.json` report; this one owns typography, panel geometry, fixed anchoring, previews, overlay rendering, burn-in and render checks. It never estimates timing from character count, scene length or text-to-speech segment length.

The workflow locks the final audio or video, requires the QC report to show a pass, picks a style from the registry, renders a still preview, checks it against the layout QC notes, renders the captioned copy while keeping the clean video and portable subtitle files, and runs `validate_caption_render.py`. The `anchor-dark` style, the default, uses a charcoal translucent rounded panel with warm white text, and `anchor-light` swaps in a warm-white panel; metrics scale with target height, so 4K captions are twice their 1080p size.

When your agent uses it

  • Burning consistent subtitles into a finished video from real word timestamps
  • Previewing caption style and position before rendering a full video
  • Fixing caption size, position, shadow or drift, including at 4K
  • Switching a video between dark and light translucent caption panels

Example prompts

  • “Burn the default captions into final-clean.mp4 using the QC-passed caption files.”
  • “Render a still preview of the light caption style before we process the whole video.”
  • “The captions look too big on the 4K export; fix the scaling and validate the render.”

Requirements

  • Python 3
  • Caption timing and a caption-qc.json report that passes QC
  • The ra-audio-to-subtitles skill when final word timestamps do not exist yet

Workflow steps

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

  1. Lock the final narration audio or final merged video.
  2. Run ra-audio-to-subtitles unless the project already has the canonical
  3. Require caption-qc.json to report status: pass.
  4. Select a style from references/style-registry.json. Use anchor-dark
  5. Generate a representative still preview before rendering a full video.
  6. Inspect the preview against references/layout-qc.md.
  7. Render the captioned derivative. Preserve the clean video and portable
  8. Run scripts/validate_caption_render.py and archive its JSON report.

What it can do on your machine

Read from SKILL.md and the folder at commit 83d1783. 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

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Skill Captions loads about 1.3k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 128 tokens; SKILL.md has 429 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~128
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.1k

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 429 words (~1,311 tokens).

“Separate subtitle timing from subtitle appearance:”

— opening of SKILL.md by Pluviobyte, Custom licence
name
skill-captions

Read the full SKILL.md on GitHub

Files

SKILL.md and 80 other files (scripts, references, assets) in skills/skill-captions of Pluviobyte/rnskill.

  • SKILL.md
  • agents/openai.yaml
  • assets/style-reference/anchor-dark/anchor-dark-caption-crop.png
  • assets/style-reference/anchor-dark/anchor-dark-render-regression-1080p.png
  • assets/style-reference/anchor-dark/anchor-dark-render-regression-4k.png
  • assets/style-reference/anchor-dark/kimi-reference-32s.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0001.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0002.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0003.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0004.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0005.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0006.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0007.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0008.png
  • assets/style-reference/anchor-light/anchor-light-render-regression-1080p-caption-work/cue-0009.png
  • … and 66 more

Open the folder on GitHubat commit 83d1783

Compare with similar skills

Skill Captions 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.

Skill Captions compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Captions this skillPluviobyte/rnskill1.6k—~1.3kAutomated safety check: PassCustom licence
Manim Video Productionbrowser-use/video-use28k6 repos~3kAutomated safety check: PassMIT
HyperFrames Animationheygen-com/hyperframes59k3 repos~2.1kAutomated safety check: PassApache-2.0
Brag Launch Videolatent-spaces/brag14k1 repos~2.3kAutomated safety check: PassMIT
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.4k6 repos~3.2kAutomated safety check: NotesApache-2.0
Embedded Video Captionsheygen-com/hyperframes59k3 repos~8.6kAutomated safety check: PassApache-2.0

Similar skills

  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    28k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • HyperFrames Animation

    heygen-com/hyperframes

    Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.

    59k GitHub starsUsed in 3 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • Brag Launch Video

    latent-spaces/brag

    Turns the current project website or app into a short, shareable launch video with Hyperframes, planned from the project code with options for tone, format and voiceover.

    14k GitHub starsUsed in 1 repo~2.3k tokens
    Media & CreativeAuto-check passed
  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.4k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes
  • Embedded Video Captions

    heygen-com/hyperframes

    Adds captions to a single-subject talking-head video without editing the footage, from plain subtitles to cinematic text placed behind the speaker.

    59k GitHub starsUsed in 3 repos~8.6k tokens
    Media & CreativeAuto-check passed
  • Weekly Changelog Video

    heygen-com/hyperframes

    Turns a weekly changelog markdown file into a branded HyperFrames video with voiceover, animated mock-UI scenes and captions, using fonts, background and scripts bundled in the skill.

    59k GitHub stars~3.3k tokensUpdated today
    Media & CreativeAuto-check passed

More from Pluviobyte/rnskill

All 45 skills in this repo
  • Motion Replica Builder

    Pluviobyte/rnskill

    Analyzes a reference video's layout, motion and timing over a chosen time range, then builds an original animated replica with new copy and assets plus a final video QC.

    1.6k GitHub stars~1.7k tokensUpdated 17 days ago
    Auto-check passed
  • Niulai Style Image Transfer

    Pluviobyte/rnskill

    Restyles photos, film stills or new scene descriptions in the rough low-budget 3D look observed in the 2026 animated film Niulai, with an iterative scoring loop.

    1.6k GitHub stars~1.3k tokensUpdated 17 days ago
    Auto-check passed
  • Creates Chinese social-media video covers in 3:4 and 4:3 from registered styles and shared presenter assets, or swaps the person in a reference cover for a digital-human frame.

    1.6k GitHub stars~1.2k tokensUpdated 17 days ago
    Auto-check passed
  • Generates a HeyGen digital-human video layer using a fixed avatar profile, local narration and an approved circular avatar placement.

    1.6k GitHub stars~2.4k tokensUpdated 17 days ago
    Auto-check passed
  • Generates SRT, VTT and caption JSON for final narration audio or a merged video using Volcengine Doubao ASR word timestamps, with a quality gate before delivery.

    1.6k GitHub stars~1.1k tokensUpdated 17 days ago
    Auto-check: notes
  • Produces a local rough cut of a talking-head or narrated screen recording, with transcript correction, an approval gate, pause compression and loudness normalization.

    1.6k GitHub stars~1.8k tokensUpdated 17 days ago
    Auto-check passed

Questions about Skill Captions

What does Skill Captions do?

Renders, previews, validates and burns in production subtitles from QC-passed caption timing, with fixed dark or light caption styles scaled to the video size. The skill separates subtitle timing from subtitle appearance.json` report; this one owns typography, panel geometry, fixed anchoring, previews, overlay rendering, burn-in and render checks.

When should I use Skill Captions?

Skill Captions fits situations like: burning consistent subtitles into a finished video from real word timestamps; previewing caption style and position before rendering a full video; fixing caption size, position, shadow or drift, including at 4K; switching a video between dark and light translucent caption panels.

How do I install Skill Captions in Claude Code?

Run `npx skills add Pluviobyte/rnskill --skill skill-captions -a claude-code`. Or copy the skill folder (skills/skill-captions in Pluviobyte/rnskill) into .claude/skills/skill-captions in your project. Claude Code loads it when a task matches its description.

How do I install Skill Captions in Codex?

Run `npx skills add Pluviobyte/rnskill --skill skill-captions -a codex`. Or copy the skill folder (skills/skill-captions in Pluviobyte/rnskill) into .agents/skills/skill-captions in your project. Codex loads it when a task matches its description.

Can I use Skill Captions 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 Pluviobyte/rnskill --skill skill-captions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-captions, .gemini/skills/skill-captions, .github/skills/skill-captions and .opencode/skills/skill-captions in your project.

What does Skill Captions need to run?

Going by SKILL.md and its folder, Skill Captions needs the command-line tools its instructions call (python3). Our summary lists: Python 3; Caption timing and a caption-qc.json report that passes QC; The ra-audio-to-subtitles skill when final word timestamps do not exist yet.

Does Skill Captions 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 Skill Captions 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Skill Captions use?

Skill Captions has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Skill Captions use?

About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Skill Captions?

Skills that share tags, products or a category with Skill Captions: Manim Video Production (browser-use/video-use, 28k stars), HyperFrames Animation (heygen-com/hyperframes, 59k stars), Brag Launch Video (latent-spaces/brag, 14k stars) and Stitch to Remotion Walkthrough Videos (google-labs-code/stitch-skills, 8.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Captions?

Pluviobyte (a GitHub user) maintains it in Pluviobyte/rnskill, which has 1,636 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on September 21, 2026.

Source: Pluviobyte/rnskill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.