What makes video-add-captions notable?

1.1K downloads. Trust evidence available

How should video-add-captions be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

video-add-captions

Add word-timed captions to an Open Recut program. Use this skill to map the canonical transcript through timeline.json, review a maintained style on source-backed pixels, render a local transparent HyperFrames PNG sequence, and register it as an overlay contribution for the shared delivery render.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.8

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.8release · observed Oct 7, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s178pg569r7j3dkw6ekc9bn7258b0eme:video-add-captions

Install using `clawhub skill install s178pg569r7j3dkw6ekc9bn7258b0eme:video-add-captions` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/whitetowerai/video-add-captions before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-whitetowerai-video-add-captions/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: video-add-captions
description: >
Add word-timed captions to an Open Recut program. Use this skill to map the
canonical transcript through timeline.json, review a maintained style on
source-backed pixels, render a local transparent HyperFrames PNG sequence,
and register it as an overlay contribution for the shared delivery render.
---

# Video Add Captions

## Dependencies

`/video-understand` is a prerequisite. Run it first so captions use the validated
word-level transcript and canonical timeline.
Before starting, verify that it is installed. If it is not, warn the user that
this prerequisite is missing and stop before processing media.

Require `ffmpeg`/`ffprobe` on PATH, Python with `Pillow`, and Node.js >= 22 (for the `.mjs` scripts and `npx hyperframes`, fetched on demand). `hyperframes render`/`snapshot` drives a headless Chrome — it manages its own `chrome-headless-shell`, and falls back to a system Chrome (set `CHROME` to override) when the cached one is unusable. Check these before processing media.

## Scope

This skill owns caption grouping, style selection, review, and the transparent
caption track. It does not transcribe, cut, retime, grade, reframe, or choose the
delivery audio policy.

Run captions before content cards and motion graphics whenever either is selected.
The approved caption layout establishes a reserved subtitle region that both later
operations must keep clear. This relative order also applies when only one pair is active.

Use `video-understand` first. If a cut exists, caption the active program
timeline; do not treat source transcript seconds as program seconds.

## Protocol Inputs

Required:

- `work/project.json`
- `work/understand/transcript.json`, with word-level source timestamps
- `work/understand/media.json`
- `work/timeline.json`
- the source video named by `work/project.json`

The timeline is the only source-to-program mapping. All ranges are half-open
`[start_s, end_s)`. `scripts/build_captions.py` uses the shared
`projectlib.map_transcript_to_timeline`; words in dropped source ranges disappear,
retained words move to program time, and cues always break at clip boundaries.

## Durable Outputs

Generated HTML, copied runtime files, extracted source frames, and overlay frames
are cache. The plan, optional spatial context, SRT, decision receipt, and review
evidence are durable.

## Caption Plan

`work/captions/captions-plan.json` is the canonical c

_meta.json

{
  "ownerId": "kn70hcphbcepjj43vwv7j0zbnh8b0jpm",
  "slug": "video-add-captions",
  "version": "1.0.8",
  "publishedAt": 1791346398173
}

scripts/caption-styles.json

{
  "presets": {
    "clean": {
      "preset": "clean",
      "font": {
        "family": "system-ui, sans-serif",
        "sizeRatio": 0.0416,
        "weight": 800,
        "color": "#F5F4ED",
        "lineHeight": 1.32,
        "letterSpacing": 0
      },
      "layout": {
        "anchor": "bottom",
        "align": "center",
        "maxWidth": 0.92,
        "paddingBottomRatio": 0.07
      },
      "background": {
        "enabled": false,
        "theme": "gray",
        "shape": "rounded",
        "color": "#000000",
        "opacity": 0.48,
        "radiusRatio": 0.018,
        "paddingXRatio": 0.035,
        "paddingYRatio": 0.018
      },
      "effects": {
        "shadow": {
          "strength": "none",
          "color": "#000000",
          "opacity": 0.55,
          "offsetYRatio": 0.02,
          "blurRatio": 0.04
        },
        "stroke": {
          "strength": "none",
          "color": "#000000",
          "widthRatio": 0
        }
      },
      "stroke": {
        "enabled": false,
        "theme": "black",
        "color": "#000000",
        "opacity": 0.85,
        "widthRatio": 0
      },
      "wordHighlight": {
        "enabled": true,
        "mode": "textColor",
        "activeColor": "#FF7A45",
        "activeScale": 1.12,
        "upcomingOpacity": 0.55,
        "backgroundColor": "#FF7A45",
        "backgroundOpacity": 0.24,
        "backgroundRadiusRatio": 0.01
      },
      "animation": {
        "type": "pop",
        "popInFrames": 6,
        "popOutFrames": 4,
        "translateYPx": 22
      }
    },
    "minimal": {
      "preset": "minimal",
      "font": {
        "family": "system-ui, sans-serif",
        "sizeRatio": 0.0352,
        "weight": 650,
        "color": "#FFFFFF",
        "lineHeight": 1.342,
        "letterSpacing": 0
      },
      "layout": {
        "anchor": "bottom",
        "align": "center",
        "maxWidth": 0.86,
        "paddingBottomRatio": 0.075
      },
      "background": {
        "enabled": false,
        "theme": "gray",
        "shape": "rounded",
        "color": "#000000",
        "opacity": 0.32,
        "radiusRatio": 0.014,
        "paddingXRatio": 0.028,
        "paddingYRatio": 0.014
      },
      "effects": {
        "shadow": {
          "strength": "none",
          "color": "#000000",
          "opacity": 0,
          "offsetYRatio": 0,
          "blurRatio": 0
        },
        "stroke": {
          "strength": "none",
          "color": "#000000",
          "widthRatio": 0
        }
      },
      "stroke": {
        "enabled": false,
        "theme": "black",
        "color": "#000000",
        "opacity": 0.85,
        "widthRatio": 0
      },
      "wordHighlight": {
        "enabled": false,
        "mode": "none",
        "activeColor": "#FFFFFF",
        "activeScale": 1,
        "upcomingOpacity": 1,
        "backgroundColor": "#FFFFFF",
        "backgroundOpacity": 0,
        "backgroundRadiusRatio": 0.01
      },
      "animation": {
        "

reference/caption-feedback-mapping.md

# Caption Feedback Mapping

This skill is agent-facing. In the canonical workflow, users choose a style and
approve or revise source-backed previews by copying structured summaries from the
bound HTML review pages. Standalone compatibility accepts an exact gallery
combination ID or `skip`, and accepts `approve` only after source-backed preview
evidence exists. Historical non-English aliases remain accepted silently but are
not user instructions. The agent maps only recorded user feedback to optional JSON
overrides accepted by `scripts/generate_caption_project.mjs`.

## Safe Edit Points

- Use `scripts/caption-styles.json` as the source of official preset and theme names.
- Record the exact gallery response with `scripts/caption_interaction.mjs select`.
- Pass `--interaction-state` to the generator. The generator reads the selected
  preset, themes, and Karaoke value from that state and rejects conflicting flags.
- Put only requested property overrides in a JSON file passed with `--overrides`.
- Edit caption cue JSON only when correcting subtitle text or timing data.

The user may skip gallery selection, which explicitly chooses `clean`. The
source-backed preview confirmation cannot be skipped. Canonical full rendering
requires the exact copied approval summary; standalone compatibility requires the
exact public response `approve`.

## Official Style Vocabulary

Official presets:

- `clean`
- `minimal`
- `social-bold`
- `pill`
- `boxed`
- `stroked`
- `shorts`

Background themes:

- `gray`
- `yellow`
- `blue`
- `pink`
- `green`

Stroke themes:

- `black`
- `yellow`
- `blue`
- `pink`
- `green`

Shorts highlight colors:

- `yellow` -> `#F8F54F`
- `green` -> `#21D32E`
- `orange` -> `#F8BD6D`
- `black` -> `#000000`
- `blue` -> `#2563EB`
- `pink` -> `#DB2777`

Karaoke is an option, not a preset. Preview ids such as `pill-yellow`,
`boxed-green`, `stroked-blue`, `shorts-yellow`, and `social-bold-karaoke` are
preset/config combinations, not official presets.

## Feedback Rules

Font and visual intensity:

- "make the text bigger" -> increase `font.sizeRatio`
- "make the text smaller" -> decrease `font.sizeRatio`
- "cleaner" -> move toward `clean` or `minimal`
- "more subtle" -> move toward `minimal`
- "more eye-catching" -> move toward `social-bold`
- "more like TikTok", "big short-video captions" -> move toward `social-bold`
- "vertical shorts style", "Reels style", "YouTube Shorts style" -> use `shorts`

Background:

- "no background" -> `background.enabled = false`
- "add a background" -> choose `pill` or `boxed`
- "rounded background", "capsule background" -> `preset = "pill"` or `background.shape = "pill"`
- "small rounded background", "rectangle background bar" -> `preset = "boxed"` or `background.shape = "rounded"`
- "make the background more transparent" -> decrease `background.opacity`
- "make the background stronger" -> increase `background.opacity`
- "gray background" -> `background.theme = "gray"`
- "yellow background" -> `background.theme = "y

reference/caption-rules.md

# Caption Rules and Data Shape

## How build_captions.py chunks words into cues

A new cue is closed when any of these conditions is met:

- the word ends a sentence: `.`, `?`, `!`, or ellipsis
- adding the next word would exceed the line budget: `--max-chars` x `--max-lines`
- adding the next word would exceed `--max-dur` seconds on screen
- there is a speech gap of at least `--gap` seconds before the next word

Each cue keeps per-word timings, so the renderer can highlight the word currently
being spoken. `lines[]` is the cue wrapped to `--max-chars` for display and for
the SRT file.

Useful defaults:

```text
--max-chars 42 --max-lines 2 --max-dur 6 --gap 0.6
```

For fast-cut vertical/social captions, try shorter cues:

```text
--max-chars 24 --max-dur 3
```

## captions.json schema

```jsonc
[
  {
    "index": 1,
    "start": 1.0,
    "end": 3.4,
    "text": "Hey, it's Thariq from the Claude Code team.",
    "lines": ["Hey, it's Thariq from the Claude", "Code team."],
    "words": [
      { "word": "Hey,", "start": 1.0, "end": 1.2 }
    ]
  }
]
```

`captions.srt` is the same content as portable SubRip. Use it as a sanity read
or to hand to a player or another tool.

## Renderer Contract

- Treat `captions.json` as renderer-neutral cue data.
- Preserve `start`, `end`, `text`, `lines[]`, and per-word timings when passing cues
  to a renderer.
- Karaoke is a true/false option, not a preset. Use `karaoke: true` for per-word
  highlight and `karaoke: false` for plain blocks.
- Keep style and compositing implementation outside this data-shaping contract.

## Expressive Planning

Standard is the default. A Standard canonical plan needs no `presentation` field,
and the legacy top-level cue array remains Standard-compatible. Expressive must be
explicitly requested with `--presentation-mode expressive`; it is a presentation
mode, not a preset.

`build_captions.py` creates only the base cues and a draft planning shell. It does
not infer placement. The Agent reads the transcript,
available understanding artifacts, timeline, generated cues, and necessary real
visual evidence, then fills the complete plan once for the whole program.

Agent layout rules:

1. Default to `bottom-standard`.
2. Keep ordinary explanatory sentences in a continuous bottom layout when possible.
3. Use `center-emphasis` for short keywords, numbers, or conclusions when emphasis is justified.
4. Do not mechanically alternate between bottom and center.
5. Do not change position in the middle of a sentence or cue.
6. Prefer merging adjacent ordinary cues into one stable layout beat.
7. Avoid repeated consecutive `center-emphasis` beats.
8. Every position change must have a semantic reason recorded in the beat rationale.
9. When uncertain, fall back to `bottom-standard`.

A layout beat covers one or more complete, contiguous cues. Beat IDs must be unique;
beats must follow time and cue order, must not overlap, and must not start or end
inside a cue. A completed Expressive plan covers e

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.