Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Subtitle Pro

ASecurity

Create accurate subtitles and captions with timing, formatting standards, SRT/VTT workflows, and QC.

2 stars
0 votes
0 copies
1 views
Added 9/29/2026
ai-agentsgo

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill subtitle-pro --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Subtitle Pro?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Subtitle Pro
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-subtitle-pro/badge)](https://www.skillsdirectory.com/skills/aicodedecode-subtitle-pro)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: subtitle-pro
description: Create accurate subtitles and captions with timing, formatting standards, SRT/VTT workflows, and QC.
category: video
---

## Overview

Subtitles expand reach (global audiences), accessibility (deaf/hard-of-hearing
viewers), and
retention (most social video is watched muted). Professional subtitling is a
craft: accurate
transcription, readable timing, proper formatting, and standards compliance
(SRT/VTT). This skill
covers creating, syncing, styling, and quality-checking subtitles.

## When to use

- Creating subtitles for YouTube, courses, or marketing videos

- Adding captions for accessibility compliance

- Translating content with subtitle files

- Fixing auto-generated captions

- Burning in subtitles vs delivering sidecar files

## Core concepts

- - - **Subtitles vs captions.** Subtitles = dialogue translation/transcription.
  Captions (closed
  captions) = dialogue + sound descriptions ([music], [laughter]) for
accessibility. Know which you
  need — accessibility compliance requires captions, not just subtitles.
- - - **Timing rules.** Minimum duration ~1 second, maximum ~7 seconds per cue.
  Reading speed: ~20
  characters/second (160-180 wpm) for adults. Cues should sync to speech —
appear as speaking
  starts, clear at natural pauses, never straddling a shot cut awkwardly.
- - - **Line discipline.** Max 2 lines per cue, ~42 characters per line. Break
  lines at natural phrase
  boundaries — never split a phrase awkwardly across lines. One idea per cue
where possible.
- - - **Format basics.** SRT: numbered cues with `HH:MM:SS,mmm` timestamps —
  universal, simple.
  WebVTT: like SRT but with styling/positioning for web players. ASS/SSA:
advanced styling (karaoke,
  positioning) for burned-in/enthusiast use.
- - - **Sidecar vs burned-in.** Sidecar files (SRT/VTT uploaded alongside) =
  toggleable, SEO-friendly,
  platform-preferred. Burned-in = always visible, necessary for some social
feeds, but unchangeable.
  Default to sidecar; burn in for platforms that need it.
- - - **Auto-captions need humans.** ASR gets you 80-90% there fast, but errors
  cluster in names,
  jargon, and homophones — exactly where accuracy matters most. Always review;
never ship raw
  auto-captions for professional work.

## Practical workflow

1. 1. 1. **Transcribe accurately.** Verbatim for captions (include false starts?
   usually cleaned
   lightly), speaker labels for multi-speaker content, sound descriptions in
brackets for captions.
   Get names and jargon right — ask the client for a term list.
2. 2. 2. **Time the cues.** Align to speech with ~100-200ms lead-in. Split long
   sentences into multiple
   cues at phrase boundaries. Ensure no overlaps and no gaps that flash cues.
3. 3. 3. **Format properly.** 1-2 lines, ≤42 chars/line, proper SRT/VTT syntax
   (validate with a linter
   — one malformed timestamp breaks the whole file). UTF-8 encoding for special
characters.
4. 4. 4. **Style deliberately.** For burned-in: readable font, adequate size for
   phone viewing,
   high-contrast (white text + black outline/shadow works on any background),
safe-area positioning
   (not under platform UI).
5. 5. 5. **QC pass.** Watch with subtitles only (mute the video — can you follow
   it?). Check: sync
   drift over long videos, spelling/grammar, consistent speaker labels, no
overlapping cues, timing
   within min/max durations.
6. 6. 6. **Deliver correctly.** Named per convention (`video.en.srt`), uploaded
   as sidecar where
   supported, burned in where required. For translations: translate meaning (not
word-for-word),
   respect the timing constraints, and have a native speaker review.

## Common pitfalls

- - - **Shipping raw auto-captions.** "Let's checkout the new calendar" instead
  of "check out." ASR
  errors in professional content look careless — always review.
- - - **Wall-of-text cues.** 4-line paragraphs flashing for 2 seconds. Split
  into digestible cues at
  natural breaks; respect reading speed.
- - - **Bad line breaks.** Splitting "unbeliev- / able" or separating adjectives
  from nouns across
  lines. Break at phrase boundaries.
- - - **Sync drift.** Captions progressively out of sync in long videos (often
  from frame-rate
  mismatches). Check the end, not just the start.
- - - **Text under UI.** Burned-in subtitles hidden behind platform controls or
  profile overlays. Know
  each platform's safe zones.
- - - **Forgetting accessibility.** Dialogue-only subtitles when captions were
  needed, no sound
  descriptions, tiny low-contrast text. If accessibility is the goal, caption
fully.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →