srt-from-script
srt-from-script converts a structured ai-video-script 3-shot drama into a time-coded SRT subtitle file by parsing each shot's duration and voiceover text, computing cumulative timestamps, and writing UTF-8 cues that preserve multilingual content. Use it in video production pipelines after script generation and before subtitle burning to automatically synchronize dialogue with shot timing.
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/srt-from-script && cp -r /tmp/srt-from-script/src/opensquilla/skills/bundled/srt-from-script ~/.claude/skills/srt-from-scriptSKILL.md
# srt-from-script Parses an ai-video-script 3-shot script and writes an SRT subtitle file whose cues track the script's VOICEOVER per shot, time-coded with cumulative shot durations. ## Inputs (`with:`) | key | required | default | notes | |---|---|---|---| | `script` | yes | — | Full script text (the entire OUTPUT FORMAT block, including OVERVIEW + SHOT_1..N). Passed via stdin so the orchestrator does not need to write a temp file. | | `output_path` | yes | — | Output `.srt` path. Parent dir created if missing. | | `gap_ms` | no | `200` | Tail pad subtracted from each cue's end so the subtitle vanishes ~200 ms before the next shot starts — avoids cuts clipping mid-character. | | `leading_offset_ms` | no | `0` | Shifts every cue forward by this many ms. Set to the cover/intro clip duration when the merged video prepends a title card before SHOT_1. | ## Parsing rules - A shot with `VOICEOVER: none` or empty contributes no SRT cue but its `DURATION_S` still advances the timeline cursor. - Cue language follows the script verbatim. Chinese stays Chinese, English stays English — no translation. - Cumulative timestamps: SHOT_1 starts at 00:00:00,000; SHOT_2 starts at SHOT_1.duration; etc. - End time of each cue = next-shot start − `gap_ms`, clamped to ≥ 800 ms after start so very short voiceover lines remain readable. ## Output Prints the absolute path of the written `.srt` on stdout. The file is UTF-8 encoded so CJK voiceover lines survive when ffmpeg reads them via the `subtitles=` filter. ## Limits - Assumes the script follows ai-video-script's strict OUTPUT FORMAT (`=== SHOT_N ===` blocks with `DURATION_S:` and `VOICEOVER:` fields). Drift away from that format → zero cues, exit 1. - 3-5 shots tested. Larger shot counts work but timestamps grow.
Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.
Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.
Read, edit, or create Microsoft Word `.docx` files. Trigger this skill whenever the user mentions a Word document, .docx file, contract, report, brief, memo, or asks to extract text, modify an existing doc, generate one from a brief, or audit tracked changes. Three execution paths: text-and-structure extraction, in-place edit-by-run (preserves styles), and create-from-scratch with python-docx. Falls back to OOXML unzip-and-patch for layout work python-docx cannot reach.
Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'