meta-short-drama
Use this meta-skill instead of answering directly when the current user asks to generate an AI short-drama or 短剧 from a topic. The workflow infers render style, character identity, and shot count (1-10, default 5) from the request (filling in conservative defaults when missing), drafts a strict shot-by-shot shooting script, pauses for one free-form review (the user can approve, adjust render style / character / shot count / shot details, or cancel in plain language), optionally re-drafts the script with the user's adjustments, generates one universal full-cast identity-reference image plus per
Profile →npx skills add opensquilla/opensquilla --skill meta-short-drama --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Instructs an AI agent to create a short-drama script and a generation plan from a user-provided topic. It infers render style, character identity, and shot count (1-10, default 5) from the request, drafts a strict shot-by-shot shooting script, pauses for one free-form review, and allows adjustments to render style, character identity, shot count, or shot details. It can optionally re-draft the script with user adjustments, then generates a universal full-cast identity-reference image plus per-shot composition images, followed by per-shot video clips anchored to both the universal reference image and the composition image. It adds a title card and ending card, burns subtitles in the user’s language, and saves the script alongside the final MP4.
How it works
- Intake extracts render style, identity anchor, and shot count from the user request, filling conservative defaults when missing. It emits a 7-line block specifying TOPIC, RENDER_STYLE, AUTO_FILLED_RENDER_STYLE, IDENTITY_ANCHOR, AUTO_FILLED_IDENTITY_ANCHOR, N_SHOTS, AUTO_FILLED_N_SHOTS.
- Draft script step produces a strict-format short-drama shooting script using the N_SHOTS value (clamped 1..10), with ASPECT_RATIO 9:16 and DURATION_S total ~50 for 5 shots. Output is plain text and includes OVERVIEW.IDENTITY_ANCHOR, OVERVIEW.RENDER_STYLE, and OVERVIEW.N_SHOTS for downstream steps.
- The draft is saved to disk as script.txt in the run directory to enable user hand-editing.
- A combined review gate presents the script preview and the assumed style/identity/shot-count, allowing the user to approve, modify, or cancel. It notes potential costs and shows the script draft and intake assumptions.
- After the user review, the system parses the free-form reply and can re-draft the script with adjustments, regenerate media assets, and finalize with media generation steps (images, per-shot video clips, title/ending cards, subtitles) and a saved deliverable location.
When to use it
Triggered by user requests for a short drama generation, such as phrases requesting a short drama or 短剧 from a topic. The process automatically pauses for one free-form review before media generation.
What it can touch
- Tools involved include write_file (to save the draft), and generation components implied by ai-video-script for drafting. The workflow references downstream media generation steps and image/video assets tied to per-shot prompts and a universal reference image.
Caveats
- High declared risk. - Outputs depend on downstream media-generation quality until assets are inspected. - Visual identity and shot count default to conservative values when unspecified. - User must review and approve before media generation proceeds; the review gate is explicit in the workflow.
# meta-short-drama End-to-end short-drama generator with one free-form user-review gate before any paid step. **1-10 shots** (default 5), title card + ending card, in-language burned subtitles, and the generated script is saved to disk regardless of outcome. ## What it does 1. **`intake_extract`** scans the user message for RENDER_STYLE, IDENTITY_ANCHOR, and N_SHOTS (1-10). Fills in defaults when missing. 2. **`script_draft`** calls `ai-video-script` with the inferred values pasted verbatim into every shot prompt. 3. **`review_gate`** — single free-form pause. The user can approve, rewrite render style / character / shot count / shot details, or cancel in plain language. 4. **`review_normalize`** parses the free-form reply. 5. **`script_revised`** (conditional) redrafts when overrides present. 6. **`final_script`** echoes the canonical script. 7. **`script_save`** writes `script.txt` to the run folder (always — even on cancel, so the user keeps the draft). 8. **`title_extract` / `subtitle_extract` / `ending_text_extract`** pull cover/ending text in the script's language. 9. **`cover_image` + `cover_video`** — Pillow title card + 2s Ken-Burns clip (`0_cover.mp4` — sorts first in mer
- What it does
- Outputs
- Dependencies
- Risk
- Limits (v2)
- When NOT to use
What does the meta-short-drama skill do?
Use this meta-skill instead of answering directly when the current user asks to generate an AI short-drama or 短剧 from a topic. The workflow infers render style, character identity, and shot count (1-10, default 5) from the request (filling in conservative defaults when missing), drafts a strict shot-by-shot shooting script, pauses for one free-form review (the user can approve, adjust render style / character / shot count / shot details, or cancel in plain language), optionally re-drafts the script with the user's adjustments, generates one universal full-cast identity-reference image plus per
How do I install it?
Run `npx skills add opensquilla/opensquilla --skill meta-short-drama --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From opensquilla/opensquilla, a repository with 6,515 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.