audio-production SKILL.md skillA
audio-production from zuimengyz/drama-plugin is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zuimengyz/drama-plugin/audio-production@git:20260922.a95ae67Pins git:20260922.a95ae67 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zuimengyz/drama-plugin
- Path
plugin/skills/audio-production/SKILL.md- Versions recorded
- 10
- Latest version
- git:20260922.a95ae67, committed Sep 22, 2026
- First version recorded
- Aug 31, 2026
- Size
- 19,082 bytes
- Repository stars
- 3
- License
- MIT
Produce exact-text dialogue speech clips, dialogue mixes, and final AV from approved Drama Dialogue and immutable source video. Use for provider-neutral voice resolution, speech freshness, duration probing, review, and deterministic AV assembly; do not use for authoring or revising Dialogue.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Audio Production ## Every spoken item and vocal mode (R3) Read [full performance coverage and isolation](../../docs/full-performance-coverage.md). Scene voice baselines may be shared, but every source line still needs speech action, resolved target, delivery change, pause/handoff and closure. Resolve space from that target's bound location, never a copied sample partner. Preserve non-lexical source vocal behavior separately; no invented words or lyrics. Consume diegetic-vocal’s approved Vocal Performance Bible. The existing projection embeds its VocalDelivery: SPOKEN, RECITATIVE, SUNG, SHARED_RESPONSE or NONVERBAL. Mode is not melody. Keep unresolved composition UNRESOLVED, with no claim to reconstruct an ancient tune. New production must qualify the requested mode and approved composition; unsupported mode fails VOCAL_MODE_CAPABILITY_REQUIRED, never silent sung-to-TTS fallback. Good existing sung native audio still wins KEEP_NATIVE. This capability does not authorize an audition, TTS or paid generation. ## Consume Voice Direction (R2 compatibility) …
Read the whole file at its exact version.
How to install
mdr add zuimengyz/drama-plugin/audio-production@sha256:5d978988b703bfaaThe line at the top of this page pins the label git:20260922.a95ae67, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_unvsjmju67sd5kql)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Aug 31, 2026 and Sep 22, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260922.a95ae67 latest | 2026-09-22 | a95ae67 | 19,082 B | A | view · diff |
| git:20260920.c32f125 | 2026-09-20 | c32f125 | 18,568 B | A | view · diff |
| git:20260918.73bcb42 | 2026-09-18 | 73bcb42 | 18,380 B | A | view · diff |
| git:20260917.b09ca69 | 2026-09-17 | b09ca69 | 17,977 B | A | view · diff |
| git:20260917.7094bfc | 2026-09-17 | 7094bfc | 17,025 B | A | view · diff |
| git:20260910.3d06bd7 | 2026-09-10 | 3d06bd7 | 15,438 B | A | view · diff |
| git:20260908.b538ddb | 2026-09-08 | b538ddb | 15,092 B | A | view · diff |
| git:20260906.2ad7b42 | 2026-09-06 | 2ad7b42 | 13,249 B | A | view · diff |
| git:20260905.c1b14e1 | 2026-09-05 | c1b14e1 | 8,512 B | A | view · diff |
| git:20260831.24816a9 | 2026-08-31 | 24816a9 | 6,697 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (19082 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
zuimengyz/drama-plugin · 3 stars · license MIT · pushed 2026-10-31 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_unvsjmju67sd5kql GET https://markdownregistry.com/api/v1/resolve?ref=zuimengyz/drama-plugin/audio-production GET https://markdownregistry.com/api/v1/blob/5d978988b703bfaab50a5289f599428bd40a38974662aa075ce1a42f3a5eab42
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from zuimengyz/drama-plugin
Every file in zuimengyz/drama-plugin