Short Drama Delivery Audit logo

Short Drama Delivery Audit

OrganizationPopular
TokenRhythm
short-drama-delivery-audit

Internal deterministic delivery gate for meta-short-drama. Verifies real-provider image/video receipts, parent-owned paid-submission dispositions, runtime fallback evidence, decodability, and content-versus-final duration with ffprobe.

Overview

PublisherTokenRhythm
Repositoryopensquilla
Skill nameshort-drama-delivery-audit
Stars
7K
Forks
566
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by TokenRhythm on GitHub. Read the source before you install it.

Installation

Install the Short Drama Delivery Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/TokenRhythm/opensquilla.git /tmp/opensquilla
mkdir -p .claude/skills
cp -r /tmp/opensquilla/src/opensquilla/skills/bundled/short-drama-delivery-audit .claude/skills/short-drama-delivery-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Short Drama Delivery Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Short Drama Delivery Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Short Drama Delivery Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

short-drama-delivery-audit

Internal machine-owned gate used immediately before meta-short-drama publishes its final video. It does not call a model and never contacts a media provider.

The helper parses the canonical script.txt to identify active shots and their content durations. It then requires sanitized real-provider receipts for the reference image, every active shot image, and every active shot video; rejects placeholders, missing provider request/job IDs, and any runtime fallback substitution; and uses ffprobe to confirm that shot MP4s and the final MP4 are decodable and have the promised durations.

When Seedance rejects a shot under provider policy, its sidecar contains only the bounded reason provider_policy_rejected and an allowlisted policy code. The audit preserves those two fields, marks the shot not generated, and reports VIDEO_POLICY_REJECTED; raw provider text, signed URLs, request IDs, and secrets are discarded before this boundary.

The parent scheduler supplies one bounded disposition per paid step. The only accepted values are safe_no_submit, maybe_accepted, and receipt. It also supplies a separate bounded SHA-256 proof only when the exact bundled paid subprocess emitted a sanitized receipt on this invocation and the emitted JSON matched the resulting sidecar. A conclusive generated/policy receipt upgrades the public asset disposition to confirmed only when that current-run proof matches. The reserved runtime slots cannot be declared as plan steps.

When safe_no_submit accompanies a missing receipt and local fallback, the audit preserves the degraded provenance but does not claim that the provider may have billed the user. A maybe_accepted, receipt, missing, or malformed disposition without a conclusive, current-run-proven receipt remains fail-closed: the audit emits PAID_SUBMISSION_STATUS_UNKNOWN, a sanitized asset-name list, and a static instruction to check provider history before starting a replacement. Raw fallback output, child failure text, and provider text never cross into the verdict. A stale or forged workspace sidecar by itself is reported as RECEIPT_NOT_PROVEN_CURRENT_RUN and can never become confirmed.

Receipt or media evidence for a shot absent from the canonical script is reported as UNEXPECTED_PAID_ASSET and listed in unexpected_paid_assets. An incomplete receipt for that unexpected asset also carries the same fail-closed unknown-billing warning.

OVERVIEW.DURATION_S is story-content duration. The meta workflow adds a fixed two-second title and two-second ending, so the expected final duration is content duration plus four seconds. Small encoder timestamp differences are tolerated, but a three-second final file cannot satisfy a seven-second expected delivery.

Inputs

  • with.run_dir: runtime-owned short-drama output directory.
  • with.runtime.paid_submission_dispositions: bounded JSON object produced by the parent scheduler under its reserved output key. It contains only static step IDs and fixed disposition values.
  • with.runtime.paid_submission_receipt_proofs: bounded JSON object produced by the parent scheduler under a second reserved output key. It contains only static step IDs and canonical sha256:<hex> receipt digests from exact bundled subprocess output captured during this run.
  • with.runtime.fallback_outputs: mapping of shot number to the corresponding fallback step output. A non-empty value proves that local substitution ran.

Output

One JSON verdict with status (verified, degraded, or blocked), verified, media_provenance, active shots, content/final durations, whitelisted provider identifiers, per-asset paid_submission_dispositions, safe_no_submit_assets, may_have_been_billed, paid_submission_status_unknown_assets, unexpected_paid_assets, billing_guidance, and bounded issue codes. Raw prompts, provider responses, fallback output, signed URLs, and credentials are never emitted.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Short Drama Delivery Audit AI skill do?

Internal deterministic delivery gate for meta-short-drama. Verifies real-provider image/video receipts, parent-owned paid-submission dispositions, runtime fallback evidence, decodability, and content-versus-final duration with ffprobe.

Why use Short Drama Delivery Audit on TypingMind?

Because you install it once and use it with any model. Short Drama Delivery Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Short Drama Delivery Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TokenRhythm/opensquilla/tree/main/src/opensquilla/skills/bundled/short-drama-delivery-audit. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Short Drama Delivery Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Short Drama Delivery Audit?

As many as you like. As long as a model supports skills, you can use Short Drama Delivery Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Short Drama Delivery Audit AI skill free?

Yes. It is published on GitHub by TokenRhythm under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇