Agent skill

Vox Director

by avabbbb in avabbbb/Iris

Compile a topic, brief, article, or research artifact into a provider-neutral Flovart ProductionSpec for a VOX-inspired editorial paper-collage explainer.

MITAuto-check passedMedia & Creative

Install Vox Director

skills CLI
$ npx skills add avabbbb/Iris --skill vox-director -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install avabbbb/Iris vox-director --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/avabbbb/Iris.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/vox-director .claude/skills/vox-director && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vox-director
GitHub stars
139
Token cost
~1.2k tokens
SKILL.md length
554 words
Files
8 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Compile a topic, brief, article, or research artifact into a provider-neutral Flovart ProductionSpec for a VOX-inspired editorial paper-collage explainer.

  • Works in 4 steps: Read references/creative-direction.md… → Inspect the Flovart command registry and… → If the topic depends on current… → …
  • Torn-paper collage videos
  • SKILL.md covers Non-negotiable boundary, Prepare, Compile the ProductionSpec and Validate and project, plus 2 more sections
  • Calls node

What it does

Vox Director is an agent skill from avabbbb/Iris. Compile a topic, brief, article, or research artifact into a provider-neutral Flovart ProductionSpec for a VOX-inspired editorial paper-collage explainer. Use for torn-paper collage videos, motion-collage explainers, narrated editorial shorts, scrapbook-style ads, or any request that needs an image-first collage workflow with style bake-off, wide/detail shot cadence, stable typography, keyframe review, narration, music, captions, and delivery verification.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `agents/openai.yaml`, `evals/cases.json` and `examples/production-spec.json`).

It sits in Media & Creative, covering Text to speech and voice and Typography. The repository describes itself as: Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas — local-first, BYOK image/video models. The licence is MIT.

When your agent uses it

  • Torn-paper collage videos
  • Motion-collage explainers
  • Narrated editorial shorts
  • Scrapbook-style ads

Example prompts

  • “/vox-director”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read references/creative-direction.md before drafting prompts or shots.
  2. Inspect the Flovart command registry and the production.dry-run schema.
  3. If the topic depends on current discourse, collect a provenance-preserving research artifact through Flovart before writing the story.
  4. Use examples/production-spec.json as the structural example, not as reusable story content.

What it can do on your machine

Read from SKILL.md and the folder at commit 57a3cab. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vox Director loads about 1.2k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 118 tokens; SKILL.md has 554 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~118
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from avabbbb/Iris at commit 57a3cab, republished under its MIT licence (© avabbbb). 554 words, ~1,183 tokens.

Download SKILL.mdSave it as .claude/skills/vox-director/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
vox-director
description
Compile a topic, brief, article, or research artifact into a provider-neutral Flovart ProductionSpec for a VOX-inspired editorial paper-collage explainer. Use for torn-paper collage videos, motion-collage explainers, narrated editorial shorts, scrapbook-style ads, or any request that needs an image-first collage workflow with style bake-off, wide/detail shot cadence, stable typography, keyframe review, narration, music, captions, and delivery verification.

VOX Skill

Turn one topic into a concise editorial paper-collage ProductionSpec. Direct the film; let Flovart own credentials, Provider routing, tasks, budgets, Artifacts, rendering, and Workflow Projection.

Non-negotiable boundary

  • Never read or request an API Key.
  • Never call a Provider endpoint or hard-code a Provider/model route.
  • Never submit, poll, retry, download, or render outside Flovart Runtime.
  • Request only the capabilities declared in flovart.skill.yaml.
  • Keep style-specific fields under extensions.community.vox-director.

Prepare

  1. Read references/creative-direction.md before drafting prompts or shots.
  2. Inspect the Flovart command registry and the production.dry-run schema.
  3. If the topic depends on current discourse, collect a provenance-preserving research artifact through Flovart before writing the story.
  4. Use examples/production-spec.json as the structural example, not as reusable story content.

Compile the ProductionSpec

  1. Choose one narrative arc that fits the topic.
  2. Draft a hook that lands within three seconds.
  3. For a 30-second film, create 6–8 shots arranged as wide/detail pairs; keep every shot at or below seven seconds.
  4. Propose three or four topic-appropriate themes (default to three) and mark one recommendation. Do not pretend the recommendation is the final approved style.
  5. Ask the user to approve the beat map and the paid 3–4 image style bake-off before any Provider submission.
  6. Lock the approved collage language in extensions.community.vox-director.look.
  7. Give every shot a flat-safe camera move and scene-specific element motion. Do not repeat the same camera move on adjacent shots.
  8. Add spec, style-reference, keyframe-review, and OCR gates.
  9. Specify one narrator profile plus instrumental editorial music ducked under narration.
  10. Request image generation before image-to-video motion. Treat weak keyframes as a re-draft problem, not a motion problem.
Show full SKILL.md (283 more words)Show less

Validate and project

Run the repository quality gate during this bundled example:

bash
node tools/flovart/vox-director-quality.js --spec <production-spec.json> --json

Require a passing score before compilation. In the built-in PI Agent, first materialize the Brief, shots, prompts, references, and connections on the user's visible Workflow. Re-read flovart_workflow_inspect, then call flovart_production_dry_run with the current project, Director identity, ProductionSpec, stable idempotency key, and draftBinding: { draftVersion, sourceNodeIds } from that exact inspection. The browser binds object versions, ChangeSets, and a redacted snapshot hash before Runtime freezes the Revision. Never open a CLI or create a second hidden canvas as an alternate authoring path.

Wait for the returned Task, inspect flovart_production_status, and verify the matching flovart_workflow_projection_get result on the user's current visible Workflow. After the user confirms Route Plan and Run Budget, flovart_production_run may create the 3–4 same-shot style bake-off Artifacts. Keep keyframes waiting at style-reference; show those Artifacts on Workflow and ask the user which style:bakeoff:<theme> Stage to lock. Approve that gate only with the chosen approvedStageKey. The Runtime must pass that exact Artifact into every keyframe image-to-image request.

Keep motion waiting until the user has reviewed the keyframe sheet and the OCR gate has passed. Approve keyframe-review and ocr explicitly, then let the same ProductionRun continue. Do not claim a finished film while Route Plan, Run Budget, required capabilities, approvals, Runtime Projection, or Artifact attachment remain blocked.

Revise

  • Revise narrative, prompts, references, duration, narration, or gates through a new ProductionSpec Revision once that command is available.
  • Treat node position, size, lock, and viewport as layout only.
  • Re-run only the smallest invalidated stage when Runtime supports stage retry.
  • Preserve prior Takes and their provenance.

Deliver

Report the exact Director version, ProductionSpec/Run/Stage identifiers, unresolved blockers, approval state, quoted versus confirmed cost, Artifact identifiers, and verification result.

© avabbbb, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in .agents/skills/vox-director of avabbbb/Iris.

  • SKILL.md
  • LICENSE
  • agents/openai.yaml
  • evals/cases.json
  • examples/production-spec.json
  • flovart.skill.yaml
  • references/creative-direction.md
  • schemas/extension.schema.json

Open the folder on GitHubat commit 57a3cab

Compare with similar skills

Vox Director next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vox Director compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vox Director this skillavabbbb/Iris139—~1.2kAutomated safety check: PassMIT
Paper Collage Explainer Generatortl2012tl/comfyUI-llama-TE2414 repos~5.2kAutomated safety check: PassNone
Anthropic Brand Stylinganthropics/skills180k30 repos~559Automated safety check: PassApache-2.0
Minimal Zine Poster GeneratorLiamGvchi/gc-minimal-zine-poster7.3k—~2.9kAutomated safety check: PassMIT
HyperFrames Media Useheygen-com/hyperframes60k—~2.4kAutomated safety check: PassApache-2.0
Media Useedenfunf/reelmimic1.9k1 repos~2kAutomated safety check: PassMIT

Similar skills

  • Paper Collage Explainer Generator

    tl2012tl/comfyUI-llama-TE

    For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge points, opinions, or abstract topics.

    241 GitHub starsUsed in 4 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Anthropic Brand Styling

    anthropics/skills

    Official

    Applies Anthropic's brand colors and fonts to artifacts such as PowerPoint slides, using fixed hex values for text and accents, Poppins headings and Lora body text.

    180k GitHub starsUsed in 30 repos~559 tokens
    Media & CreativeAuto-check passed
  • Minimal Zine Poster Generator

    LiamGvchi/gc-minimal-zine-poster

    Creates or analyzes quiet, paper-texture zine posters with big negative space, one color accent and experimental type, returning an image prompt and the generated poster.

    7.3k GitHub stars~2.9k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • HyperFrames Media Use

    heygen-com/hyperframes

    Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.

    60k GitHub stars~2.4k tokensUpdated today
    Media & CreativeAuto-check passed
  • Media Use

    edenfunf/reelmimic

    Agent Media OS, the single skill for every media need in a HyperFrames project.

    1.9k GitHub starsUsed in 1 repo~2k tokens
    Media & CreativeAuto-check passed
  • Mono Color

    yanliudesign/mono-color-skill

    Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo.

    3.4k GitHub stars~8.5k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

More from avabbbb/Iris

  • Flovart

    avabbbb/Iris

    Use Iris's visible Workflow through its stable Agent surface.

    139 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Open Flovart

    avabbbb/Iris

    Prepare Flovart for a user's Workflow task. An agent skill from avabbbb/Iris.

    139 GitHub stars~456 tokensUpdated today
    Auto-check passed
  • Flovart

    avabbbb/Iris

    在 WorkBuddy 中用自然语言操作用户看得见的 Iris Workflow,并把真实制作结果交给 Iris 处理。

    139 GitHub stars~316 tokensUpdated today
    Auto-check passed

Questions about Vox Director

What does Vox Director do?

Compile a topic, brief, article, or research artifact into a provider-neutral Flovart ProductionSpec for a VOX-inspired editorial paper-collage explainer. Vox Director is an agent skill from avabbbb/Iris. Compile a topic, brief, article, or research artifact into a provider-neutral Flovart ProductionSpec for a VOX-inspired editorial paper-collage explainer.

When should I use Vox Director?

Vox Director fits situations like: torn-paper collage videos; motion-collage explainers; narrated editorial shorts; scrapbook-style ads.

How do I install Vox Director in Claude Code?

Run `npx skills add avabbbb/Iris --skill vox-director -a claude-code`. Or copy the skill folder (.agents/skills/vox-director in avabbbb/Iris) into .claude/skills/vox-director in your project. Claude Code loads it when a task matches its description.

How do I install Vox Director in Codex?

Run `npx skills add avabbbb/Iris --skill vox-director -a codex`. Or copy the skill folder (.agents/skills/vox-director in avabbbb/Iris) into .agents/skills/vox-director in your project. Codex loads it when a task matches its description.

Can I use Vox Director in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add avabbbb/Iris --skill vox-director -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vox-director, .gemini/skills/vox-director, .github/skills/vox-director and .opencode/skills/vox-director in your project.

What does Vox Director need to run?

Going by SKILL.md and its folder, Vox Director needs the command-line tools its instructions call (node).

Does Vox Director access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vox Director safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vox Director use?

Vox Director is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vox Director use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 825 tokens, read only when the agent opens those files.

What are the alternatives to Vox Director?

Skills that share tags, products or a category with Vox Director: Paper Collage Explainer Generator (tl2012tl/comfyUI-llama-TE, 241 stars), Anthropic Brand Styling (anthropics/skills, 180k stars), Minimal Zine Poster Generator (LiamGvchi/gc-minimal-zine-poster, 7.3k stars) and HyperFrames Media Use (heygen-com/hyperframes, 60k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vox Director?

avabbbb (a GitHub user) maintains it in avabbbb/Iris, which has 139 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 2026.

Source: avabbbb/Iris on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.