Source profileQuality 92/100

event4u-app/agent-config/src/skills/video-director/SKILL.md

video-director

Use when turning a scene idea into the 11-block cinematic prompt for live-action AI video — lens, lighting, blocking, motion, negatives. Triggers 'cinematic prompt', 'film-grade scene'.

Source repository stars
7
Declared platforms
0
Static risk flags
0
Last source update
2026-07-28
Source checked
2026-07-28
DecisionCompatibilityInstallWorkflowPermissionsEvidenceSource

Decision brief

What it does—and where it fits

Turn a scene idea into the 11-block cinematic prompt the hollywood-director persona ships. Output is provider-agnostic prose; provider-specific tuning is handed off to motion-choreographer.

Best for

  • A scene idea, beat, or script line needs to become a cinematic
  • A draft prompt reads as "AI video" — flat, centered, generic
  • Live-action / photoreal scenes. For animation acting beats, route

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/event4u-app/agent-config --skill "src/skills/video-director"
Safe inspection promptEditorial

Inspect the Agent Skill "video-director" from https://github.com/event4u-app/agent-config/blob/0adf49a8ae84b0ff6e2de8759eea43257e020eff/src/skills/video-director/SKILL.md at commit 0adf49a8ae84b0ff6e2de8759eea43257e020eff. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    Procedure

    1. Confirm the input is a live-action / photoreal beat (not animation). 2. If a character.json exists under agents/reference/ai-video//characters/, read the identity tokens — they are reused verbatim. 3. Read the scene's intent in one sentence — what is the camera witnessing, an…

    Confirm the input is a live-action / photoreal beat (not animation).If a character.json exists under agents/reference/ai-video//characters/,Read the scene's intent in one sentence — what is the camera
  2. 02

    Step 0: Inspect

    1. Confirm the input is a live-action / photoreal beat (not animation). 2. If a character.json exists under agents/reference/ai-video//characters/, read the identity tokens — they are reused verbatim. 3. Read the scene's intent in one sentence — what is the camera witnessing, an…

    Confirm the input is a live-action / photoreal beat (not animation).If a character.json exists under agents/reference/ai-video//characters/,Read the scene's intent in one sentence — what is the camera
  3. 03

    Step 1: Draft the 11 blocks

    Emit each block on its own labeled line. Blocks are mandatory and in this order:

    SCENE — location, time-of-day, weather, era.CHARACTER — verbatim identity tokens from character.jsonACTION — verbs and beats. Anticipation → action → reaction
  4. 04

    Step 2: Self-review

    1. Lens length present? "Cinematic" without mm → fail. 2. Lighting direction present? "Golden hour" without angle → fail. 3. ACTION names beats, not adjectives? 4. NEGATIVE block has at least 4 entries, load-bearing on top? 5. CHARACTER block reuses identity tokens verbatim when…

    Lens length present? "Cinematic" without mm → fail.Lighting direction present? "Golden hour" without angle → fail.ACTION names beats, not adjectives?
  5. 05

    Step 3: Validate

    1. Output is plain text, one labeled block per line, ready for scripts/ai-video/lib/parse-blueprint.sh (Phase 3 Step 5). 2. No provider tokens (no --aspect, no --model). That is motion-choreographer's job.

    Output is plain text, one labeled block per line, ready forNo provider tokens (no --aspect, no --model). That is1. Output is plain text, one labeled block per line, ready for scripts/ai-video/lib/parse-blueprint.sh (Phase 3 Step 5). 2. No provider tokens (no --aspect, no --model). That is motion-choreographer's job.

Permission review

Static risk signals and limitations

No configured static risk pattern was detected

This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score92/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars7SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
event4u-app/agent-config
Skill path
src/skills/video-director/SKILL.md
Commit
0adf49a8ae84b0ff6e2de8759eea43257e020eff
License
MIT
Collected
2026-07-28
Default branch
main
View the original SKILL.md

video-director

Turn a scene idea into the 11-block cinematic prompt the hollywood-director persona ships. Output is provider-agnostic prose; provider-specific tuning is handed off to motion-choreographer.

When to use

  • A scene idea, beat, or script line needs to become a cinematic prompt ready to feed an image+video pipeline.
  • A draft prompt reads as "AI video" — flat, centered, generic golden-hour — and needs directorial choices on the page.
  • Live-action / photoreal scenes. For animation acting beats, route to pixar-storyteller.

Do NOT use when:

  • The deliverable is a still graphic or poster → canvas-design.
  • The work is provider-specific token tuning → motion-choreographer after this skill has produced the blocks.
  • A character identity must be re-used across scenes → run character-consistency first to lock identity tokens, then call this skill.

Procedure

Step 0: Inspect

  1. Confirm the input is a live-action / photoreal beat (not animation).
  2. If a character.json exists under agents/reference/ai-video/<project>/characters/, read the identity tokens — they are reused verbatim.
  3. Read the scene's intent in one sentence — what is the camera witnessing, and why now?

Step 1: Draft the 11 blocks

Emit each block on its own labeled line. Blocks are mandatory and in this order:

  1. SCENE — location, time-of-day, weather, era.
  2. CHARACTER — verbatim identity tokens from character.json when present; otherwise silhouette + wardrobe + signature prop.
  3. ACTION — verbs and beats. Anticipation → action → reaction named separately. No "doing things" prose.
  4. CAMERA — position, height, distance, move (lock-off, dolly, handheld, push, pull). Off-axis when on-axis is the AI default.
  5. LENS — focal length in mm (24 / 35 / 50 / 85 / 200) and aperture intent (deep / shallow). "Cinematic" alone fails.
  6. LIGHTING — key, fill, back, practical sources named. "Golden hour" requires an angle (low-east 15°, etc.).
  7. ENVIRONMENT MOTION — what the world does (wind, water, crowd, traffic) and on which beat.
  8. SECONDARY MOTION — hair, cloth, dust, breath. Names the reactive layer that sells the primary action.
  9. MOOD — one emotional read; no compound moods.
  10. DURATION — seconds. Integer or one decimal.
  11. NEGATIVE CONSTRAINTS — clichés to reject, in load-bearing order (top survives truncation). Always names: centered framing, symmetric composition, generic "cinematic", soap-opera contrast.

Step 2: Self-review

  1. Lens length present? "Cinematic" without mm → fail.
  2. Lighting direction present? "Golden hour" without angle → fail.
  3. ACTION names beats, not adjectives?
  4. NEGATIVE block has at least 4 entries, load-bearing on top?
  5. CHARACTER block reuses identity tokens verbatim when a lock exists?

Any "no" → revise that block before handing off.

Step 3: Validate

  1. Output is plain text, one labeled block per line, ready for scripts/ai-video/lib/parse-blueprint.sh (Phase 3 Step 5).
  2. No provider tokens (no --aspect, no --model). That is motion-choreographer's job.

Output format

  1. scenes/<id>/prompt.txt — 11 labeled blocks, one per line, ready for the blueprint parser.
  2. scenes/<id>/review.md — one-paragraph rationale per non-obvious directorial choice (lens, light angle, camera move).

Gotcha

  • The model defaults to centered, on-axis, symmetric — name an off-axis or rule-of-thirds camera or it will silently center.
  • "Golden hour" alone reads as a sunset GIF; require a sun angle.
  • ACTION written as a paragraph of adjectives ("dynamically", "powerfully") fails — adapters need verbs with beat counts.
  • When character.json exists, paraphrasing identity tokens breaks Character Lock — copy them verbatim.
  • Negative constraints in the truncated tail get dropped — load- bearing ones go first.

Do NOT

  • Do NOT emit provider-specific tokens (aspect ratio, model id, duration flags) — that is motion-choreographer's scope.
  • Do NOT collapse anticipation / action / reaction into one verb.
  • Do NOT use "cinematic" without lens + lighting + camera move.
  • Do NOT invent character details when a character.json exists.

Policies

The 11-block cinematic prompt is live-action shape — real-person and brand-impersonation risks are the highest in the cluster. Before emitting:

Refuse-and-surface at the directorial layer; live-action realism amplifies every policy gap downstream.