CommunityWriting & Editinggithub.com

ad-script

Three-column commercial script with read-aloud budget and mute test. Use when writing a timed video ad script from a brief or premise, or auditing a draft script for pacing and sound-off comprehension.

What is ad-script?

ad-script is a Claude Code agent skill that three-column commercial script with read-aloud budget and mute test. Use when writing a timed video ad script from a brief or premise, or auditing a draft script for pacing and sound-off comprehension.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Dankosik/ad-skills/tree/main/skills/ad-script

Installed? Explore more Writing & Editing skills: steipete/notion, langchain-ai/langchain, bytedance/podcast-generation · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Process

  1. Lock inputs and route.

    • Premise options requested: call the Skill tool with "ad-concepts" and stop.
    • Existing draft script supplied: read draft-audit.md and run that workflow instead of steps 2 to 5.
    • New script requested: ask once only if product or exact runtime is missing; when a direct brief omits a premise ("Write a 20-second ad for X"), commit to one dramatic situation passing the swap test and proceed.
    • Exit gate: four inputs are locked before step 2: exact runtime in seconds, product with one single-minded proposition (secondary claims parked out of scope), one product-locked dramatic situation, and any tone or transferable mechanisms.
  2. Build the timed visual spine first.

    • Populate Time and Video from opening hook through physical proof and brand entry to closing button before writing any spoken line.
    • Express every emotion and product claim as camera-observable reality (physical actions, objects, facial reactions, environment, diegetic text).
    • Exit gate: contiguous MM:SS-MM:SS beats sum strictly to target runtime with zero gaps or overlaps, every Video cell passes the camera-lens test (zero internal states, off-screen backstory, or abstract summaries), and physical proof plus brand entry land on or before the button.
  3. Layer Audio as counterpoint.

    • Populate Audio (## Format) as audio counterpoint: every spoken line adds subtext, irony, rhythm, or a twist absent from Video. Replace any line that captions visible action with SFX: or an earned pause ([PAUSE Ns]).
    • Place at least one earned pause or visual/SFX-only beat at the key reveal, reaction, or proof turn (omit only for declared patter).
    • Exit gate: zero captioning lines remain, and every silence or reaction hold carries an explicit [PAUSE Ns] duration.
  4. Audit the read-aloud budget.

    • Pick a delivery tier from ## Cadence and verify spoken pace per beat and across the full spot:
      • Count spoken words only (VO: and CHARACTER:); exclude cue labels, SFX:, MUSIC:, and parenthetical delivery notes.
      • Subtract every [PAUSE Ns] and visual/SFX-only hold from beat duration to get net speaking seconds.
      • Check both words/sec and syllable density against the declared tier.
    • When any beat or total exceeds ceiling, cut spoken words while preserving earned pauses; adjust beat durations only when visual action needs more room.
    • Exit gate: every beat and the full spot sit at or under the stated cadence ceiling, all earned pauses remain intact, and cumulative timestamps still match target runtime.
  5. Run the mute test.

    • Strip all spoken audio (VO: and CHARACTER:) and explanatory supers or cards.
    • Perform a blind read strictly of Video as written: state what a muted viewer learns about the product, cite the exact beat timecode(s) carrying physical proof, and separately list what lives only in Audio.
    • Exit gate: the single-minded proposition is provable strictly from the cited Video beats (Verdict: PASS). If any part of the core claim depends on spoken audio or explanatory copy, rewrite Video so physical action carries the proof, then re-run step 4 before delivering.

Cadence

  • Baseline conversational: <= 2.3 words/sec in English, <= 2.0 words/sec in longer-word languages (Russian, German, etc.); <= 4.5 syllables/sec baseline ceiling across languages.
  • Deadpan or dramatic: <= 1.8 words/sec (EN) / <= 1.6 words/sec (longer-word languages).
  • Deliberate patter: up to 3.0 words/sec (EN) / 2.6 words/sec (longer-word languages); declare explicitly in Header.

Format

  1. Header: Product, single-minded proposition, exact runtime, brand entry timestamp, delivery cadence and wps ceiling.
  2. Three-column script (Markdown table):
TimeVideoAudio
0:00-0:03Camera-observable actionVO:, CHARACTER:, SFX:, MUSIC:, [PAUSE Ns]
  1. Read-aloud budget: per-beat lines (0:00-0:03: 4w / 2.0s = 2.0 wps, [PAUSE 1s] or [visual/SFX only]) plus totals (spoken words, pause/visual-only sec, net speaking sec, overall wps, Verdict: PASS).
  2. Mute test: Visual-only read (citing proof beat timecodes), Audio-only layer, Verdict: PASS.

Related Skills