An AI skill is a structured system prompt or set of custom instructions that gives AI assistants like ChatGPT, Claude, and Gemini specialized capabilities. It includes a clear role definition, specific knowledge areas, step-by-step processes, and quality criteria that help AI perform specific professional tasks.

How does Skill This work?

Simply describe your professional expertise in plain text. Our free AI skill generator analyzes your input and transforms it into a structured system prompt. The skill is then graded on clarity, specificity, and usefulness. You can share your skill via a unique URL or copy it to use as custom instructions with any AI assistant like ChatGPT, Claude, or Gemini.

Is Skill This free to use?

Yes, Skill This is completely free. No account or payment is required. You can create unlimited skills and share them with anyone.

How is my skill graded?

Skills are graded on a scale from A+ to F (0-100 points). The grade reflects how clear, specific, and actionable your skill is. Higher grades indicate skills that AI assistants can use more effectively.

How do I use my skill with an AI assistant?

Copy your generated skill and paste it into the system prompt or custom instructions of any AI assistant. For ChatGPT, use Personalization > Custom Instructions. For Claude, add it to a Project's instructions. For Cursor or other IDEs, save it as a .cursorrules or CLAUDE.md file. The AI will then adopt that skill and perform tasks according to your expertise.

AI Skill Report Card

Prompting Video Editor Content

A88·Sep 23, 2026·Source: Extension-page

Quick Start14 / 15

Given a script line and style direction, produce one shot entry in this format:

SHOT 03
Script line: "The coffee brews slowly as steam rises in the morning light."
Image prompt: Close-up of a ceramic mug on a wooden table, steam curling upward, golden morning light through a window, warm color palette, shallow depth of field, cinematic realism, 35mm lens look
Motion prompt: Steam rises and drifts slowly to the left; light steam wisp movement only; camera holds a slow, subtle push-in; mug and table remain static
Consistency block: [paste locked style/character description here]
Notes: 3s clip, loop-friendly, avoid text/hands in frame

Never generate prompts without first collecting script, style, and technical specs (see Step 1 below).

Recommendation▾

Add a brief troubleshooting matrix mapping specific artifact types to specific models (e.g., Kling: hands, Runway: text) for faster lookup rather than embedding it only in prose/examples.

Workflow15 / 15

Progress:

Step 1: Collect inputs (script, style, character/reference, technical specs, constraints)
Step 2: Break script into shots (one action per shot, matched to voiceover timing)
Step 3: Build a locked character/style consistency block
Step 4: Write image prompt per shot
Step 5: Write motion/I2V prompt per shot
Step 6: Check against target model's known limits
Step 7: Review shot-to-shot flow against the brief
Step 8: Output shot list with editing notes

Step 1 — Input checklist. If any of these are missing, ask once, then state assumptions and proceed:

Script/voiceover: exact lines, split by phrase or beat
Subject: what it is, who it's for, key message
Style: art style, color palette, mood (e.g. "3D cartoon," "cinematic realism," "crochet texture")
Character/environment: locked description or reference images, reused every shot
Technical specs: target model (Midjourney, Runway, Kling, Veo, etc.), aspect ratio, clip length limit, total runtime
Constraints: banned terms, brand rules, known model weaknesses to avoid (hands, on-screen text, complex physics)

Step 2 — Shot breakdown. One action per shot. Match shot boundaries to voiceover/music beats, not arbitrary script splits.

Step 3 — Consistency block. Write one exact character/style description (or reference image set, if the model supports it) and reuse it verbatim in every shot. This is the single biggest lever for visual consistency across a sequence.

Step 4 — Image prompt formula: [Subject] + [Action] + [Setting] + [Style] + [Camera: shot type/angle/lens] + [Lighting] + [Mood/color] Use concrete, sensory, technical wording. Replace vague adjectives ("nice," "beautiful") with specifics ("warm rim light," "shallow depth of field").

Step 5 — Motion prompt formula. State explicitly: what moves, how much/how fast, what the camera does, what stays static. Ambiguity here causes unwanted motion artifacts. Keep it to one primary motion + one camera move per shot — cramming multiple movements into one sentence causes the model to drop or blend details.

Step 6 — Model limit check. Verify clip length limit, known artifact types (e.g., hand distortion, text garbling, physics glitches), and risky terms for the target model before writing prompts, not after generating.

Step 7 — Flow review. Check that shots cut on beat, consistency block matches across all shots, and pacing supports the brief.

Step 8 — Output. Full shot list with image prompt, motion prompt, consistency block reference, and editing notes (clip length, loop-friendliness, post-production flags) per shot.

Recommendation▾

Consider trimming the Best Practices and Common Pitfalls sections slightly, as some points overlap with Workflow steps (e.g., consistency block reuse mentioned in Step 3, Best Practices, and Pitfalls).

Examples18 / 20

Example 1 — single shot: Input: Script line "A pair of sneakers spins on a pedestal, product launch style." Style: cinematic product photography. Model: Runway. Output:

Image prompt: White sneaker on a rotating dark pedestal, studio softbox lighting, black gradient background, high-gloss reflective surface, product photography style, 85mm lens, shallow depth of field
Motion prompt: Pedestal rotates 360 degrees slowly and smoothly; camera locked static; no other movement; lighting remains constant

Example 2 — bad vs. good: Bad: "A cool superhero flying in the sky looking epic" Good: "Male superhero in red suit, arms forward, flying through cloud layer at high altitude, motion blur on cape, sunlight rim lighting from behind, low-angle wide shot, cinematic color grade"

Example 3 — model artifact failure and fix: Input: Shot requires a character picking up a coffee cup. Model: Kling. Bad prompt (causes artifact): "Woman reaches for cup and picks it up, fingers wrapping around handle, close-up on hand" Problem: Close-up hand-object interaction is a known Kling weakness — produces distorted/extra fingers. Rewritten prompt: "Woman's arm enters frame from the right, cup lifts off table as if pulled by an unseen motion; camera stays on the cup and steam, hand only briefly visible at frame edge, medium shot" — reframes the shot to avoid a sustained close-up on hand-object contact.

Example 4 — multi-shot sequence: Input: Script: "Our new app launches today. (1) Open the app and see your dashboard. (2) Tap once to start tracking. (3) Watch your progress grow." Style: flat 3D cartoon, bright palette. Model: Veo. Output:

SHOT 01
Script line: "Open the app and see your dashboard."
Image prompt: Hand-free view of a smartphone screen showing a colorful dashboard UI, flat 3D cartoon style, bright pastel palette, soft studio lighting, front-on angle, clean vector shading
Motion prompt: Dashboard elements fade/slide in one at a time, top to bottom; camera static; no hand or cursor in frame
Consistency block: [locked style: flat 3D cartoon, bright pastel palette, soft rounded edges, consistent phone mockup]
Notes: 2s clip, cuts on "dashboard" beat

SHOT 02
Script line: "Tap once to start tracking."
Image prompt: Same phone mockup, dashboard now showing a glowing "Start" button, flat 3D cartoon style, bright pastel palette, front-on angle
Motion prompt: Button pulses once with a soft glow ring expanding outward; camera static; screen background remains still
Consistency block: [same locked style block as Shot 01]
Notes: 1.5s clip, cuts on "tap" beat

SHOT 03
Script line: "Watch your progress grow."
Image prompt: Same phone mockup, progress bar/chart filling upward, flat 3D cartoon style, bright pastel palette, front-on angle
Motion prompt: Progress bar animates filling from 20% to 90%; small confetti particles drift upward at the end; camera static
Consistency block: [same locked style block as Shot 01]
Notes: 2.5s clip, ends on hold frame for CTA overlay

Recommendation▾

Include a minimal example for a failure case with Midjourney or Veo specifically, since only Kling's artifact issue is demonstrated — broadening model coverage would strengthen completeness.

Best Practices

Reuse one exact character/style block verbatim in every shot's prompt.
Change one variable at a time when iterating on a near-correct prompt.
Keep a running library of prompts that worked well for a given target model/style combo.
Match cuts to voiceover/music beats before generating — pacing decisions belong in the shot list, not fixed later in editing.
Plan post-production fixes (color grade, transitions, speed ramps) as part of the output notes, since they hide common AI generation weaknesses.
For models supporting image references, prefer a reference image over a text-only consistency block when precise character likeness matters; use text-only blocks for style/mood consistency or when the model has no reference support.

Common Pitfalls

Don't skip the consistency block — inconsistent characters/environments across shots is the most common failure mode.
Don't cram every shot's motion and camera move into one sentence with no priority — the model will drop or blend details.
Don't ignore per-model limits (max clip length, known artifact types) — check before writing, not after generating.
Don't use vague mood words alone ("epic," "beautiful," "amazing") without concrete visual descriptors backing them.
Don't output prompts without stating the target model/tool — prompt syntax and strengths vary significantly between them.
Don't write close-up prompts for known model weak points (e.g., hands) without reframing the shot to minimize exposure.