generating-ai-actors
Generates one photorealistic person as a single image — an AI actor, influencer, presenter or model.
Skill by SupercmoHQ
Chalk Labs
Need help deploying generating-ai-actors?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/supercmohq-generating-ai-actors
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/generating-ai-actors
What's inside
- Skill name
generating-ai-actors- Description
- Generates one photorealistic person as a single image — an AI actor, influencer, presenter or model. The image is reusable, so passing it into any later generation brings the same face, hair and build back and one person can hold across a whole set of images or videos. Use when the user wants an AI actor, or when something needs a person and no photo of one was supplied.
- License
- Apache-2.0
- Metadata
- summary: Casts a distinct, demographic-specific AI actor as a reusable identity reference, allowing you to reliably feature the exact same brand face across an entire multi-asset image and video campaign. · version: 0.4.0 · category: creative
- Instructions
- 143 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- eval_cases.json · evals/
SKILL.md (first lines)
# The actor Generate an image of an AI actor. Anything the brief specifies wins. The defaults below fill gaps only. ## Workflow ### Step 1: Cast the person An adult, always. Fill a younger brief with an adult and say so. Keep casual words for young people out of the prompt altogether, even where the person described is plainly an adult. They trip the image model's content filter and lose the generation. Decide each of these deliberately rather than leaving it to the model, which returns the same face every time. **Who they are** — gender, age, ethnicity, build. An age anywhere from early twenties to late sixties, a build anywhere from slight to athletic, broad or full. **How they look.** This is what makes them recognisable when the image is reused, so it carries the most weight. Take the face feature by feature. **The examples below are a starting point, not the choices on offer.** Reach past them, decide each line separately, and don't cast the same combination twice. - **Face shape, jaw and chin** — oval, square, heart, long, round, diamond, oblong, pear, inverted triangle. The jaw strong and angular, or soft and tapered. The chin with a deep cleft or a subtle dimple. - **Cheekbones** — high and sharp, soft and low, broad, prominent, sculpted, subtle and flushed, apple-cheeked, hollowed beneath, or slightly asymmetrical. - **Eyes, shape and set** — almond, round, hooded, monolid, downturned, upturned, deep-set, wide-set, or close-set. - **Eyes, colour** — emerald green, stormy grey, hazel with gold flecks, amber, pale ice blue, deep mahogany brown, heterochromia, violet-blue, moss green, or near-black. - **Eyebrows** — thick and bushy, neatly arched, thin and straight, feathered and wild, bleached, dark and heavy, soft and sparse, subtly unibrowed, sharp and angular, or softly rounded. - **Nose, bridge and tip** — straight, aquiline, upturned, wide and flat, snub, button, Roman, bulbous-tipped, or slightly crooked from a healed break. - **Mouth** — full evenly, thin on top and full on the bottom, wide and generous, small and tight, a sharp Cupid's bow, a flat Cupid's bow, a resting smirk, downturned corners, slightly parted at rest, or soft and pillowy. - **Skin texture and tone** — smooth and glass-like, visible pores, sun-weathered with deep crow's feet, scattered natural hyperpigmentation, subtle acne scarring, porcelain pale, rich deep bronze, rosy-cheeked, olive with gold undertones, or naturally dewy. - **Hair, colour** — auburn, bright copper, honey blonde, icy platinum, salt-and-pepper, henna red, jet black, ash brown, silver-white, or a faded pastel wash. - **Hair, length and how it's worn** — a military buzz crop, a jaw-length asymmetrical bob, a blunt shoulder cut, flowing past the waist, a shaved undercut, a messy top-knot, a slicked-back low bun, intricate protective braids, heavy blunt bangs, or a sweeping curtain fringe. - **Hair, texture** — poker-straight, loose beachy waves, tight coiled ringlets, fine and flyaway, thick and heavy, coarse, silky, a soft frizzy halo, locs, or naturally bald. - **Facial hair** — clean-shaven, a heavy five-o'clock shadow, a neatly trimmed goatee, a full thick beard, a pencil moustache, a handlebar moustache, a soul patch, scattered stubble, a sculpted chinstrap, or heavy mutton chops. - **Glasses** — none, thick black acetate frames, thin round wire frames, rimless, browline frames, oversized geometric frames, tortoiseshell cat-eye, clear acrylic, vintage aviators, or subtly tinted lenses. - **Makeup** — none at all, lip balm and brushed brows only, everyday concealer and mascara, sharp winged eyeliner, a bold matte red lip, a heavy smoky eye, graphic neon liner, fully contoured evening glam, a sheer lip tint, or faux freckles. - **One distinguishing feature, or none** — freckles dusted across the nose, deep cheek dimples, a small silver septum piercing, a small scar through the eyebrow, a jagged scar on the chin, a gold tooth, a subtle neck tattoo, or a small nose stud. Never a mole or a beauty mark. Keep the face attractive and the build well-proportioned. **Say in the prompt that the person is invented.** Open the subject with it, in these words or close to them: *"a wholly fictional, non-identifiable person — not a real or public figure, and not resembling any actual individual."* **What they're wearing** — the garments and how they sit on the body, any accessories or jewellery, and how the whole thing is put together. **The top is closed, whatever the brief asks for.** Every description should put the neckline high and the chest fully covered. Anything cut low or strappy is only ever worn with a closed layer over it, never by itself. Write that coverage as what is there, not as what isn't: *"a round-neck T-shirt"*, *"a fully buttoned V-neck cardigan"*. Describing what to leave off — the plunge, the skin, the gap — tends to put exactly that in the picture, so phrase the whole line as presence. ### Step 2: Set the scene A place the brief names is the place. Otherwise pick one that fits how the actor will be used, indoors or out. Then describe it — the surfaces, the objects, and what fills the space. A name alone gives the model nothing to build the room from. - **The setting** — where they are, and what surrounds them. - **What's behind them** — what falls in frame, as it happens to be rather than arranged. - **Colours** — the ones that dominate. - **Time of day and weather**, where they show. - **The light** — where it comes from, its quality, and what it catches. Default to plain, neutral daytime light with no warm tint — ordinary daylight colour, not a sunset glow — unless the brief asks otherwise. No studio lighting, no plain backdrop. ### Step 3: Set the shot - A self-portrait on a phone's front camera. - Head and shoulders fill the frame, at arm's length. - Framing slightly tilted, not quite centred. - Looking into the lens, face turned toward it. Not sideways, not in profile, not glancing off to one side. - Small-sensor grain, real skin, no retouching, subject sharp and background falling away on its own. - Hands empty Keep out: *portrait*, *editorial*, *studio*, *posed*, *retouched*, *magazine-style*, any professional camera, tripod or lighting rig, ### Step 4: Write the prompt in this order Write the prompt as prose in this order — one paragraph is enough. 1. **Subject** — from Step 1 2. **Location** — from Step 2 3. **Composition** — from Step 3
From SupercmoHQ/superCMO-skills, Apache-2.0.
More from SupercmoHQ/superCMO-skills
- 0.796score
planning-campaigns
SupercmoHQ
Decides what to make next — turns the brand, the product, your own running ads and competitor research into the concepts worth testing next.
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
researching-competitor-ads
SupercmoHQ
Analyzes the ads competitors are running — the ones live now, the ones they have already stopped, and which have run longest.
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
analyzing-own-ads
SupercmoHQ
Audits the ads a company is running itself — what's live now, what it has already stopped, and which have run longest.
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
writing-ad-copy
SupercmoHQ
Writes the words of an ad — the headline, primary text, description and call to action that go into the ad platform's own fields, shaped to the channel it…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
analyzing-products
SupercmoHQ
Normalizes a product into generation-ready facts — from an e-commerce URL (a clean description plus curated product images) or from a photo alone (category…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
cloning-video-ads
SupercmoHQ
Clones an existing video ad — reads a supplied reference ad, keeps its structure, pacing, shots, camera and hook, and rebuilds it as a new video with the…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
generating-ad-videos
SupercmoHQ
Makes a product ad video — a product showcase with no one on screen, or a story or lifestyle commercial where a presenter or actor plays a role in the brand's…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
generating-audio
SupercmoHQ
ALWAYS read this skill before generating spoken audio or calling audio_generate — a voiceover, narration, an ad read, a character line, or any script read…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
generating-cartoon-videos
SupercmoHQ
Generates a cartoon video for a product — a drawn, animated, anime, illustrated or painted spot that holds one art style and the same characters across every…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
generating-image-ads
SupercmoHQ
Turns a product photo or URL into a static image ad — one image, or a set.
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
generating-images
SupercmoHQ
ALWAYS read this skill before generating or editing any image, or calling image_generate — text-to-image or image-to-image, simple or complex.
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
generating-product-photos
SupercmoHQ
ALWAYS read this skill before generating a product photography — before writing any prompt or calling image_generate.
SkillAFreshness: A★ 206Claude Code +9
Signals
- Stars
- 206
- Forks
- 23
- Open issues
- 9
- Contributors
- 4
- Last commit (this folder)
- Aug 13, 2026 (2 months ago)
- Last release
- Oct 21, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 0.4.0
- License
- Apache-2.0
- Repository
- github.com/SupercmoHQ/superCMO-skills
- Website
- getsupercmo.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from SupercmoHQ
- 0.796score
adapting-formats
SupercmoHQ
Resizes an existing image ad into the other shapes it has to run in — reads the ad first, then regenerates it at each ratio with the original passed in as a…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
analyzing-brand
SupercmoHQ
Analyzes a brand from its own website — its colours and fonts, the logo and imagery it uses, how it sounds, who it sells to, the claims it makes, and what it…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
analyzing-own-ads
SupercmoHQ
Audits the ads a company is running itself — what's live now, what it has already stopped, and which have run longest.
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
analyzing-products
SupercmoHQ
Normalizes a product into generation-ready facts — from an e-commerce URL (a clean description plus curated product images) or from a photo alone (category…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
cloning-video-ads
SupercmoHQ
Clones an existing video ad — reads a supplied reference ad, keeps its structure, pacing, shots, camera and hook, and rebuilds it as a new video with the…
SkillAFreshness: A★ 206Claude Code +9 - 0.796score
generating-ad-videos
SupercmoHQ
Makes a product ad video — a product showcase with no one on screen, or a story or lifestyle commercial where a presenter or actor plays a role in the brand's…
SkillAFreshness: A★ 206Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get generating-ai-actors running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
generating-ai-actors skill. Agent Mart. https://agentmart.dev/skills/supercmohq-generating-ai-actors (last updated 2026-10-24)