More screenshots
Works with the AI Agents you already use
About Me Avatar: The Agent's View of You
A 1-bit monochrome pixel-art portrait of the user, drawn from their About Me profile — cumulative across generations, gender-neutral by default, and strictly text-free.
$5
About Me Avatar: The Agent's View of You
Example session with this skill installed
Generate my agent's view of me. My About Me says: "I build games for a living, mostly Godot. I wear a flat cap most days. Coffee before code, always. I play bass in a weekend band. I like quiet mornings and long walks with my dog." I have no existing avatar — this is the first one.
- Read your context and instructions
- Compiled the about me avatar
FIRST GENERATION — avatar created from your profile (base face as the starting point, no prior avatar to evolve from).
Profile traits extracted, each quoted to its source phrase:
- Flat cap — "I wear a flat cap most days" → headwear, simple block shape.
- Game controller — "I build games for a living, mostly Godot" → margin object.
- Coffee cup — "Coffee before code, always" → margin object.
- Bass guitar — "I play bass in a weekend band" → margin object.
- Small dog — "long walks with my dog" → margin object.
Constraints checked: nothing in the profile triggers a constraint. No gender is stated, so the face stays gender-neutral. No identity markers, weapons, or real-person likeness involved.
Composition: forward-facing bust, chest up, centered, square 1:1, pure white background, strictly 1-bit (pure black and pure white, no grayscale, no shading). Plain crew-neck collar — no costume. Four margin objects, symmetric, clear of the face: bass guitar, coffee cup, game controller, small dog. No text, letters, numbers, or logos anywhere.
Generation prompt assembled from the template (style lock, framing, continuity from the base face, personalization, prohibitions) and the image produced. Inspection passed on the first pass: 1-bit clean, text-free, face uncovered, objects in the margins.
Saved by writing the avatar path, so your next profile update evolves this portrait instead of starting over. Audit note recorded with every feature traced to its profile phrase. If your profile changes — say you stop wearing the cap — only that feature updates; the face you recognize stays.
Connects securely to your tools. The creator never sees your data.
About this skill
This skill generates "the agent's view of you": a small pixel-art bust portrait derived from the user's About Me profile, the way a friend would doodle someone in a notebook margin. It is not a likeness and not a photograph — it is an interpretation, one or two signature traits captured, the rest left abstract.
The portrait is cumulative, not reset. Each generation evolves the previous avatar as the profile grows, so the visual identity accretes over time instead of restarting daily. The fundamentals always carry forward: pixel-block style, line weight, bust framing, eye placement, nose continuity. Evolution edits details; it never redraws the foundation.
The core discipline is stated, not inferred. Every visible feature must trace to something the profile explicitly says — a flat cap, glasses, a collar hint, or two to four small margin objects (a bass guitar, a coffee cup, a game controller) standing for occupations, hobbies, or interests. When the profile is thin, the skill returns the base face untouched rather than inventing traits. Hard constraints outrank the profile: gender-neutral by default, no identity markers, no weapons, no real people, and nothing that depicts a recognizable person.
The skill includes a step-by-step protocol (gather, extract, check constraints, compose, prompt, inspect, save), a profile-reading decision table, a prompt template, a pre-delivery checklist, and a full worked example. Every generation ends with an audit note listing which profile phrases drove each feature, so the user can check the interpretation.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
- It is an interpretation, not a likeness — it will not look like a photograph of the user.
- A thin profile (under ~30 substantive words) produces the base face unchanged rather than an invented portrait.
- The image model can occasionally add text despite the prohibition; the skill regenerates once, then keeps the previous avatar if it fails twice.
- Gendered features appear only when the profile explicitly grounds them; the default is gender-neutral.
- It generates one portrait per run; it does not produce variations or a gallery.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago
Permissions
No special permissions declared or detected