- Name
-
@di-atomic/persona-builder
- Tagline
-
An AI employee somebody would actually pay to hire.
- Hero subhead
-
Researches the real profession first, then composes the persona from what it found: the title from what the market calls the role, the skills from practitioner frequency, the self-description from the register practitioners use on themselves, and the name from name-frequency distributions checked until it belongs to nobody.
- Who it's for
-
Anyone shipping an AI employee, a catalog agent, or a synthetic spokesperson, and anyone whose persona keeps coming back looking obviously generated.
- Version
-
0.1.1
- Tier
-
beta
- Path type
-
guidance-only
- Hero image
-
- Diagram image
-
- Install command
-
opvs-skills install @di-atomic/persona-builder
- Trigger phrase
-
build a persona for
- Marketplace URL
-
https://market.opvs.ai/v/di-atomic/persona-builder
- Blog URL
-
https://di-atomic.com/blog/shipping-di-atomic-persona-builder
- Stat 1 value
-
7/102
- Stat 1 label
-
of my own shipped avatars met the standard before I built this
- Stat 2 value
-
17/17
- Stat 2 label
-
planted defects caught in testing, with 5 of 5 clean controls passing
- Stat 3 value
-
5
- Stat 3 label
-
scripts that print PASS or FAIL, including one that fails closed
- Stat 4 value
-
226
- Stat 4 label
-
words in the prompt that passed, against 85 in the one that shipped
- What headline
-
The three rules doing most of the work
- Cap 1 icon
-
📷
- Cap 1 title
-
Three camera registers, not one
- Cap 1 desc
-
An editorial headshot wants 85mm at f/2.8 on a blurred background. A social post wants a phone, uneven framing and some clutter. A casual post that looks studio-shot reads as an ad, and readers discount ads. The seed and the content want opposite cameras, so the gate checks per pack instead of applying one rule everywhere.
- Cap 2 icon
-
📎
- Cap 2 title
-
Stop describing what the reference fixes
- Cap 2 desc
-
Once a reference image has locked the identity, re-describing the face in a variation prompt fights the reference and drifts the likeness. A good variation prompt says what changes, which is the setting, the pose and the light, and says nothing at all about the person.
- Cap 3 icon
-
🔍
- Cap 3 title
-
Imperfection is the highest-value token
- Cap 3 desc
-
Pores, asymmetry, a stray hair, light falling off unevenly. Strip those out and you do not get a cleaner photograph, you get an obvious render. It is the cheapest single edit that moves an image from generated to photographed, and 74 of my 102 avatars contained none of it.
- Showcase headline
-
Same character, same model, same day
- Showcase before caption
-
The 85-word prompt. Polished, symmetrical, evenly lit. Indistinguishable from the stock-corporate avatar already in the catalog.
- Showcase after caption
-
The 226-word prompt. Pores, asymmetry, flyaway strands, light that falls off. The only variable that changed is the text.
- Diagram caption
-
Research returns distributions and vocabulary. The people it read stay behind, and the script enforcing that fails closed.
- Worked title
-
How the research actually runs
- Worked example
-
> "build a persona for a hospitality SDR"
FRAME ....... 8 to 15 companies that really employ the role
a human judgement call, and it is logged
WIDE ........ company mode, short, ~1,000 people
title vocabulary approx $4
SKILLS ...... keeper companies at full
skills, experience, education $8/1K
DEEP ........ profile mode on 15 to 25
headline + about $0.003 each
AGGREGATE ... distributions out
individuals stay behind
-> no name, employer, biography, profile URL
or photo survives into the persona file
-> manifest missing? the check FAILS CLOSED
- Worked framing
-
The naming step is the one people get wrong. Taking the most frequent first name and pairing it with the most frequent surname reliably produces a real, findable person, so the name is composed across frequency bands instead and then checked against the research set until it belongs to nobody.
- Rel 1 icon
-
🎨
- Rel 1 name
-
@di-atomic/media-generator
- Rel 1 desc
-
Renders the seed, the face-consistency frame and the six variations.
- Rel 1 url
-
https://market.opvs.ai/v/di-atomic/media-generator
- Rel 2 icon
-
🎤
- Rel 2 name
-
@di-atomic/voice-builder
- Rel 2 desc
-
Sets the register the persona speaks and writes in.
- Rel 2 url
-
https://market.opvs.ai/v/di-atomic/voice-builder
- Rel 3 icon
-
🔍
- Rel 3 name
-
@spideriq/lead-gen-skills
- Rel 3 desc
-
Runs the LinkedIn profession research the persona is composed from.
- Rel 3 url
-
https://market.opvs.ai/v/spideriq/lead-gen-skills
- CTA headline
-
I ran the gate on my own catalog before I shipped it.
- CTA description
-
Seven of my own hundred and two avatars passed, which is exactly why the skill exists: the standard was applied once and then quietly stopped being the default. If you are building AI employees that need to look like people somebody would hire, in any of our seven languages, that is the day job.
- Security score
-
100
- Upstream license
-
PROPRIETARY
