beatra-ai/beatra-skills / plugins/ai-headshot-studio/skills/ai-headshot-studio
ai-headshot-studio
VerifiedTransform a casual selfie into a studio-quality professional headshot for LinkedIn, resume, company website, business card, or social media. This AI headshot generator creates polished professional portraits with new backgrounds, professional attire, and studio lighting while preserving the person's identity. Generate corporate headshots, tech startup portraits, academic profile photos, medical professional images, and creative industry portraits from one selfie. Specify a professional style and industry, pair with a desired background or setting, or refine an accepted headshot toward a publish-ready result.
AI Headshot Studio
Create one studio-quality professional headshot or portrait from a casual selfie, an industry style, or an accepted draft. Reuse decisions already present in the conversation and move by the shortest route that completes the requested headshot.
Choose the route
- Transform a selfie into a professional headshot: with one selfie photo,
specify a professional style and industry—corporate, tech, creative, academic,
medical, or startup—and receive a polished headshot with new background,
professional attire, and studio lighting using
beatra.images.transform. This is the default when a source selfie exists. - Transform with a background reference: when the user provides a desired
background or setting alongside the selfie, use
beatra.images.transformwith the selfie asimages[0]and the background reference asimages[1]to place the person in a specific professional environment while preserving identity. - Refine an accepted headshot: use
beatra.images.editwith the accepted headshot asimages[0]to adjust lighting, background, expression, or attire without changing the person's identity or overall composition.
Follow headshot routing for the precise branch and industry style matrix, and portrait craft when turning the request into a visual specification that meets professional headshot standards.
Shape one headshot brief
Reuse the user's professional context, target platform, style preference, and any visual references. Ask only when a missing decision materially changes the result. For a standard professional headshot, propose a square 1:1 canvas with studio lighting, a clean background, and the person centered in head-and-shoulders framing as the default.
Build the brief around:
- the professional context and industry—corporate, tech, creative, academic, medical, startup, or a custom direction;
- the target platform and use case—LinkedIn profile, resume, company website, business card, or social media;
- one style direction—corporate formal, modern casual, creative artistic, clean editorial, or medical clinical;
- a background preference—solid white, soft gray, navy gradient, modern office, outdoor, or studio backdrop;
- an output format—square for LinkedIn and social media profiles, portrait for resume and print;
- ordered visual references when available (selfie first, background or style reference second).
If the user has already stated the industry or style, reuse it. If that choice is genuinely missing, propose the best default and include it in the single paid-call confirmation.
Prepare the call
Use only this Skill's bundled scripts/mcp_client.py for every remote MCP
operation. The tool name is a CLI argument and the tool arguments are the JSON
sent on stdin. Do not configure or call a host Beatra Connector, and do not use
REST/OpenAPI as a fallback. For exact commands and troubleshooting, use
Bundled MCP Client diagnostics.
- Upload the source selfie through the bundled client helpers first, then call
beatra.images.transformwith the uploaded artifact as the first ordered reference. Label the person's role and identity cues explicitly in the prompt so the model preserves facial features, skin tone, and hair. - For a background reference transform, upload the background image as a second ordered reference and label it as a background or setting guide only.
- For an accepted headshot, call
beatra.images.edit. Use at most two normalizededit_regionsonimage_index=0for localized fixes; omit regions for a whole-image adjustment.
Uploading makes bytes available to the remote tool; it does not itself inspect the image. Review only visual facts the host can actually see.
Keep model=auto and count=1 unless the user explicitly chooses otherwise.
Call beatra.models.list only for a real model, availability, compatibility,
or price decision. The detailed request shapes and examples are in
workflow.
Confirm and execute once
Planning and brief preparation are free. Before the paid image call, show and freeze the final prompt, ordered references, canvas, style direction, background, lighting, model, controls, and output count. Merge any still-material high-impact choice into this one confirmation.
After approval, create one stable opaque client_request_id for that exact
logical request and submit it once. A changed prompt, reference or order,
canvas, style direction, background, model, count, or control is new paid work
and needs a new confirmation and a new ID.
Track, review, and deliver
After receiving a task_id, poll only that task with beatra.tasks.get. If the
ID is lost, use beatra.tasks.list to find candidates and verify the selected
one with tasks.get. Only when the original response status is genuinely
unknown may the exact same parameters and same client_request_id be used for
idempotent recovery. Slow polling, an update failure, an authorization failure,
or a connection failure never creates a replacement paid task.
Use beatra.tasks.cancel only when the user asks. If cancellation returns
409, continue tracking the original task. See review and
recovery for the full recovery contract.
When the result is visible, review identity fidelity (is the person's face
recognizable against the source selfie?), professional appearance (is attire,
grooming, and expression appropriate for the industry?), background quality (is
the background clean and professional?), lighting (is the lighting flattering and
even with sharp focus on the eyes?), and canvas fit (is the output ratio correct
for the target platform?). Deliver the artifact links, observed dimensions, task
ID, and billing.net_charged_credits. Offer at most one focused, unexecuted
revision. Generated assets can also be viewed and managed at
beatra.ai.
If the tool returns insufficient credits: give the user the tool message in full. Do not change the URL. You may translate the other words. Do not replace it with your own top-up copy. Point the user to pay using that message.
When the user asks how many credits remain, call beatra.wallet.get. When they
ask what was charged, call beatra.wallet.ledger. Both are read-only. Do not
invent an account-balance or top-up tool. Do not make wallet.get a required
step before every paid submit.
References by task
- Choosing among selfie transform, background-reference transform, and headshot refine, or planning for a specific industry style: headshot routing
- Turning a request into a professional headshot specification with lighting, background, attire, and identity preservation rules: portrait craft
- Exact request shapes, ordered-reference labeling, and JSON examples for each route: workflow
- Lost task, slow task, cancellation, result review, or planning a revision: review and recovery
- First install or expired authorization: installation and authentication
- Bundled MCP Client commands and diagnostics: Bundled MCP Client diagnostics
- Installation registration: installation registration
- Task lookup, polling, and result fields: tasks and results
- Balance, validation, and structured errors: billing, errors, and recovery
- Disconnecting the installation: uninstall and disconnect
- Updates and security: updates and security
Installation and account operations
For first use and shared operations, follow installation and authentication, installation registration, tasks and results, billing, errors, and recovery, and uninstall and disconnect.
Updates and security
This Skill runs only the files installed with it and leaves them unchanged while it runs; it never downloads or executes other code. It talks to Beatra's official services over HTTPS, and a file you choose to upload goes only to the one-time upload address Beatra issues for it.
Once a day at most, the bundled client reads Beatra's public version list. When the store or tool you installed from has a newer version, it prints one line with the command that updates it there. Updating stays your choice, through that store or tool. See updates and security.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |