AI Image Realism Skill

Overview

Make existing AI portraits, product images, and marketing visuals look more natural by fixing plastic skin, malformed hands and faces, repeated textures, and inconsistent lighting, from inside Claude Code, Codex, or OpenClaw. The work is produced on the hosted, paid Beatra service (mcp.beatra.ai).

This catalog entry is a reviewed pointer, not the executable package. It contains no client code and performs no Beatra operation by itself. The package it points to bundles three standard-library Python scripts that make network calls and store a credential. It has no self-updater: it never downloads code and never changes its own files. Read Install and Security & Safety Notes before activating it.

Pinned identity	Value
Package	ai-image-realism 0.3.6
Source commit	beatra-ai/ai-image-realism-skill@0b29222 (full SHA 0b29222a61c52917887efa40d39e100683b03625)
Package tree	d7b1f2866555aae60d53de35293437b2ecbdb6d6 (Git tree ID of skills/ai-image-realism at that commit)
License	MIT No Attribution (MIT-0)

The pinned tree holds regular files only (no symlinks, no executable bits, no binaries). Confirm that with the inspect commands below.

When to Use This Skill

• Use when the user explicitly wants an existing image retouched on Beatra and accepts that it is paid.
• Use when the host agent can view the source image and the user has agreed to send it to a third party.
• Do not use for local-only image editing or when no paid render was approved.

Install (pinned, verified, approved twice)

Step 1: Fetch the pinned tree into a review directory

Explain that this fetches an external package from github.com, then ask for approval. Only after approval:

set -e
umask 077
review_dir="$(mktemp -d)"
cd "$review_dir" || exit 1
git clone --quiet --filter=blob:none --no-checkout https://github.com/beatra-ai/ai-image-realism-skill.git src
git -C src checkout --quiet 0b29222a61c52917887efa40d39e100683b03625 -- skills/ai-image-realism
test "$(git -C src rev-parse '0b29222a61c52917887efa40d39e100683b03625:skills/ai-image-realism')" = 'd7b1f2866555aae60d53de35293437b2ecbdb6d6' && echo TREE-OK

Stop if the last command does not print TREE-OK. The expected commit and tree IDs come from this catalog entry, not from the package or its website, and Git addresses every fetched object by its hash.

Step 2: Inspect before activation

git -C src ls-tree -r 0b29222a61c52917887efa40d39e100683b03625 -- skills/ai-image-realism | awk '$1 != "100644"'  # expect no output
grep -n -E 'maybe_auto_update|download_update|_apply_update' src/skills/ai-image-realism/scripts/mcp_client.py  # expect no output

The first check lists any symlink, executable, or submodule entry; the second finds the entry points of the self-updater that earlier versions shipped.

Report to the user what the review found: SKILL.md, manifest.json, install-source.json (the one-line marker {"schema_version":1,"source":"github"}), the bundled Markdown references, and scripts/authorize.py, scripts/mcp_client.py, scripts/uninstall.py (Python 3.10+, standard library only, no dependency installation, no lifecycle hooks). Summarize the network, credential, local-state, telemetry, and version-notice behavior listed under Security & Safety Notes.

The manifest and pattern scans above are only inventory aids. Before activation, read every file in the pinned tree, including each script, reference and hook, and inspect all dependency and network behavior. Do not claim source review from grep output. If complete review cannot be performed, stop before copying or executing; ask for a separate review rather than treating a digest as evidence of safety.

Step 3: Copy in

Ask for a second, separate approval, because this changes agent configuration. Then copy the reviewed tree to the host's skills directory (Claude Code shown; use the equivalent path for other hosts):

dest="$HOME/.claude/skills/ai-image-realism"
test ! -e "$dest" && test ! -L "$dest" || { echo "destination exists; stop and ask the user"; exit 1; }
cp -R "src/skills/ai-image-realism" "$dest"

There is no update switch to turn off in this version.

Step 4: Authorize as its own decision

Authorization opens a browser sign-in and stores a bearer token. Ask first.

python3 "$dest/scripts/authorize.py"

Start a new agent session if the host discovers skills only at startup.

How It Works

1. Read the installed package's SKILL.md and its references; they define the routes, payload shapes, and review loop.
2. Use free, non-billable discovery first (beatra.models.list, task list) to read current model cards and credit estimates.
3. Show the user a cost card for exactly one paid call: tool, model, estimate, and which files will be uploaded. Wait for explicit approval. Planning or "just do it" is not approval.
4. Upload only files the user supplied and approved for this task, then submit once with a stable client_request_id and poll the returned task.
5. Report the delivered artifact and billing.net_charged_credits, review the result with the user, and ask again before any further paid stage.

Examples

Free connection check (non-billable)

python3 "$HOME/.claude/skills/ai-image-realism/scripts/mcp_client.py" verify

One approved paid call

After the user approved the cost card for this exact payload, submit once with a stable request id using the tool name from the installed SKILL.md. If the response is lost, retry only with the same client_request_id and identical arguments; never submit a replacement while the task is running.

Update

This pinned version cannot update itself: it has no code that downloads or replaces package files. update only reports what the store or tool that installed the copy offers; for a copy installed by the steps above it finds no such record and says to update the way you installed it. See the version notice under Security & Safety Notes.

To move to a newer version, repeat Steps 1 to 3 for that commit in a new review directory, show the user the file-level changes against the installed copy (for example git -C src diff --stat 0b29222 <new-commit> -- skills/ai-image-realism), and replace the directory only after approval. A version not listed in this entry has not been reviewed here.

Uninstall

dest="$HOME/.claude/skills/ai-image-realism"
python3 "$dest/scripts/uninstall.py" --dry-run
python3 "$dest/scripts/uninstall.py"

Read the JSON decision. disconnected means this was the last Beatra skill on the device: the token was revoked (when revoked is true), the files credentials.json, installation.json, host.json, skills.json, network.json, balance-holds.json, pending_authorization.json, and .authorize.lock under ~/.beatra were removed, and so were the records state.json, source.json, registration.json, and update.lock in each ~/.beatra/updates/<id>/. A directory is removed only once it is empty; the script never deletes recursively and leaves anything it does not know, such as an interrupted update's transaction/. keep_connection means another Beatra skill still uses the shared token, which stays. revoke_retry means the server refused the revocation and nothing changed; run it again shortly. The script never deletes the package directory: after confirming the path it prints with the user, delete $dest.

If anything is still under ~/.beatra after a disconnected decision, show it to the user before removing it. A token that could not be revoked expires after 15 days idle and can be revoked at once in the Beatra Console under Agents.

Best Practices

• ✅ Keep one approval per paid call, per upload set, and per install step.
• ✅ Report net charged credits from the terminal task, not the estimate.
• ❌ Do not replace the installed copy with an unreviewed version silently.
• ❌ Do not print, paste, or move the token out of ~/.beatra/credentials.json.
• ❌ Do not retry a paid call with a new request ID after an uncertain response.

Limitations

• Requires a Beatra account, network access, Python 3.10+, and prepaid credits.
• Models, prices, schemas, and availability are controlled by Beatra and its upstream model providers and can change; the service is provided as is.
• Outputs are probabilistic, not guaranteed unique or non-infringing, and need human review before publication.
• This catalog entry reviews only the pinned tree above. A newer version is a different review.

Security & Safety Notes

risk: critical is deliberate.

• Network. Every request is HTTPS and refuses redirects. Authorization uses api.beatra.ai and tool calls go to mcp.beatra.ai; an upload is a PUT of the approved file to the HTTPS address the server returns, without the bearer token. Unless a cached decision is still valid (10 minutes to 7 days), each run first asks https://api.beatra.ai/skill-route, and also https://api.beatra.cn/skill-route when the first is slow or answers cn, which network to use. These probes carry no credential or package identity. When the answer is cn, authorization and tool calls go to api.beatra.cn and mcp.beatra.cn with the same bearer token, and the version notice reads from www.beatra.cn; Beatra serves these .cn hosts from mainland China. python3 "$dest/scripts/mcp_client.py" network --use ai pins the .ai hosts and stops the probes; after that no request, the version-notice read included, retries on the other network.
• Version notice, no self-update. This version has no code that downloads or replaces package files and writes nothing inside the install directory. Before verify, tools, upload, or call, at most once every 24 hours per install path, it records the check time and looks, read-only, for records another installer left beside the package (ClawHub origin.json, SkillHub or skills CLI lock entries, gh skill frontmatter). A copy installed by the steps above normally has none and makes no request. When one is found, it reads https://beatra.ai/skills/ai-image-realism/sources.json (no credential, 3-second timeout, 64 KiB cap) and, if that installer offers a newer version, prints one line to stderr with the installer's own update command. It never runs the command.
• Uploads and third parties. Prompts and uploaded media are sent to Beatra and forwarded to the third-party model provider executing the task. Beatra runs the service outside mainland China; on the cn route (see Network) requests reach it through Beatra's hosts in mainland China. See the privacy policy.
• Billing. Paid tools consume prepaid credits. Credits for tasks that fail for reasons attributable to Beatra or the upstream model are returned automatically; otherwise purchases are non-refundable, and actual usage can exceed the estimate and leave a negative balance. See the terms.
• Credentials. authorize.py runs an OAuth device flow, opens the browser on the approval page, and stores one bearer token in ~/.beatra/credentials.json (directory 0700, file 0600). The token never goes into argv, environment variables, or output. It carries full Beatra scope, including wallet:spend, has a sliding 15-day idle lifetime, and is shared by every Beatra skill on the device. While the user has not yet selected Allow, the pending device code is kept in ~/.beatra/pending_authorization.json (0600) so a rerun finishes the same approval instead of opening a new one. When verify, tools, upload, or call finds no working token, the client makes one check of that saved approval and stores the token if the user has already selected Allow; it never starts a new authorization or opens a browser.
• Local state. ~/.beatra/ also holds installation.json (random installation reference), host.json (agent platform and hostname), skills.json (installed Beatra skill paths), network.json (route decision, with a country code when the route answer includes one), balance-holds.json (after an insufficient-credit refusal, that tool is answered locally for up to 30 minutes; call --recheck-balance sends one call), a short-lived .authorize.lock, and, per install path, updates/<id>/state.json (last version check), source.json (install source), and registration.json (last registration). All of these files are 0600.
• Telemetry. Authorization sends the hostname as the device name, the package slug and version, the detected agent platform (for example claude-code, from environment variables), and the installation reference. After connecting, at most once a day unless the version, platform, route, or install source changes, the client makes a non-billable beatra.installations.register call with those package and platform fields, the release channel, the network route, the install source (github for this tree), and coarse runtime facts: OS and OS version, CPU architecture, Python version, locale, and UTC offset. Every tool call adds source_package_slug and source_platform. There is no opt-out for these fields.
• Retention. Account data is kept for the life of the account. Task records, artifacts, and billing ledgers are retained after account closure for audit and tax purposes.
• Content rights. Users keep rights in their inputs and receive Beatra's rights in outputs; they must hold rights to uploaded media and must not create deceptive impersonations.

Additional Resources

• Source tree at the pinned commit
• Product page
• Terms and privacy policy

Compare the result with the source at full size for identity, text, logo geometry, product shape and any new artifact before claiming the defect is fixed, and report visible drift instead of hiding it.