Install
$ agentstack add skill-spritecook-skills-spritecook-upload-assets ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
SpriteCook Upload Assets
Use this skill when a local image file should become a reusable SpriteCook asset_id.
Pair it with spritecook-workflow-essentials for credential safety, manifests, and downstream asset reuse.
Preferred Flow
- Inspect the local file path without printing file bytes.
- Determine
file_name, MIMEcontent_type, optionalsize_bytes, and whetherpixelshould be true. - Call
create_asset_upload(file_name=..., content_type=..., pixel=..., size_bytes=...). - Upload the file bytes to the returned
upload_urlwith HTTPPUTand the returned headers. - Call
finalize_asset_upload(upload_token=...). - Use the returned
asset_idin the next SpriteCook tool.
The upload URL and token are short-lived secrets. Do not print them in user-facing prose, save them to project files, or include them in manifests.
PowerShell Pattern
On Windows, upload without printing bytes:
Invoke-WebRequest -Method Put -Uri $uploadUrl -InFile $path -ContentType $contentType | Out-Null
Use variables for $uploadUrl, $path, and $contentType; do not echo them if they include the upload token.
When To Use Inline Import
Use import_asset(image=...) only when the image is already a small data URL or base64 value that can be passed directly without logging it.
Do not use shell commands that print base64 to the terminal. If encoding is necessary, store the value in memory or a private variable and pass it directly to the MCP tool.
Reusing Uploaded Assets
- Use
reference_asset_idwhen the uploaded asset is one specific source or context image. - Use
edit_asset_idonly when the uploaded asset is the one image being directly modified. - Use
style_asset_idsongenerate_game_artwhen uploaded assets are ambient style guides; pass up to 10 IDs. - Use
style_asset_idongenerate_tilesetfor one tileset style guide image. - Use
asset_idonanimate_game_artwhen the uploaded asset is the source to animate.
Save the returned asset_id and a local file hash in the project manifest when the workspace is writable.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: SpriteCook
- Source: SpriteCook/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.