摄影照片评分/Photo Scorer
v1.4.10给你的照片打分、评价反馈、给出改进建议或美学分析 / Aesthetic photo scorer with detailed analysis
⭐ 0· 96·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description (photo aesthetic scoring) aligns with the included scripts (Improved Aesthetic Predictor + NIMA), the config, and requirements. The heavy ML dependencies (PyTorch, TensorFlow) and model weight files are expected for local model inference.
Instruction Scope
SKILL.md instructs the agent to run the two scoring scripts, compute a dynamic weighted score, and generate multi-level textual evaluations. It also requires ALWAYS generating a 10-level (detailed ~4000-word) evaluation in the background and saving it for later retrieval. The code provides functions that produce reports but does not implement an explicit background-generation-and-save mechanism or specify storage locations — this is a behavioral/instruction vs. implementation mismatch and a privacy/retention consideration (saving user photos/evaluations). No instructions or code attempt to read unrelated system credentials or make external network calls.
Install Mechanism
No install spec in the registry (instruction-only), but the package contains code and a requirements.txt. README recommends cloning external model repositories and downloading weights from GitHub (expected for ML model setups). The code forces transformers to offline mode and uses local_files_only for CLIP; there are no hidden or obscure download URLs in the code. Installing will require pulling large ML packages and model weights from known sources (GitHub), which is normal but heavyweight.
Credentials
The skill does not request secrets or credentials. Optional environment variables exist to override model directories (AESTHETIC_SCORER_MODEL_DIR and AESTHETIC_SCORER_NIMA_DIR) which are proportionate to a local-model skill. The code does include a deprecated api_key parameter (not used), which is harmless but unnecessary.
Persistence & Privilege
The skill does not request elevated privileges and always:false. However, SKILL.md explicitly requires generating and saving detailed evaluations in the background so they can be retrieved later — that implies persistent storage of user-provided photos or evaluation text. The packaged code does not show where/how saved evaluations are persisted, so installing/using the skill may cause the agent or user to need to implement storage. This is not an escalation of system privileges but is a privacy consideration you should confirm (where are saved reports stored, retention policy, encryption, who can access them).
Assessment
This skill appears to do what it says: local aesthetic scoring using two models and AI-generated text. Before installing, consider the following:
- Disk space & dependencies: Models and ML frameworks (PyTorch/TensorFlow) are large — ensure you have enough disk space and the ability to install them. The default model paths are Windows-style (F:\...), so you will likely need to set the AESTHETIC_SCORER_MODEL_DIR and AESTHETIC_SCORER_NIMA_DIR environment variables to point where you store downloaded weights.
- Model downloads: README instructs cloning GitHub repos and downloading model weights. Those are normal for ML skills, but verify you download weights from trusted sources (the upstream project repos) and that you understand how to populate the local model cache for transformers/CLIP (the code expects local files only).
- Background saving / privacy: SKILL.md says the skill must ALWAYS generate a detailed (~4000-word) evaluation in the background and save it for instant retrieval. The code included returns reports but does not show a storage implementation or location. Decide whether you are comfortable with the skill (or your agent) persisting full evaluations or copies of images on disk — ask where they will be stored, how long they are retained, and whether they are encrypted or accessible by others.
- Offline claims: The scripts set transformers to offline and there are no explicit network calls in the code, but installing models initially requires network access. If strict offline operation is required, ensure you provision all model weights and transformers caches before running.
- Minor oddities: The predict functions accept a deprecated api_key parameter and the code uses default Windows paths; these are not malicious but indicate the package expects manual configuration.
If you want to proceed, verify model files are from trusted sources, update model directory env vars to sensible paths, and ask the skill author or provider where / how detailed evaluations and any cached artifacts will be stored and how to clear them. If you need, I can: (1) point out exactly which files to edit to change the save behavior, (2) suggest filesystem locations and cleanup scripts, or (3) produce a checklist for safe local installation.Like a lobster shell, security has layers — review code before you run it.
AIvk97b2yq62hanc8gfvj97ddk12183eyrmaestheticvk97b2yq62hanc8gfvj97ddk12183eyrmbeautyvk97b2yq62hanc8gfvj97ddk12183eyrmimagevk97b2yq62hanc8gfvj97ddk12183eyrmlatestvk97b2yq62hanc8gfvj97ddk12183eyrmphotovk97b2yq62hanc8gfvj97ddk12183eyrmscorervk97b2yq62hanc8gfvj97ddk12183eyrmvisionvk97b2yq62hanc8gfvj97ddk12183eyrm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.