BC photo-screener
AI-powered photo pre-screening using MobileCLIP2-S0 model. 18x faster than ViT-L/14 with 80% selection consistency (Top-10 overlap 8/10). Use when the user wants to: - Filter/screen a large batch of photos before sending to LLM - Score photos by aesthetic quality - Remove near-duplicate photos (burst shots) - Classify photos by scene type - Prepare photos for multimodal LLM processing Triggers: User mentions filtering photos, screening images, aesthetic scoring, removing duplicates, classifying scenes, or preparing photos for LLM. Auto-skipped when photo count ≤ user's requested output count OR ≤ 20 (batch_size). Only triggered when photo count exceeds both thresholds. Dependencies: Python: torch, open-clip-torch, pillow, numpy, pillow-heif (optional, for HEIC/HEIF) Model: MobileCLIP2-S0 (~300MB, downloaded on demand with user confirmation) Check: bash scripts/setup_deps.sh Model Download: The model is NOT pre-downloaded. On first run: - Interactive mode: prompts user for confirmation - Non-interactive mode: exits with manual download instructions - Uses HuggingFace mirror (hf-mirror.com) for China acceleration - Add --auto-download to skip confirmation
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1192 chars, limit 1024
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1315 tokens
- 100Running it twice. Mutating operations check current state
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1191: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (6 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.