BC photo-toolkit
Photography utility toolkit: convert RAW/JPG/HEIC to thumbnails, find photos by shooting date, generate layout previews, deflicker timelapse frames, and assemble video. Supports all major camera brands: Nikon (NEF), Canon (CR2/CR3), Sony (ARW), Fujifilm (RAF), Olympus (ORF), Panasonic (RW2), Pentax (PEF), Samsung (SRW), Leica (DNG), Adobe (DNG), Hasselblad (3FR), Phase One (IIQ), Sigma (X3F), plus standard JPEG (.jpg/.jpeg) and Apple HEIC/HEIF (.heic/.heif). Use when the user wants to: - Convert RAW/JPG/HEIC files to JPG format (single file or batch) - Generate thumbnails / previews from camera photos - Batch process photo files in a directory (with optional recursive search) - Find / filter photos by shooting date - List all photo files grouped by shooting date - Generate layout preview grid from graded photos - Remove flicker from timelapse frame sequences (deflicker) - Assemble sequential JPG frames into MP4 video Triggers: User mentions converting RAW/NEF/CR2/ARW/RAF/JPG/HEIC to JPG, generating thumbnails, batch processing camera photos, finding photos by date, deflicker, timelapse video assembly. Dependencies: System: libraw (RedHat: dnf install LibRaw-devel / Debian: apt-get install libraw-dev) Python: rawpy, pillow, numpy, pillow-heif (optional, for HEIC/HEIF) Check: bash scripts/setup_deps.sh
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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1331 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
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 4 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1957 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 1330: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -33 of 7 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 4 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.