AC apple-photos-cleaner
Analyze, clean up, and organize Apple Photos libraries. Find and report junk photos (screenshots, low-quality, burst leftovers, duplicates), analyze storage usage, generate photo timeline recaps, plan smart exports, analyze Live Photos, check iCloud sync, audit shared libraries, detect similar photos, curate seasonal highlights, and score face quality. All analysis operations are READ-ONLY on the database (safe). macOS only. Requires Python 3.9+ (stdlib only) and access to the Apple Photos SQLite database. Trigger on: Photos cleanup, photo storage, duplicate photos, junk photos, screenshot cleanup, Photos analysis, photo timeline, photo export, Photos library stats, burst cleanup, storage hogs, photo organization, Live Photos, iCloud sync, shared library, similar photos, seasonal highlights, face quality, portraits.
Analyze, clean up, and organize Apple Photos libraries.
As a process C 61/100 · Has gaps — weak spots: execution cost, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 25. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9769 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 40Execution cost. Instruction body is 9769 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Steps. 267 steps, 6 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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 827: 120–800 characters recommended
- -31 of 21 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 52 headings
- +3Step-by-step instructions: 267 items
- +3Output format is stated explicitly
- +4Has examples (45 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.