DD photo-alchemy
Transform any photo into surrealist AI art. Uses Claude to write a story about your photo, then Gemini generates a reimagined version in one of 35+ visual styles. Deep Apple Photos integration — pick from albums, save back, schedule as an Apple TV screensaver.
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, failures and branches
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 3
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:36Downloads and executes remote code from an unrecognised host (pipe to shell)curl -LsSf uvx.sh/imagemine/install.sh | sh
-
high Dangerous commands
cmd-persistenceSKILL.md:126Persistence mechanism (cron / launchd / scheduled task / autorun registry)# Writes ~/Library/LaunchAgents/imagemine.plist and prints the launchctl command
-
high Dangerous commands
cmd-persistenceSKILL.md:127Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/imagemine.plist
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 260 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill
Process rating: all ten parameters 48/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 22 steps
- 100Execution cost. Instruction body is 1352 tokens
- low 11 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 260: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (9 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.