CB video-production
Complete A/B video pipeline — storyboard, Veo 3 batch generation, browser preview with feedback loop, and ffmpeg assembly into final videos. Use when creating multi-scene videos, running A/B tests on hooks/CTAs, previewing clips before stitching, or assembling a final cut from approved clips.
As a process B 71/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
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.
- 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 · 5
-
high Dangerous commands
cmd-persistenceSKILL.md:144Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v quota_watcher; \
-
high Dangerous commands
cmd-persistenceSKILL.md:145Persistence mechanism (cron / launchd / scheduled task / autorun registry)echo "*/30 * * * * /path/to/quota_watcher.sh >> /tmp/quota_watcher.log 2>&1") | crontab -
Medium and low: 3
-
medium Dangerous commands
cmd-persistencescripts/quota_watcher.sh:37Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)crontab -l | grep -v "quota_watcher" | crontab -
detector -
low Dangerous commands
cmd-cron-mentionscripts/quota_watcher.sh:37Mentions editing / listing crontabcrontab -l | grep -v "quota_watcher" | crontab -
-
low Dangerous commands
cmd-cron-mentionSKILL.md:144Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v quota_watcher; \
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 29 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2431 tokens
- 100Progress reporting. Reports progress
- low 15 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)
- -44 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 293: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 29 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.