AC skill-guardian
Safely manage your AI skill collection with trust scoring, security vetting, delayed auto-updates, and pending periods for new skills. Use when adding new skills, monitoring skill security, tracking versions, or preventing risky automatic updates. Features intelligent update rules (high-trust skills update immediately, others wait 10 days) and 5-10 day pending period for new skill additions. Perfect for users who want a curated, secure skill library without surprises.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-cron-mentionreferences/cron-setup.md:11Mentions editing / listing crontab (documentation of a security skill)crontab -e
security skill -
low Dangerous commands
cmd-cron-mentionSKILL.md:90Mentions editing / listing crontab (documentation of a security skill)crontab -e
security skill
Files scanned: 13. 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 51/100
- 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. 1 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1072 tokens
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
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 472: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.