FC my-computer
Desktop automation agent that uses CLI commands, application automation, and scripting to work directly with the user's local machine. Use this skill whenever the user asks to organize files or photos, batch rename or process files, automate repetitive local tasks, build desktop applications with local dev tools, control or script local applications (Finder, browsers, IDE, etc.), utilize local compute resources (GPU, idle machines), combine local file operations with cloud services, set up recurring scheduled tasks, perform system diagnostics or maintenance, clean up disk space, manage processes, generate reports from local data, or any task that involves automating work on the user's own computer. Also trigger when the user mentions things like "organize my files", "clean up my desktop", "sort my photos", "rename these invoices", "build me an app", "use my GPU", "automate this", "schedule a task", "check my disk space", "what's using my CPU", or describes any tedious local task they want automated — even if they don't explicitly say "automation".
As a process C 56/100 · Has gaps — weak spots: result and completion, 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.
- 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 · 6
-
high Dangerous commands
cmd-persistencereferences/platform-guide.md:220Persistence mechanism (cron / launchd / scheduled task / autorun registry)schtasks /create /tn "DailyCleanup" /tr "powershell.exe -File C:\scripts\cleanup.ps1" /sc daily /st 09:00
-
high Dangerous commands
cmd-persistenceSKILL.md:301Persistence mechanism (cron / launchd / scheduled task / autorun registry)# Create a plist in ~/Library/LaunchAgents/
-
high Dangerous commands
cmd-persistenceSKILL.md:302Persistence mechanism (cron / launchd / scheduled task / autorun registry)cat > ~/Library/LaunchAgents/com.user.cleanup-downloads.plist << 'EOF'
-
high Dangerous commands
cmd-persistenceSKILL.md:326Persistence mechanism (cron / launchd / scheduled task / autorun registry)launchctl load ~/Library/LaunchAgents/com.user.cleanup-downloads.plist
-
high Dangerous commands
cmd-persistenceSKILL.md:332Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "0 9 * * * /home/user/scripts/cleanup.sh") | crontab -
Medium and low: 1
-
low Dangerous commands
cmd-cron-mentionSKILL.md:332Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "0 9 * * * /home/user/scripts/cleanup.sh") | crontab -
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1063 chars, limit 1024
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 17 mutating operations with no state check
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4399 tokens
- 100Steps. 90 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1063: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Structure: 24 headings
- +3Step-by-step instructions: 90 items
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.