AC rdk-x5-system
修改和管理 RDK X5 系统配置：查看系统版本/硬件信息/系统日志、rdk-backup 一键备份与恢复、apt OTA 升级、miniboot 固件更新、CPU/BPU 频率调节与温度阈值设置、config.txt 配置修改、实时内核切换、systemd 开机自启动、存储扩容。Use when the user wants to CHANGE system settings, backup/restore, upgrade firmware, adjust CPU/BPU frequency, configure autostart services, switch RT kernel, expand storage, check system version, or view system logs. For read-only hardware status queries (CPU/BPU/温度/内存/磁盘 实时查看) → use rdk-x5-monitor instead. Do NOT use for network config (use rdk-x5-network), camera (use rdk-x5-camera), AI inference (use rdk-x5-ai-detect), NAS setup, Docker/容器, or custom application development.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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
-
medium Dangerous commands
cmd-privilegeSKILL.md:66Privilege escalation / world-writable permissionsecho performance | sudo tee /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
-
low Dangerous commands
cmd-background-processSKILL.md:105Starts a background / autostarted processsudo systemctl enable my-app.service
Files scanned: 2. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50Steps. 2 steps
- 100Tools and files. No external tools needed
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 585 tokens
- 100Running it twice. No mutating operations
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
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 624: enough signal without eating the budget
- +4Structure: 14 headings
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.