AC unattended-task-pitfalls
Hardening playbook for AI agent unattended/scheduled tasks (cron jobs, scheduled backups, auto-reports). Real incident-derived rules on background execution, artifact verification, isolated-session context blindness, notification design, and self-healing retries. Use when building or debugging cron/scheduled/automated agent tasks, "task failed but reported success" issues, corrupted backup artifacts, or silent misjudgment in scheduled summarization/archival jobs.
Hardening playbook for AI agent unattended/scheduled tasks (cron jobs, scheduled backups, auto-reports).
As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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-background-processSKILL.md:43Starts a background / autostarted process (documentation of a security skill)- 工具调用层报 504 Gateway Timeout，**底层命令可能已经执行成功**（尤其 setsid 后台任务不受会话死亡影响）
security skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. 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 55/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 847 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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
- +1No license
- +2Single-language instructions
- +3Description length 467: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.