DF agentdrive-backup
龙虾（AI Agent）把自身根目录备份到 360AgentDrive 云端的完整操作手册。当龙虾需要执行以下任意操作时，必须加载此 Skill：备份根目录、开启或恢复自动备份监听（claw-auto-backup）、执行首轮备份（claw-backup）、安装或升级 agentdrive CLI、获取 API Key、登录 AgentDrive（微信扫码或手机号）。覆盖全流程：登录鉴权 → CLI 安装升级 → 根目录自动识别（多候选特征打分）→ 首轮备份 → 自动监听 → 保活 crontab；备份路径规范为 /<龙虾名称>/。
As a process F 46/100 · Will not run — References files that are not bundled: $QR_DATA_URL, qr_image_data_url的值, src/www/backup_skill.md:596
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.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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 · 4
-
high Dangerous commands
cmd-persistenceSKILL.md:633Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null; echo "0 * * * * /tmp/agentdrive_auto_backup_guard.sh >/dev/null 2>&1") | crontab -
-
high Dangerous commands
cmd-persistenceSKILL.md:945Persistence mechanism (cron / launchd / scheduled task / autorun registry)(crontab -l 2>/dev/null | grep -v 'agentdrive_auto_backup_guard.sh'; echo "0 * * * * /tmp/agentdrive_auto_backup_guard.sh >/dev/null 2>&1") | crontab -
Medium and low: 2
-
low Dangerous commands
cmd-cron-mentionSKILL.md:633Mentions editing / listing crontab(crontab -l 2>/dev/null; echo "0 * * * * /tmp/agentdrive_auto_backup_guard.sh >/dev/null 2>&1") | crontab -
-
low Dangerous commands
cmd-cron-mentionSKILL.md:945Mentions editing / listing crontab(crontab -l 2>/dev/null | grep -v 'agentdrive_auto_backup_guard.sh'; echo "0 * * * * /tmp/agentdrive_auto_backup_guard.sh >/dev/null 2>&1") | crontab -
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6495 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: $QR_DATA_URL - warning
missing-refreference to a missing file: qr_image_data_url的值 - warning
missing-refreference to a missing file: src/www/backup_skill.md:596 - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 46/100
- 0Tools and files. 3 referenced file(s) missing: $QR_DATA_URL, qr_image_data_url的值, src/www/backup_skill.md:596
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 6495 tokens
- 100Steps. 119 steps
- 100Failures and branches. 19 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 269: enough signal without eating the budget
- +4Structure: 59 headings
- +3Step-by-step instructions: 119 items
- +4Has examples (25 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.