SKILLEMALL.ai
GitHub ↗ RU Sign in

BD linux-disk-space-triage

Linux磁盘告警清理与根分区扩容分析。Use when 磁盘告警、需腾空间、问如何扩大根分区。

ClawHub Hermes author: peterliu-512 v1.0.1 MIT-0 5 files body ≈ 869 tokens Open the sourceclawhub.ai↗ analyzed 15 h ago

Linux磁盘告警清理与根分区扩容分析。Use when 磁盘告警、需腾空间、问如何扩大根分区。

As a process D 40/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureDockerInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
78/100
safety, quality, tests
Safety 60%
72
Quality 40%
86
Run on models
none yet
Process rating
D
40/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

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

    For the model run — optional
    • 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 · 8

    ✓ No critical or high findings

    Medium and low: 8
    • medium Dangerous commands cmd-privilege references/data-dir-migration-softlink-pattern.md:21
      Privilege escalation / world-writable permissions
      sudo mkdir -p /data/models && sudo chown <user>:<user> /data/models
    • medium Dangerous commands cmd-privilege references/data-dir-migration-softlink-pattern.md:55
      Privilege escalation / world-writable permissions
      sudo mkdir -p /data/cache/{pip,uv,npm} && sudo chown -R <user>:<user> /data/cache
    • medium Dangerous commands cmd-shell-rc references/data-dir-migration-softlink-pattern.md:59
      Writes to a shell startup file
      echo 'export UV_CACHE_DIR=/data/cache/uv' >> ~/.bashrc
    • medium Dangerous commands cmd-privilege SKILL.md:47
      Privilege escalation / world-writable permissions
      sudo rm -f /var/log/messages-*       # 旧轮转文件（保留当前 messages，单份可 400-600M）
    • medium Dangerous commands cmd-privilege SKILL.md:51
      Privilege escalation / world-writable permissions
      echo -e "[Journal]\nSystemMaxUse=300M" | sudo tee /etc/systemd/journald.conf.d/size.conf
    • low Dangerous commands cmd-cron-mention references/data-dir-migration-softlink-pattern.md:16
      Mentions editing / listing crontab
      crontab -l | grep -i models                             # cron 引用
    • low Dangerous commands cmd-privilege references/data-dir-migration-softlink-pattern.md:68
      Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
      ——必须先 `sudo mkdir -p` + `sudo chown <user>:<user>` 再同步；建好的目录归用户所有，
      quoted
    • low Dangerous commands cmd-privilege references/disk-cleanup-expansion-case-202608.md:10
      Privilege escalation / world-writable permissions (documentation table row)
      | 系统日志旧轮转 | 2.0G | `sudo rm -f /var/log/messages-*`（4 份 465-575M） |
      table

    Files scanned: 5. 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 40/100

    • 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
    • 0Consistency. Frontmatter name (linux-disk-space-triage) differs from the folder (linux-disk-triage)
    • 20When it triggers. No condition that starts the skill
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 100Steps. 25 steps
    • 100Execution cost. Instruction body is 869 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)
    • +3Description length 48: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 25 items
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (2 of 3)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

    External checks

    ClawHub: suspicious
    This disk-cleanup skill is purpose-aligned but includes powerful deletion and system-configuration commands that need careful human review before use.
    LLM: suspicious (high) · 15 Sept 2026