BB alibabacloud-sysom-diagnosis
Use when troubleshooting Linux server performance or stability issues — CPU saturation, high load, scheduling delay, memory pressure, OOM events, high RSS, page cache / shared memory growth, memory cgroup residue, Java heap issues, disk IO saturation or latency, packet loss, network jitter, or a server that is slow, stuck, or unstable. Performs diagnosis and surfaces recommendations; does not apply fixes automatically.
As a process B 77/100 · Nearly there — weak spots: result and completion, inputs and preconditions
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Broad scope
meta-agent-memory-dumpreferences/java/memory/case-library.mdAgent memory / workspace files bundled with the skill (7) — likely a workspace dump with personal data or tokensreferences/java/memory/case-library.md, references/java/memory/decision-tree.md, references/java/memory/glossary.md, references/java/memory/javamem-envelope-guide.md, references/java/memory/memory-gui
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read
-
medium Dangerous commands
cmd-privilegeSKILL.md:70Privilege escalation / world-writable permissions| sudo bash
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5040 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 77/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 70Execution cost. Instruction body is 5040 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 47 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +2Single-language instructions
- +3Description length 422: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (8 of 9)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.