AB skills-search
Search for Agent Skills across ClawHub, skills.sh, and SkillsMP, then rank by Health Score (downloads + stars + installs + security). Use this skill whenever the user mentions finding, searching, installing, recommending, or discovering skills — even if they say "是否有" / "帮我找" / "有没有能XXX的" / "装个XXX" / "有没有XXX相关的skill". Always search all three platforms before recommending.
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, consistency, progress reporting
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 text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Instruction override
en-ignore-previousSKILL.md:61Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)- instructions to override system prompt or exfiltrate data silently
security skill
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 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (skills-search) differs from the folder (skills-wide-search)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 19 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 806 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (8 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 374: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 19 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.