SKILLEMALL.ai

AB linkfox-skill-evaluator

Evaluate whether a skill is both safe to run and effective at its job. Use when the user wants to test, benchmark, grade, critique, audit, vet, or compare versions of a skill — phrases like "这个 skill 好不好"、"evaluate this skill"、"vet this skill"、"新版本比旧版本好吗"、"帮我测测这个 skill"、"这个 skill 安全吗"、"skill 有没有效果"、"skill 质量如何". Trigger whenever a user has a skill in hand and wants an objective read — on effectiveness, on safety, or both; the evaluation always covers both dimensions regardless of which the user asks about first. Works on any skill regardless of domain (writing, code generation, data extraction, workflows, domain-specialized skills, third-party community skills).

ClawHub Agent Skills author: lienong1122334 v1.0.0 MIT-0 9 files body ≈ 4 088 tokens Open the sourceclawhub.ai analyzed 4 d ago

Evaluate whether a skill is both safe to run and effective at its job.

As a process B 67/100 · Nearly there — weak spots: failures and branches, progress reporting

AnalyzerAWSAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
97/100
safety, quality, tests
Safety 60%
100
Quality 40%
92
Run on models
none yet
Process rating
B
67/100
Nearly there
Failures and branches w 10
0
Progress reporting w 2
0
Tools and files w 18
60
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

    Files scanned: 8. 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 67/100

    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 60Tools and files. Uses tools (bash, web, python, node) 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
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4088 tokens
    • 100Steps. 113 steps
    • 100Consistency. Name and required fields are in place
    • 100Running it twice. No mutating operations
    • low 19 top-level sections: this looks like several domains in one skill

    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)
    • -5TODO / placeholder text left in the skill
    • -252 emoji in the instructions: noise for the model
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 8 example trigger phrases
    • +3Description length 670: enough signal without eating the budget
    • +4Structure: 40 headings
    • +3Step-by-step instructions: 113 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: clean
    This is a skill-review workflow that is mostly coherent and proportionate, with some stale backup material and broad review claims users should treat as guidance rather than a guarantee.
    LLM: benign (high) · VirusTotal: · 14 Aug 2026