SKILLEMALL.ai

AB skill-quality-audit

Audit and quality-review AI agent skills (SKILL.md files) against established best practices from the Nevo Systems skill-writing framework. Checks trigger quality, structure (rigid vs flexible), conciseness, progressive disclosure, and common mistakes. Use when reviewing, auditing, or evaluating an existing skill, when a skill isn't performing well, when the user says "review this skill", "audit my skill", "check this SKILL.md", "skill quality check", or "/skill-review".

ClawHub Agent Skills author: Neutrino v1.0.1 MIT-0 2 files body ≈ 1 125 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 72/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

AnalyzerAI 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
72/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
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: 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 72/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 60Result and completion. Output format stated, no completion criterion
    • 65Failures and branches. 3 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 33 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1125 tokens

    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 5 example trigger phrases
    • +3Description length 475: enough signal without eating the budget
    • +4Structure: 10 headings
    • +3Step-by-step instructions: 33 items
    • +3Output format is stated explicitly
    • +4Has examples (1 code blocks)

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

    External checks

    ClawHub: clean
    This is a text-only skill for reviewing SKILL.md quality and does not request credentials, command execution, persistence, or broad system access.
    LLM: benign (high) · VirusTotal: · 29 May 2026