SKILLEMALL.ai

AB benchmark-filter

Benchmark filtering for Chinese creator, OPC, and one-person-business work. Use when Codex needs to judge whether a person, creator, or business is actually worth studying; separate business signal from vanity signal; decide what layer is worth copying; and recommend whether to stop at a shortlist or hand the target to $opc-case-research for deeper study.

ClawHub Agent Skills author: cellinlab v0.1.0 MIT-0 6 files body ≈ 1 080 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 69/100 · Nearly there — weak spots: inputs and preconditions, consistency, progress reporting

ProcedureInfrastructureSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
87
Run on models
none yet
Process rating
B
69/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Consistency w 8
40
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: 6. 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 69/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 40Consistency. Frontmatter name (benchmark-filter) differs from the folder (cell-benchmark-filter)
    • 60Result and completion. Output format stated, no completion criterion
    • 60Failures and branches. 2 branches
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 64 steps
    • 100Execution cost. Instruction body is 1080 tokens
    • 100Running it twice. No mutating operations

    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)
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 357: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 64 items
    • +3Output format is stated explicitly
    • +4Reference files are cited in the instructions (2 of 2)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This is an instruction-only benchmark-filtering skill with minor routing and language-default caveats, but no code execution, data access, or hidden behavior.
    LLM: benign (high) · VirusTotal: · 29 May 2026