SKILLEMALL.ai

AB investment-risk-scanner

Investment risk scanner using Buffett + Porter's Five Forces framework. Triggers when users ask "analyze XXX's risk", "is this project legit", "can I buy this stock", "Buffett framework check", "is this business model sustainable", "Ponzi", "subsidy dependent", "loss making", "valuation". 5-layer Buffett framework + Porter's Five Forces as complementary check. Built-in cases: Qutoutiao, StepN, WeWork, Quibi, Tesla, NVDA, PLTR, COIN, AMC, RIVN, BYD, Geely. Key addition: Supply Chain Finance risks (迪链-type tools), Hidden liabilities, OCF quality analysis.

ClawHub Agent Skills author: Bear Xiong v2.1.0 MIT-0 2 files body ≈ 3 624 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

AnalyzerInfrastructureFinancetype and topics are labelled automatically from the skill text
JSON
Technical rating
A
96/100
safety, quality, tests
Safety 60%
100
Quality 40%
90
Run on models
none yet
Process rating
B
71/100
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 71/100

    • 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
    • 55Failures and branches. 1 branches
    • 60Result and completion. Output format stated, no completion criterion
    • 70When it triggers. States when to use, but not when not to
    • 100Tools and files. No external tools needed
    • 100Steps. 7 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3624 tokens
    • low 13 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)
    • -2113 emoji in the instructions: noise for the model
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 8 example trigger phrases
    • +3Description length 559: enough signal without eating the budget
    • +4Structure: 35 headings
    • +3Step-by-step instructions: 7 items
    • +3Output format is stated explicitly
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.

    External checks

    ClawHub: clean
    This is an instruction-only investment risk checklist; its main issue is that it may give broad buy/watch/avoid-style analysis, not that it accesses accounts or runs hidden code.
    LLM: benign (high) · VirusTotal: · 29 May 2026