SKILLEMALL.ai

AC cogdx-bias-scan

Detect systematic inference-level biases in an AI agent's reasoning via Cerebratech CogDx API ($0.10 per call, credits accepted). Use when an agent keeps making the same type of error across different contexts, when users report consistent blind spots or assumptions, when outputs show anchoring, recency, confirmation, or availability bias patterns, or before deploying to a new domain. Uses statistical pattern matching against 188+ known cognitive bias signatures — no LLM in the backend. Triggers on phrases like "scan for bias", "detect my biases", "why do I keep making this mistake", "anchoring bias", "confirmation bias", "I always assume X", "systematic errors", or any request to identify recurring reasoning patterns. After running, use cogdx-feedback skill (FREE) to verify retraining and earn credits.

ClawHub Agent Skills author: Dr Amanda Kavner v1.0.1 MIT-0 4 files body ≈ 795 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice

AnalyzerAI and agentsInfrastructureData and analyticstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
97/100
safety, quality, tests
Safety 60%
100
Quality 40%
93
Run on models
none yet
Process rating
C
58/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
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: 4. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "repository"

    Process rating: all ten parameters 58/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 1 mutating operations with no state check
    • 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. 17 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 795 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)
    • +3Description length 814: 120–800 characters recommended
    • +2Single-language instructions
    • +5Description quotes 7 example trigger phrases
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 17 items
    • +3Output format is stated explicitly
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (2 of 2)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.

    External checks

    ClawHub: clean
    This is an instruction-only paid API integration that openly sends selected prompt and response samples to Cerebratech for bias analysis.
    LLM: benign (high) · VirusTotal: · 29 May 2026