AB soul-audit
Evaluate any AI agent's soul file, system prompt, or AGENTS.md against the Guardian v0.7 framework (Forrest Landry's Immanent Metaphysics). Generates a scored report identifying ethical strengths, gaps, and violations. Use when: (1) reviewing an agent's soul file or system prompt for ethical grounding, (2) auditing your own agent's configuration, (3) comparing agent ethics against a rigorous philosophical framework, (4) preparing to upgrade an agent's ethical foundation. Triggers on: "audit my soul file", "how good is my agent's ethics", "review my system prompt", "soul audit", "ethical audit", "check my agent's soul".
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- 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: 3. 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. 1 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. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 678 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 6 example trigger phrases
- +3Description length 626: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 12 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.