AC inversion-protocol
Meta-cognitive reasoning skill that makes any AI agent dramatically better at decision-making by thinking backwards before acting forward. Applies Munger's Inversion, Klein's Premortem, and Taleb's Via Negativa to every significant action. Zero dependencies, zero cost, pure reasoning enhancement. Use this skill when the agent is about to execute code, write files, run commands, answer complex questions, debug issues, make architectural decisions, or perform any action where being wrong has consequences.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Dangerous commands
cmd-privilegeexamples/general-scenarios.md:76Privilege escalation / world-writable permissions (test fixture / example file; quoted — discussed, not commanded)**Task**: User asks "Is it safe to run `chmod 777` on my web server's upload
fixturequoted -
low Dangerous commands
cmd-privilegeexamples/general-scenarios.md:81Privilege escalation / world-writable permissions (test fixture / example file)Agent explains what chmod 777 does and warns it's "generally not recommended"
fixture
Files scanned: 5. 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 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 72 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2340 tokens
- 100Progress reporting. Reports progress
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)
- +3Output format is not stated: the model decides each time
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 508: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.