AC asi-proxy-phase-skill
Diagnose, explain, and improve an evidence-gated, protocol-relative ASI-proxy readiness regime using K. Takahashi's pinned papers and public repositories. Use for observable-only or no-meta agent improvement, verification bottlenecks, provenance and memory failures, certified reusable capability, finite-resource phase diagnostics, paper-to-implementation lineage, multi-repository intervention planning, or iterative implementation and evaluation. Do not use for unrelated generic coding or to claim that real ASI or a scientific phase transition has been achieved.
Diagnose, explain, and improve an evidence-gated, protocol-relative ASI-proxy readiness regime using K.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 26. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 57 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2063 tokens
- low No test case covers injection arriving through data
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 567: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 6 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.