AB Capability Evolver
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvement proposals. Use when the user or agent asks to analyze logs, diagnose failures, improve agent reliability, generate evolution proposals, or assess system health. Supports analyze, evolve, and status actions.
Meta-skill for AI agent self-improvement.
As a process B 66/100 · Nearly there — weak spots: consistency, running it twice
The same skill appears in 3 more places: ClawHub, ClawHub, ClawHub
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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 66/100
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (Capability Evolver) differs from the folder (capability-evolver-pro)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4565 tokens
- 100Steps. 68 steps
- 100Progress reporting. Reports progress
- low 16 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 367: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 68 items
- +3Output format is stated explicitly
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.