AB Self-Improving Agent
Local skill for capturing learnings, errors, corrections, and patterns to enable continuous agent improvement. Processes events locally in your OpenClaw agent without external API calls. Returns structured insights, suggested rules, and batch summaries. Provided by Claw0x.
As a process B 65/100 · Nearly there — weak spots: when it triggers, consistency, running it twice
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: 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 65/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (Self-Improving Agent) differs from the folder (self-improving-agent-pro)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4217 tokens
- 100Steps. 72 steps
- 100Failures and branches. 2 branches, has a failure section
- 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 273: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.
External checks
ClawHub: suspicious
The skill is local and purpose-aligned, but it encourages automatically turning raw errors and corrections into persistent agent rules without enough redaction or approval controls.
LLM: suspicious (high) · VirusTotal: · 29 May 2026