AB claw-self-improving-plus
Turn raw mistakes, corrections, discoveries, and repeated decisions into structured learnings and promotion candidates. Use when the user wants a conservative self-improvement workflow that captures lessons, scores reuse value, deduplicates similar learnings, drafts anchored candidate patches for SOUL.md, AGENTS.md, TOOLS.md, or MEMORY.md, reviews them through an approval step, and keeps human control before any long-term file edits.
As a process B 73/100 · Nearly there — weak spots: 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 · 0
✓ No critical or high findings
Files scanned: 22. 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 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) 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
- 100Steps. 81 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1307 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 10 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 437: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 81 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 5)
- +3All 15 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.