AB self-improving-agent
Automatically capture corrections, failures, and reusable discoveries into `.learnings/` files using signal-based filtering. Triggers when the user corrects the agent, a tool/command fails in a reusable way, or a better approach is discovered. Also handles periodic retention scoring and promotion of proven patterns into SOUL.md, AGENTS.md, or TOOLS.md.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
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: 6. 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 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (self-improving-agent) differs from the folder (auto-improving-agent)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 808 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 354: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.