AC adaptive-brain
Adaptive self-improving agent brain that learns, evolves, and optimizes itself over time. Use when you need: performance tracking, error pattern detection, automatic behavior adaptation, skill evolution, confidence-weighted learning, rollback on bad changes, metrics dashboards, proactive failure prediction, or cross-session memory synthesis. Triggers on "self improve", "learn from mistakes", "track performance", "evolve behavior", "adaptive agent", "improve yourself", "what did you learn", "learning dashboard", or when errors/corrections are detected.
As a process C 59/100 · Has gaps — 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Adaptive self-improving agent brain that learns, evolves, and opti… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (adaptive-brain) differs from the folder (eternal-adaptive-brain)
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 22 steps
- 100Execution cost. Instruction body is 1505 tokens
- 100Progress reporting. Reports progress
- low 11 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -228 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 557: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (11 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.