AD self-improvement-llm
Autonomous memory and self-learning system for AI agents. Continuously collects experience, manages memory (daily logs, user preferences, knowledge extraction), builds knowledge graphs connecting events→lessons→principles, extracts principles, auto-adjusts behavior, and verifies improvements. Proposes actionable changes for user review before applying. Use when: (1) Agent needs to learn from past sessions, (2) User asks "improve yourself" or "learn from this", (3) Periodic self-evaluation is needed, (4) Agent needs to auto-correct recurring mistakes, (5) Updating AGENTS.md/SOUL.md/MEMORY.md/TOOLS.md based on experience, (6) Extracting universal principles from episodic experiences, (7) Processing user feedback to permanently adapt behavior, (8) Managing daily memory logs, user preferences, or knowledge retention.
Autonomous memory and self-learning system for AI agents.
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 13. 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: Autonomous memory and self-learning system for AI agents. Continuo… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, git, python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4370 tokens
- 85Steps. 103 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 23 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)
- +3Description length 824: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Structure: 52 headings
- +3Step-by-step instructions: 103 items
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.