AC self-evolve
Self-evolution system for OpenClaw agents. Enables continuous learning through mistake tracking, experience distillation, skill improvement queues, and automated daily/weekly evolution cycles. Inspired by Hermes Agent's self-improving architecture, implemented with native OpenClaw capabilities (memory files + cron). 自我进化系统，让 OpenClaw agent 持续学习和改进。 Use when: (1) setting up self-evolution for an agent, (2) agent wants to learn from mistakes, (3) capturing lessons learned, (4) running evolution cycles, (5) improving skills based on usage, (6) "自我进化", "自我学习", "self-improve", "learn from mistakes", "evolution setup", "进化系统", "经验总结", "复盘". NOT for: memory management basics (use AGENTS.md), skill creation (use skill-creator), or one-off reminders (use cron directly).
As a process C 51/100 · Has gaps — 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: 5. 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 51/100
- 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
- 40Consistency. Frontmatter name (self-evolve) differs from the folder (agent-self-evolve)
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Execution cost. Instruction body is 1275 tokens
- 100Progress reporting. Reports progress
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 771: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.