AC self-improvement
错误学习闭环：记录失败和纠正 → Pattern-Key 分类 → 定期复盘 → 整合长期记忆 → 防止再犯。 Use when: (1) 命令/操作意外失败且原因值得记录, (2) 用户纠正了错误（"不对"/"Actually..."/"你搞错了"）, (3) 用户要求的能力不存在（能力缺口信号）, (4) 外部 API/工具故障且需记录规避方案, (5) 发现更好的做法可以替代当前方式, (6) 开始重大任务前回顾历史教训。 NOT for: 一次性小错误（typo/手误/用户说"没关系"的）、 功能性 bug 修复（用 problem-solving）、 skill 创建/优化（用 skill-creator）、 日常操作日志（不是每个 tool call 都要记）。
错误学习闭环：记录失败和纠正 → Pattern-Key 分类 → 定期复盘 → 整合长期记忆 → 防止再犯。 Use when: (1) 命令/操作意外失败且原因值得记录, (2) 用户纠正了错误（"不对"/"Actually..."/"你搞错了"）, (3) 用户要求的能力不存在（能力缺口信号）, (4) 外部…
As a process C 52/100 · 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: 15. 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 52/100
- 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
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (self-improvement) differs from the folder (self-improving-learner)
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 21 steps
- 100Execution cost. Instruction body is 1078 tokens
- 100Running it twice. No mutating operations
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
- +3Output format is not stated: the model decides each time
- -43 reference files, but SKILL.md never points to them: the model will not open them
- -33 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 341: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.