BC agent-mistake-patterns
AI agent mistake pattern vault and self-correction discipline: memory-recall failures (notes exist but not consulted before acting), missing workflow steps, edit-anchor mistakes, inefficient debugging paths. Teaches the pre-action recall habit (grep your own notes first), mistake archiving, root-cause classification, and fix-verification loops. AI智能体犯错模式库与自我纠错纪律：记忆检索失败（笔记在、动手前没翻）、流程步骤缺失、编辑锚点错误、低效排查路径。强调动手前先检索自己的笔记、错误归档、根因分类与修复验证闭环。Keywords: agent mistakes, self-correction, memory recall, note retrieval, error patterns, root cause, 智能体纠错, 犯错模式, 记忆检索, 笔记纪律, 自我改进, error archive, 防错机制
AI agent mistake pattern vault and self-correction discipline: memory-recall failures (notes exist but not consulted before acting), missing workflow steps…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "created" - note
frontmatter-keyunknown frontmatter key "updated" - note
frontmatter-keyunknown frontmatter key "lang"
Process rating: all ten parameters 53/100
- 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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 41 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 740 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 587: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.