AD ai-harness-engineering
AI驾驭工程错题本：记录OpenClaw所有被验证的错误、幻觉、缺陷、失误，形成可追溯错误台账，驱动模型自省与进化。 触发场景： (1) 用户纠正OpenClaw的回答（"不对"/"错了"/"应该是"/"Actually"等） (2) OpenClaw回答与事实不符，被用户指出 (3) 代码错误、逻辑错误被验证 (4) 漏步骤、漏信息、回答不完整被指出 (5) 格式错误、结构混乱 (6) 安全问题、越权、误导行为 (7) 用户明确要求"记录这个错误"/"添加到错题本"/"记住这个教训" (8) 用户想要但没有的功能（"能不能"/"希望你能"/"Is there a way"） (9) 用户查看错误统计/错题本/复盘报告 ⚡ 自动进化机制（核心）： - 定时自动提升：每2小时检查recurrence_count>=3的学习，自动写入workspace - 错误摘要注入：session启动时自动读取错误台账摘要，注入到上下文 - 回答前自检：每次回答前自动查询错误台账，规避已记录的错误 关键词：错题本、错误记录、自省、进化、HarnessEngineering、错误台账、复盘、功能请求、Feature Request
As a process D 44/100 · Unfinished process — 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: 19. 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")
Process rating: all ten parameters 44/100
- 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
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4034 tokens
- 100Steps. 63 steps
- 100Consistency. Name and required fields are in place
- 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
- +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
- +5Description quotes 5 example trigger phrases
- +3Description length 517: enough signal without eating the budget
- +4Structure: 60 headings
- +3Step-by-step instructions: 63 items
- +4Has examples (37 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 12 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.