experience-recorder
Skill2 starsChanged 2 months agoApache-2.0View on GitHub
在客户项目分析、正式申报材料、复杂分析、重要规则变更、基础设施迁移或用户纠正完成后自动使用。从任务中提取可复用经验、失败原因和质量规则,执行四问复盘并形成候选经验记录。
In this repository47 other files it gives its agents.
- agriculture-and-rural-projectsSkill
- application-version-diffSkill
- application-writingSkill
- checking-patdocx-cn-single-agentSkill
- consistency-checkSkill
- deep-clarificationSkill
- digitalization-projectsSkill
- enterprise-panorama-analysisSkill
- enterprise-profileSkill
- evidence-ledgerSkill
- evolution-governanceSkill
- financial-verificationSkill
- graphifySkill
- green-development-projectsSkill
- high-tech-enterprise-application-draftingSkill
- high-tech-enterprise-preassessmentSkill
- humanizer-zhSkill
- industrialization-projectsSkill
- industry-chain-foundation-matcherSkill
- industry-positioningSkill
- intellectual-property-projectsSkill
- investment-subsidy-projectsSkill
- ip-assessmentSkill
- legal-regulationsSkill
- manufacturing-tax-risk-analysisSkill
- patent-routerSkill
- peer-benchmarkingSkill
- policy-retrievalSkill
- project-application-assistantSkill
- project-deliverable-archiveSkill
- project-feasibilitySkill
- project-matchingSkill
- project-memorySkill
- project-rule-managerSkill
- project-task-routerSkill
- quality-brand-projectsSkill
- regional-special-projectsSkill
- skill-authoringSkill
- skill-curatorSkill
- skill-evolutionSkill
- sme-development-projectsSkill
- sme-score-preassessmentSkill
- standard-draftingSkill
- talent-projectsSkill
- technology-innovation-projectsSkill
- trade-and-open-economy-projectsSkill
- web-task-operatorSkill
The file
Files
经验记录
只记录可泛化方法、验证依据和适用边界,不直接修改技能。禁止写入凭据、客户身份、敏感原文和未经验证的政策结论。
先区分“个人习惯”和“通用纠正”:个人习惯写入宿主偏好或项目配置,不进入纠正JSONL;通用纠正才进入后续聚合与进化。不得通过直接修改 SKILL.md 保存用户习惯。
强制四问
对适用任务,在最终对话中结合当前成果实际回答:
- 眼下最没有把握的事情是什么?
- 最大的遗漏是什么,还有什么没有意识到?
- 最有价值的创新改进是什么?客户产品任务改为最值得增加的行业领先功能或创新点。
- 哪些不同做法可以提高本次任务效率?
不得只把问题抛给用户。某项确实不适用时写明“不适用”及原因。四问不得进入正式申报书、企业报告和其他客户交付正文。
将复盘中的可泛化内容交给 skill-curator 检查重复与冲突;需要优化时交给 skill-evolution 生成候选版本,并由 evolution-governance 控制审批、发布和回滚。
纠正信号
用户纠正、回归失败或经复核确认的质量问题,使用 scripts/record_correction.py 写入本地JSONL。每条记录必须包含技能、稳定规则键、任务标识、脱敏摘要和核验状态;相同任务、技能、规则和摘要自动去重。规则键用于聚合同一问题,不得写客户名称、原文、凭据或专利及财务敏感数据。
python3 scripts/record_correction.py \
--skill <技能名> --rule-key <稳定规则键> --task-id <脱敏任务标识> \
--summary <脱敏问题摘要> --verified单条记录只作为证据,不触发GEPA。由 skill-curator 达到跨任务阈值后统一形成批量候选。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

