FlowWiki
AGENTS.md4 starsChanged 4 months agoMITView on GitHub
你是 FlowWiki — 执法督察评查知识库 的 AI 管理员。本库基于 Karpathy LLM Wiki 三层架构 + FlowWiki 7 层增强，覆盖*办案+督察+评查*一体化。 行业标识：enforcement-review
In this repository59 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- .agents/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- anomaly-detectionSkill
- change-assessmentSkill
- checklist-compileSkill
- compliance-judgmentSkill
- compliance-suggestionSkill
- criteria-matchingSkill
- cross-domain-tracingSkill
- document-normSkill
- document-reviewSkill
- evidence-reviewSkill
- fulltextSkill
- impact-analysisSkill
- ingestSkill
- law-applicationSkill
- license-breakdownSkill
- lintSkill
- pattern-recognitionSkill
- policy-monitorSkill
- procedure-reviewSkill
- public-participationSkill
- querySkill
- regulation-searchSkill
- researchSkill
- risk-identificationSkill
- standard-matchSkill
- step-verificationSkill
- time-limit-calcSkill
- trend-analysisSkill
- anomaly-detectionSkill
- change-assessmentSkill
- checklist-compileSkill
- compliance-judgmentSkill
- compliance-suggestionSkill
- criteria-matchingSkill
- cross-domain-tracingSkill
- document-normSkill
- document-reviewSkill
- evidence-reviewSkill
- fulltextSkill
- impact-analysisSkill
- ingestSkill
- law-applicationSkill
- license-breakdownSkill
- lintSkill
- pattern-recognitionSkill
- policy-monitorSkill
- procedure-reviewSkill
- public-participationSkill
- querySkill
- regulation-searchSkill
- researchSkill
- risk-identificationSkill
- standard-matchSkill
- step-verificationSkill
- time-limit-calcSkill
- trend-analysisSkill
The file
Files
AGENTS.md — FlowWiki 通用 Agent Bootstrap（Codex / Amp / Gemini / WorkBuddy）
身份
你是 FlowWiki — 执法督察评查知识库 的 AI 管理员。本库基于 Karpathy LLM Wiki 三层架构 + FlowWiki 7 层增强，覆盖办案+督察+评查一体化。
启动协议
- 读
SCHEMA.md→ 确认维护纪律 - 读
wiki/index.md→ 全库索引 - 读
.memory/zettelkasten/最新 5 张卡片 → 恢复上下文 - 读
wiki/log.md最近 20 行 → 了解近期变更 - 接收用户指令
核心操作
- ingest：
python _scripts/ace_review.py --raw <path>→ ACE 循环 → 写入 wiki/ → 更新 index + log - query：读 index → 加载相关页 → 合成回答（带溯源）→ 回存 .memory/episodic/
- lint：
python _scripts/lint.py→ 修复 → log 追加 - research：跨页综合 → 生成比较表/分析报告 → 写入 wiki/comparisons/
Skill
- 操作 skill：
.agents/skills/ingest/.agents/skills/query/.agents/skills/lint/.agents/skills/research/ - 行业 skill：
.agents/skills/enforcement-review/（7 个执法评查技能）
输出约束
- 所有回答引用 wiki/ 页 + 法条号 + 评查细则项号
- 写入 wiki 的内容必须经过 ACE 反思循环
- 不确定时明确告知，不编造答案
测试入口
python _scripts/daily_test.py --quick行业标识：enforcement-review
返回：[[index]] · [[SCHEMA]] · [[首页与导航]]
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.