five-step
Skill0 starsChanged 2 months agoNo licenceView on GitHub
示例： - /five-step → 我问你要实现什么 - /five-step network PolicyNetwork - /five-step buffer RolloutBuffer - /five-step loss DQNLoss 状态检查： - 检查是否有未完成的组件（从 session memory） - 如果有，问："你上次在实现 PolicyNetwork - Step 3，要继续吗？" 目标：用人话明确组件的数学含义、输入输出、实现细节 根据组件类型问不同的问题：
In this repository21 other files it gives its agents.
- activate-conda-envSkill
- apifox-branchSkill
- apifox-cli-checkupSkill
- apifox-cliSkill
- apifox-import-exportSkill
- apifox-test-automationSkill
- apifox-test-caseSkill
- apifox-test-scenarioSkill
- apifox-workflow-api-lifecycleSkill
- deeppapernoteSkill
- document-changesSkill
- explain-callflowSkill
- find-skillsSkill
- git-commit-messageSkill
- graphify-windowsSkill
- ljg-paper-riverSkill
- paper-readerSkill
- paper-translatorSkill
- pdf-enhanceSkill
- save-and-restore-progressSkill
- understand-codeSkill
The file
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.