llm-token-optimizer
Skill2 starsChanged 21 days agoNo licenceView on GitHub
分析和优化大模型应用的 Token 消耗，在效果不明显下降的前提下显著降本。只要用户提到「省 Token」「降本」「LLM 成本优化」「Prompt 瘦身」「上下文压缩」「模型路由」「RAG 优化」「Hackathon 赛题04」「让 AI 更省钱」，或要评审/改造一个 LLM 调用链路时使用此 skill。 输出结构化诊断报告 + 可落地优化方案 + 效果预估；支持从现有代码/Prompt/架构出发做审计，也支持从零写 Hackathon 提案。
In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- cc-showtimeSkill
- frontend-designSkill
- markitdownSkill
- skill-generatorSkill
- brainstormingSkill
- executing-plansSkill
- file-to-flashcardSkill
- interview-qa-organizerSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- parallel-dispatchSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- verification-before-completionSkill
- writing-plansSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
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.