Loading...
Loading...
Compare original and translation side by side
| Skill | Use when |
|---|---|
| New to Cekura, first-time setup, platform walkthrough |
| Set up a voice AI agent — provider, mock tools, KB, dynamic vars |
| Auto-tune agent prompts from eval results — diagnose → propose → apply → re-validate |
| Design new metrics, improve existing ones, metric best practices |
| Improve metric accuracy through feedback cycle (labs workflow) |
| Catalog of built-in metrics — what each does, costs, constraints, configuration |
| Design evaluators, test suites, coverage strategy, conditional actions |
| Debug a failing production call, reproduce with evals, fix, regression test, raise PR |
| 技能 | 使用场景 |
|---|---|
| 首次使用Cekura、初始设置、平台导览 |
| 设置语音AI Agent——提供商、模拟工具、知识库（KB）、动态变量 |
| 根据评估结果自动优化Agent提示词——诊断→提议→应用→重新验证 |
| 设计新指标、改进现有指标、指标最佳实践 |
| 通过反馈循环提升指标准确性（实验室工作流） |
| 内置指标目录——每个指标的功能、成本、约束、配置 |
| 设计评估器、测试套件、覆盖策略、条件操作 |
| 调试失败的生产调用、通过评估重现问题、修复、回归测试、提交PR |
| Command | Use when |
|---|---|
| Run the guided onboarding flow (state-aware, picks up where you left off) |
| Configure the Cekura MCP server (Claude Code only) |
| Update all Cekura skills to the latest version |
| Report a bug — files a GitHub issue, optionally attempts a fix |
| Create or update a metric via API |
| List metrics for an agent or project |
| Run metrics on specific calls |
| Full improvement cycle: collect feedback, run labs, auto-improve |
| Create or update a single evaluator with full field walkthrough |
| Auto-generate evaluators (or bulk create from CSV/JSON) |
| List evaluators for an agent or project |
| Execute evaluators (run test scenarios) |
| Check results from a test run |
| Full end-to-end quality report — generates 10 evals, runs them, produces structured analysis |
| 命令 | 使用场景 |
|---|---|
| 运行引导式入门流程（感知状态，可从上次中断处继续） |
| 配置Cekura MCP服务器（仅Claude Code可用） |
| 将所有Cekura技能更新至最新版本 |
| 报告Bug——提交GitHub Issue，可选尝试修复 |
| 通过API创建或更新指标 |
| 列出Agent或项目的指标 |
| 针对特定调用运行指标评估 |
| 完整改进周期：收集反馈、运行实验室测试、自动优化 |
| 创建或更新单个评估器，包含完整字段引导 |
| 自动生成评估器（或从CSV/JSON批量创建） |
| 列出Agent或项目的评估器 |
| 执行评估器（运行测试场景） |
| 查看测试运行的结果 |
| 完整端到端质量报告——生成10个评估器、运行评估、生成结构化分析 |
| User Need | Route To |
|---|---|
| "I'm new to Cekura" / first-time setup | cekura-onboarding skill |
| "Set up my agent" / "connect my voice agent" | cekura-create-agent skill |
| "Configure MCP" / "MCP not working" | |
| "Create metrics for my agent" | cekura-metric-design skill |
| "My metrics are giving wrong results" | |
| "I need to test my agent" | cekura-eval-design skill |
| "Generate test scenarios" | |
| "Create a specific test scenario" | |
| "Run my tests" | |
| "Check test results" | |
| "Create a metric that checks X" | |
| "Update this metric" | |
| "Evaluate calls against metrics" | |
| "Update my skills" | |
| "What metrics should I have?" | cekura-metric-design skill (baseline metrics section) |
| "Help me improve this metric" | |
| "Leave feedback on a metric result" | |
| "Set up production monitoring" | cekura-onboarding skill (Phase 6) + observability docs |
| "Add mock tools" / "set up tools" | cekura-create-agent skill (Phase 4) |
| "Upload knowledge base" | cekura-create-agent skill (Phase 5) |
| "Something's broken" / "file a bug" | |
| "Improve my agent" / "auto-tune from eval results" | cekura-self-improving-agent skill |
| "Which built-in metrics are available?" / "what does Hallucination Detection cost?" | cekura-predefined-metrics skill |
| "Fix this prod call bug" / "reproduce and test a fix" | cekura-fixing-prod-issues skill |
| "Run a full quality report" / "generate evals and run them end-to-end" | |
| 用户需求 | 引导至 |
|---|---|
| “我是Cekura新手” / 首次设置 | cekura-onboarding技能 |
| “设置我的Agent” / “连接我的语音Agent” | cekura-create-agent技能 |
| “配置MCP” / “MCP无法工作” | |
| “为我的Agent创建指标” | cekura-metric-design技能 |
| “我的指标结果不正确” | |
| “我需要测试我的Agent” | cekura-eval-design技能 |
| “生成测试场景” | |
| “创建特定测试场景” | |
| “运行我的测试” | |
| “查看测试结果” | |
| “创建一个检查X的指标” | |
| “更新这个指标” | |
| “针对指标评估调用” | |
| “更新我的技能” | |
| “我应该使用哪些指标？” | cekura-metric-design技能（基线指标部分） |
| “帮我改进这个指标” | |
| “对指标结果提供反馈” | |
| “设置生产监控” | cekura-onboarding技能（第六阶段） + 可观测性文档 |
| “添加模拟工具” / “设置工具” | cekura-create-agent技能（第四阶段） |
| “上传知识库” | cekura-create-agent技能（第五阶段） |
| “某个功能坏了” / “提交Bug” | |
| “改进我的Agent” / “根据评估结果自动优化” | cekura-self-improving-agent技能 |
| “有哪些可用的内置指标？” / “幻觉检测的成本是多少？” | cekura-predefined-metrics技能 |
| “修复这个生产调用Bug” / “重现并测试修复方案” | cekura-fixing-prod-issues技能 |
| “运行完整质量报告” / “生成评估器并端到端运行” | |
/setup-mcp/setup-mcp/autogen-eval/run-evals/eval-results/autogen-eval/run-evals/eval-results/improve-metric/evaluate-calls/improve-metric/evaluate-calls/create-metric/evaluate-calls/create-metric/evaluate-calls/setup-mcp/setup-mcp