浏览 mberto10 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
已收录技能
43收录技能的仓库 Stars 合计
0仓库 Forks
0平均每个技能的仓库 Stars
0同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
This skill should be used when the user asks to "write an email", "draft a message", "status update email", "meeting follow-up", "formulate in german", "wie formuliere ich", or needs help with German business c...
This skill should be used when the user invokes "/compound:discover", asks to "find patterns", "extract workflows", "what could be a skill", "what could be a command", "what could be an agent", "modularize this...
Meeting preparation for Jour Fixe, stakeholder updates, team syncs, and Lenkungsausschuss. Use when the user asks to prepare agendas, meeting updates, or decision lists.
This skill should be used when the user asks to "define a tool", "create tool schema", "design inputSchema", "add tool annotations", "handle file uploads", "tool descriptions", "tool naming", or needs guidance...
German business communication for project updates and meeting follow-ups. Use when the user asks to draft emails, status updates, stakeholder messages, or follow-up notes in German.
Production readiness evaluation for alpha that traces UI flows end-to-end (UI -> API -> backend -> persistence/integrations), defines what each flow should and should not do, finds stubbed or missing behavior,...
This skill should be used when the user asks to "evaluate UX", "run UX evaluation", "check user experience", "evaluate the signup flow", "test the onboarding", "assess user journey", "evaluate a lifecycle phase...
Systematic methodology for backend production readiness audits that extend infrastructure checks with security, performance, reliability, observability, and data integrity layers.
Use when the user asks to fetch Langfuse traces, list recent runs, inspect a trace ID, debug workflow inputs or outputs, filter by tags or metadata, or needs compact trace summaries for analysis.
This skill should be used when the user invokes "/compound:reflect", asks to "reflect on this session", "capture learnings", "what did we learn", "debrief this work", or wants to create a structured learning ar...
Use when the user says "analyze trace", "debug workflow", "why did this fail", "output is wrong", "missing data", "slow run", or needs root-cause analysis that ties Langfuse traces to code and fixes.
Use this skill when users want to add Langfuse tracing to their code, set up observability, instrument LLM calls, or add scoring to their pipelines. Helps users correctly structure traces, spans, and generation...
Use when the user wants to add or update human scores on traces, manage annotation workflows, list scores, find traces pending review, or export annotations from Langfuse.
This skill should be used when the user asks to "get langfuse traces", "fetch trace data", "retrieve last traces", "show me the trace", "debug a trace", "analyze trace ID", "what happened in trace", or needs to...
Use when the user asks to evaluate UX, dogfood a product, assess production readiness, run an MCP app evaluation, trace UI-to-backend gaps, or find UX issues in a flow. Provides three modes (ux-eval, dogfood, m...
This skill should be used when the user invokes "/compound:reflect", asks to "reflect on this session", "capture learnings", "what did we learn", "debrief this work", or wants to create a structured learning ar...
Use when the user wants to run an evaluation cycle: execute a Langfuse experiment, analyze failures, compare cycles, and document findings.
Use when the user asks to analyze score trends, regressions, distributions, or compare quality metrics across releases, environments, or trace names in Langfuse.
This skill should be used when the user asks to "evaluate a goal", "trace a user goal", "goal-driven evaluation", "test if users can achieve X", "evaluate end-to-end", "trace through layers", or wants to unders...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。