Analítica
Anàlisi, informes i visualització
team-solve
shhac
Investigate and solve problems using a team of specialist agents. Use when facing complex, multi-faceted problems that benefit from parallel research and structured implementation.
competing-hypotheses
shhac
Debug problems by investigating multiple hypotheses in parallel. Use when you have a bug, unexpected behaviour, or mystery where the root cause is unclear. Spawns parallel investigator agents each pursuing a different theory, then compares evidence to identify the most likely cause and fix.
executing-plans
izyanrajwani
Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.
customer-health-analyst
ncklrs
Expert customer health scoring and analytics guidance. Use when designing health scores, building churn prediction models, analyzing usage metrics, identifying at-risk accounts, creating executive dashboards, or performing cohort analysis. Use for leading indicator development, customer data enrichment, risk escalation frameworks, and retention analytics.
product-analyst
ncklrs
Expert product analytics strategist for SaaS and digital products. Use when designing product metrics frameworks, funnel analysis, cohort retention, feature adoption tracking, A/B testing, experimentation design, data instrumentation, or product dashboards. Covers AARRR, HEART, behavioral analytics, and impact measurement.
product-leader
ncklrs
Strategic product leadership guidance for SaaS and technology companies. Covers product strategy, roadmap planning, product discovery, user research, growth product management, platform strategy, product analytics, and product launches. Use when defining product vision, prioritizing features, conducting discovery, analyzing metrics, or launching products. Use for "product strategy", "roadmap planning", "feature prioritization", "product discovery", "product metrics", "PRD writing".
Observable Plot Skill
maragudk
GitHub Repository
role-algorithms:graph-algorithms
rnavarych
Implements graph algorithms — BFS/DFS traversal, shortest paths (Dijkstra, Bellman-Ford, Floyd-Warshall, A*, Johnson's), minimum spanning trees (Kruskal, Prim), topological sort, strongly connected components (Tarjan, Kosaraju), maximum flow (Ford-Fulkerson, Dinic), and bipartite matching (Hopcroft-Karp, Hungarian). Use when solving traversal, shortest path, network flow, connectivity, or scheduling problems.
operate-align-moe-kernel
SyFI-ServingStudio
Diagnose alignment of one existing fused MoE kernel through exact-input, compressed-popularity, and full-run comparisons. Not for whole-model MoE attribution, routing-model design, or adding a new kernel backend.
argocd-helm
mujez
ArgoCD and Helm expert skill. Use when deploying applications with ArgoCD, creating or reviewing Helm charts, designing GitOps workflows, managing ApplicationSets, multi-cluster deployments, progressive delivery with Argo Rollouts, troubleshooting sync issues, secrets management (SOPS, External Secrets Operator), and Kubernetes manifest management. Covers ArgoCD 3.x and Helm 3.x best practices.
dashboards
ahmadzayan-hub
Deep analysis of a dataset through the governed pipeline (scripts/analyse.py), then a dashboard where every figure shows its source. In claude.ai cloud sessions it builds a real Claude Dashboard with the Dashboard artifact type; anywhere else, or offline, it writes a free self-contained HTML dashboard (render.py). Use for KPI pages, scorecards, management dashboards, capstone or client dashboards, and "analyse this file and show me".
surrealdb
mikkelkrogsholm
"SurrealDB — multi-model database supporting document, graph, relational, key-value, time-series, and vector search in a single engine using SurrealQL. Use when building with SurrealDB or asking about schema design (schemafull vs schemaless), SurrealQL queries, graph relations with RELATE, live queries, full-text search, JS/TS SDK setup, namespace and database hierarchy, record IDs, authentication with DEFINE ACCESS, or connecting with WebSocket vs HTTP. Fetch live documentation for up-to-date details."
argus-build-diagnostics
tuist
Diagnose xcodebuild builds using argus. Use this instead of parsing xcodebuild output to avoid filling the context window. Query build errors, warnings, slowest targets, bottlenecks, implicit/redundant dependencies, and dependency graph with linking information for optimization analysis.
slidev-mermaid
yoanbernabeu
Create diagrams with Mermaid in Slidev. Use this skill for flowcharts, sequence diagrams, class diagrams, and more.
word-count-checker
rawveg
Automatically checks word counts of documents when the user mentions word count in relation to a file. Triggers on phrases like "Check the word count of X", "Stop when the word count is N", or similar references to document word counts. Use this skill proactively whenever word count is mentioned with a document reference.
operate-compare-serving-performance
SyFI-ServingStudio
Compare two real serving engines by end-to-end performance, then compare broad GPU-time regions without per-iteration alignment. Not for simulator alignment or an A/B within one implementation.
flow-navigator
khgs2411
Navigate Flow projects with dashboard-first pattern. Use when user asks about status, current work, what's next, or project progress. Read-only skill.
data-visualizer
daffy0208
Expert in creating charts, dashboards, and data visualizations using modern libraries
knowledge-pipline
YesIamGodt
"多模态知识管道技能 — 摄入文档(PDF/图片/视频/Office)到持久化知识维基，支持知识融合、跨源矛盾检测、多源聚合查询、知识图谱构建。当用户提到摄入文档、构建知识库、查询维基、检查一致性、构建知识图谱、文档分析、多模态理解、数据管道等需求时触发此技能。即使用户没有明确说 pipeline 或 knowledge-pipline，只要涉及将文档转化为结构化知识、跨文档分析对比、或知识图谱可视化，都应触发此技能。"
Knowledge Graph Builder
daffy0208
Design and build knowledge graphs. Use when modeling complex relationships, building semantic search, or creating knowledge bases. Covers schema design, entity relationships, and graph database selection.
Orchestration Planner
daffy0208
Plan multi-step workflows using capability graph and Codex-powered goal decomposition with HTN-style hierarchical task planning.
customer-feedback-analyzer
daffy0208
Synthesize user feedback from multiple channels and identify patterns to inform product decisions. Use when analyzing feedback, prioritizing feature requests, conducting NPS surveys, or understanding user sentiment. Covers feedback collection, categorization, prioritization frameworks, and closing the feedback loop.
aspire
Tyler-R-Kendrick
Use when configuring dev containers for .NET Aspire projects. Covers the Aspire workload, Docker-in-Docker requirement, dashboard port forwarding, and multi-service orchestration in Codespaces. USE FOR: .NET Aspire dev containers, Aspire workload in Codespaces, Aspire dashboard port forwarding, Aspire + Docker-in-Docker setup DO NOT USE FOR: general .NET dev containers without Aspire (use dotnet), standalone Docker-in-Docker (use docker-in-docker), general devcontainer.json (use devcontainer)
mcp-apps
Tyler-R-Kendrick
Use when building MCP Apps that serve interactive UI from MCP servers. Covers the ui:// URI scheme, HTML rendering in sandboxed iframes, and bidirectional communication between UI and host. USE FOR: rich UI in agent conversations, interactive dashboards from MCP servers, sandboxed iframe rendering DO NOT USE FOR: basic tool responses without UI (use mcp), agent communication (use a2a), full web applications