Loading...
Loading...
Found 1,836 Skills
Reduce a webpage to a structural skeleton with semantic tokens. Two-phase pipeline: Phase 1 injects a browser script that tokenizes content ({TEXT}, {HEADING:n}, {IMAGE:WxH}, {CTA:label}, {LINK:label}, {INPUT:type}, {VIDEO}, {ICON}). Phase 2 applies LLM structural reasoning to collapse repeated patterns ({REPEAT:N}), remove decorative wrappers, strip utility classes, and produce skeleton.html + manifest.json. Use when migrating pages to EDS, analyzing page structure, extracting page blueprints, or preparing input for GenAI block generation. Triggers on: reduce page, page skeleton, page blueprint, extract structure, tokenize page, page reduction, structural skeleton, reduce URL.
Designs, deepens, and hardens TypeScript codebase architecture in three modes: folder structures, module contracts, and middleware pipelines for a new app; domain-informed deepening of existing code; and the guardrail tooling, CI gates, and wayfinding that stop a structure decaying. Use when setting up project structure, organizing a monorepo, designing backend modules, writing an architecture brief, recovering domain terminology, recording an architecture decision, or asking "how should I structure this app", "find architecture improvements", "this module is a mess", "make this codebase agent-friendly", "set up guardrails for coding agents", "add a dead-code check", or "my agent can't find anything in this repo". For scaffolding a new repo use scaffold-nextjs or scaffold-cli, for multi-tenant isolation use multi-tenant-architecture, for the AGENTS.md file's own content use agents-md, and for review of a local diff use pr-reviewer.
Pilot the v1 research guide against synthetic personas —every trait marked as evidence or assumption, at least one skeptic— to find broken questions before spending real fieldwork, and write the Diagnosis + Script v2. Manually triggered, fourth station of the discovery pipeline; it validates nothing.
Run the socratic discovery interview that separates the symptom from the cause, grades the evidence, applies the metric gate and prioritizes up to three hypotheses, and write the Discovery Brief as dated research of the loaded product node. Manually triggered, first station of the discovery pipeline.
Long-form Web Novel Deconstruction. In-depth analysis of the Golden Three Chapters, character framework, highlight design, and rhythm control of hit long-form novels. Single in-depth deconstruction pipeline: After completing the Golden Three Chapters (Stage 1), a quick preview report is generated and the user is asked whether to proceed with full deconstruction. Upon confirmation, continue from Stage 2 with chapter-by-chapter summaries, aggregate analysis, setting relationship extraction, and summary report. All outputs are saved to StoryDeconstructionLibrary/{NovelTitle}/. Trigger methods: /story-long-analyze, /长篇拆文 (Chinese command), "Help me deconstruct this book", "Deconstruct this book", "Analyze the Golden Three Chapters", "In-depth deconstruction", "Complete deconstruction", "Systematic deconstruction", or providing the path to the novel text file — all enter the same pipeline.
Build Jenkins declarative and scripted pipelines with stages, agents, parameters, and plugins. Implement multi-branch pipelines and deployment automation.
Generate production-ready fal.ai workflow JSON files. Use when user requests "create workflow", "chain models", "multi-step generation", "image to video pipeline", or complex AI generation pipelines.
Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools. Implements automated training, deployment, and monitoring across cloud platforms. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.
Optimizes CI pipelines for monorepos by detecting affected packages/apps and running only necessary builds and tests. Includes Turborepo/Nx strategies, caching, and parallel execution. Use for "monorepo CI", "affected detection", "incremental builds", or "workspace optimization".
Write a systematic review protocol into `output/PROTOCOL.md` (databases, queries, inclusion/exclusion, time window, extraction fields). **Trigger**: protocol, PRISMA, systematic review, inclusion/exclusion, 检索式, 纳入排除. **Use when**: systematic review pipeline 的起点（C1），需要先锁定 protocol 再开始 screening/extraction。 **Skip if**: 不是做 systematic review（或 protocol 已经锁定且不允许修改）。 **Network**: none. **Guardrail**: protocol 必须包含可执行的检索与筛选规则；需要 HUMAN 签字后才能进入 screening。
Build AI that answers questions about your database. Use when you need text-to-SQL, natural language database queries, a data assistant for non-technical users, AI-powered analytics, plain English database search, or a chatbot that talks to your database. Covers DSPy pipelines for schema understanding, SQL generation, validation, and result interpretation.
Build event streaming and real-time data pipelines with Kafka, Pulsar, Redpanda, Flink, and Spark. Covers producer/consumer patterns, stream processing, event sourcing, and CDC across TypeScript, Python, Go, and Java. When building real-time systems, microservices communication, or data integration pipelines.