发现 Skills

Operate intake triage and cross-project routing decisions over the LPM workspace context. Use this skill when the user wants to classify new work, preview routing candidates, or resolve ambiguous project ownership.

Check new decisions against prior decisions and stated principles.

Transaction guidance: patterns for building, signing, and submitting transactions. Provides reusable command templates only (no execution). Use the paired operator Skill to perform any runtime operations.

Plan, build, audit, and fix a new agent in one automated run — no approval gates after the initial ask. Use when the user wants to create an agent end-to-end in one step, or says "ship an agent", "build this end-to-end", "one-shot build", "create and deploy an agent", "build an agent start to finish".

Use always - non-negotiable rules for TypeScript safety, socket events, and React patterns

Use when building a component catalog, when standardizing component props and states across a product, when two engineers are about to build competing versions of the same component, or before a major UI build sprint.

Guides measure-first performance investigation using CPU profilers, memory analyzers, flamegraphs, and reproducible benchmarking across Python and Node.js. USE WHEN the user asks to "profile this code", "find the bottleneck", "create a flamegraph", "benchmark this function", "find memory leaks", "check memory usage", "reduce latency", or "measure execution time", or works with cProfile, py-spy, scalene, clinic.js, Chrome DevTools, hyperfine, or pytest-benchmark. DO NOT USE for security auditing, dependency management, or code refactoring.

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

Use when adding new files, patterns, or examples to skeleton/. Use when creating new controller, model, job, mailable, migration, view, or component in the skeleton app.

Automates the release workflow for the Payload Newsletter Plugin. Use when releasing a new version, bumping the version, or publishing to npm.

Create UIs matching the myOperator design system. Use this skill when the user asks to "build with myoperator design", "create myoperator-style UI", "use myoperator design system", "myoperator dashboard", "myoperator page", or asks for interfaces, pages, dashboards, or components that should follow myOperator's visual language. Generates standalone React/Tailwind code with the design system's color tokens, typography, and component patterns.

A framework for processing code review feedback with technical rigor rather than reflexive compliance. Covers how to evaluate reviewer suggestions before implementing, distinguish style feedback from substantive issues, push back on incorrect feedback constructively, and avoid blind-implementation of suggestions that introduce bugs or degrade design.

Expert in deep observation, pattern recognition, and creative connection discovery. Use for uncovering hidden insights and minimizing cognitive biases.

Extract clean markdown or text content from specific URLs via the Tavily CLI. Use this skill when the user has one or more URLs and wants their content, says "extract", "grab the content from", "pull the text from", "get the page at", "read this webpage", or needs clean text from web pages. Handles JavaScript-rendered pages, returns LLM-optimized markdown, and supports query-focused chunking for targeted extraction. Can process up to 20 URLs in a single call.

Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says "search for", "find me", "look up", "what's the latest on", "find articles about", or needs current information from the internet. Returns relevant results with content snippets, relevance scores, and metadata — optimized for LLM consumption. Supports domain filtering, time ranges, and multiple search depths.

Given outputs from 5 research sub-agents (time-sliced or partitioned), validate and synthesize them into a coherent, citation-backed Markdown deep research report with deduplication, contradiction handling, and explicit debug visibility when inputs are missing or malformed.

Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing applications, managing infrastructure as code, deploying to Kubernetes clusters, configuring cloud platforms, automating releases, or responding to production incidents. Invoke for pipelines, Docker, Kubernetes, GitOps, Terraform, GitHub Actions, on-call, or platform engineering.

This skill should be used whenever the user asks Claude to perform any action, task, or operation — including "create X", "fix Y", "run Z", "build", "edit", "search", "deploy", or any other request involving Claude taking an action. Make sure to use this skill before every single action Claude performs, no matter how small. Activate on every action request without exception.

Find and complete paid expert surveys from expert network platforms (Arbolus, Guidepoint, GLG, AlphaSights, Techsponential) using the user's real professional background. Automates the mechanical form-filling of expert consultations that pay $50-$100+. Use this skill whenever the user mentions surveys, canopy, expert consultations, Arbolus, Guidepoint, GLG, AlphaSights, 'find surveys', 'check surveys', 'complete survey', 'paid survey', 'expert network', 'canopy reward', or any reference to survey rewards/honorariums. Also activate when the user asks to check Gmail for survey invitations or mentions earning money from expertise sharing.

Activate mode for helping with learning and problem solving.

End-to-end YouTube publishing workflow using ordered scripts: prepare/concat video, upload draft, transcribe with Parakeet, generate copy+thumbnails with Gemini, update YouTube metadata, then schedule socials (Postiz) 15 minutes after publish.

审查 Python 代码，提供改进建议，确保代码质量和最佳实践

Join the DevFlow community. Community and meta information — not a workflow command.

Multi-perspective collaborative inquiry. Decomposes a topic into six cognitive lenses (Scope, Logic, Mythos, Bridge, Meta, Pattern) that operate as a chorus rather than a single voice, then synthesizes meta-patterns no single lens could find alone. MANDATORY TRIGGERS: "expansive inquiry", "multi-perspective inquiry", "explore this from every angle", "six-lens analysis", "run a chorus on this". STRONG TRIGGERS: "help me think through X deeply", "mythopoetic AND logical analysis". Do NOT trigger on simple Q&A or failure-focused inquiries — use premortem for those.