发现 Skills

Execute Perplexity multi-turn research sessions and batch query pipelines. Use when conducting in-depth investigations, generating research briefs, or processing multiple related search queries. Trigger with phrases like "perplexity research", "perplexity batch search", "multi-query perplexity", "perplexity deep dive", "perplexity report".

Implement reliability patterns for Perplexity Sonar API: circuit breaker, model fallback, streaming timeout, and citation validation. Trigger with phrases like "perplexity reliability", "perplexity circuit breaker", "perplexity fallback", "perplexity resilience", "perplexity timeout".

Deduplicate Podium contacts in production and survive the data-quality failures — phone-format inconsistency producing four contacts for one phone, merge-api ordering that silently discards the richer record, opt-out flags lost on merge re-enabling marketing on an opted-out person, soft-delete confusion, cross-location duplicate blind spots, and simultaneous-merge race conditions. Use when you build a Podium dedup pipeline, scan and detect duplicate clusters, normalize phones to e164 form across an entire contact corpus, preserve opt-out state through merges, or validate cross-location duplicate resolution. Trigger with "podium contact dedup", "podium phone normalization", "podium e164", "podium duplicate contacts", "podium merge contacts", "podium opt-out preservation", "podium cross-location dedup".

This skill enables Claude to track and optimize application response times. It uses the response-time-tracker plugin to monitor API endpoints, database queries, external service calls, frontend rendering, and background job execution. The plugin calculates P50, P95, and P99 percentiles, average and maximum response times. Use this skill when you need to identify performance bottlenecks, monitor SLOs, or receive alerts about performance degradation. Trigger this skill with phrases like "track response times", "optimize latency", or "monitor application performance".

Rest Endpoint Designer - Auto-activating skill for API Development. Triggers on: rest endpoint designer, rest endpoint designer Part of the API Development skill category.

Schema Validator - Auto-activating skill for Data Pipelines. Triggers on: schema validator, schema validator Part of the Data Pipelines skill category.

Optimize Sentry costs, reduce event volume, and manage quota spend. Use when analyzing Sentry billing, reducing error/transaction volume, configuring sampling rates, or preventing overage charges. Trigger: "reduce sentry costs", "sentry billing optimization", "sentry quota management", "optimize sentry spend", "sentry sampling".

Implement Supabase across different app architectures: Next.js SSR with server components using service_role and client components with anon key, SPA (React/Vue), mobile (React Native), serverless (Edge Functions), and multi-tenant with schema-per-tenant or RLS isolation. Use when choosing how to integrate Supabase into your specific stack, setting up SSR auth flows, configuring mobile deep links, or designing multi-tenant data isolation. Trigger with phrases like "supabase next.js", "supabase SSR", "supabase react native", "supabase SPA", "supabase serverless", "supabase multi-tenant", "supabase server component", "supabase architecture", "supabase service_role server".

Optimize Supabase costs through plan selection, database tuning, storage cleanup, connection pooling, and Edge Function optimization. Use when analyzing Supabase billing, reducing costs, right-sizing compute, or implementing usage tracking and budget alerts. Trigger with phrases like "supabase cost", "supabase billing", "reduce supabase costs", "supabase pricing", "supabase expensive", "supabase budget".

This skill enables Claude to automatically generate comprehensive unit tests from source code. It is triggered when the user requests unit tests, test cases, or test suites for specific files or code snippets. The skill supports multiple testing frameworks including Jest, pytest, JUnit, and others, intelligently detecting the appropriate framework or using one specified by the user. Use this skill when the user asks to "generate tests", "create unit tests", or uses the shortcut "gut" followed by a file path.

Diagnose and fix Vast.ai common errors and exceptions. Use when encountering Vast.ai errors, debugging failed instances, or troubleshooting GPU rental issues. Trigger with phrases like "vastai error", "fix vastai", "vastai not working", "debug vastai", "vastai instance failed".

Configure Vercel CI/CD with GitHub Actions, preview deployments, and automated testing. Use when setting up automated deployments, configuring preview bots, or integrating Vercel into your CI pipeline. Trigger with phrases like "vercel CI", "vercel GitHub Actions", "vercel automated deploy", "CI vercel", "vercel pipeline".

Versioning Strategy Helper - Auto-activating skill for API Development. Triggers on: versioning strategy helper, versioning strategy helper Part of the API Development skill category.

Apply Webflow API security best practices — token management, scope least privilege, OAuth 2.0 secret rotation, webhook signature verification, and audit logging. Use when securing API tokens, implementing least privilege access, or auditing Webflow security configuration. Trigger with phrases like "webflow security", "webflow secrets", "secure webflow", "webflow API key security", "webflow token rotation".

Advanced Windsurf debugging for hard-to-diagnose IDE, Cascade, and indexing issues. Use when standard troubleshooting fails, Cascade produces consistently wrong output, or investigating deep configuration problems. Trigger with phrases like "windsurf deep debug", "windsurf mystery error", "windsurf impossible to fix", "cascade keeps failing", "windsurf advanced debug".

Configure and optimize Supercomplete code suggestions. Activate when users mention "code completion", "autocomplete", "supercomplete", "inline suggestions", or "ai completions". Handles completion configuration and optimization. Use when working with windsurf code completion functionality. Trigger with phrases like "windsurf code completion", "windsurf completion", "windsurf".

Manage integrate MCP servers with Windsurf for extended capabilities. Activate when users mention "mcp integration", "model context protocol", "external tools", "mcp server", or "cascade tools". Handles MCP server configuration and integration. Use when working with windsurf mcp integration functionality. Trigger with phrases like "windsurf mcp integration", "windsurf integration", "windsurf".

Manage large-scale refactoring with Cascade coordination. Activate when users mention "large refactoring", "codebase migration", "architecture refactor", "major refactoring", or "system-wide changes". Handles complex refactoring operations. Use when working with windsurf refactoring large functionality. Trigger with phrases like "windsurf refactoring large", "windsurf large", "windsurf".

Implement Windsurf reference architecture with optimal project structure and AI configuration. Use when designing workspace configuration for Windsurf, setting up team standards, or establishing architecture patterns that maximize Cascade effectiveness. Trigger with phrases like "windsurf architecture", "windsurf project structure", "windsurf best practices", "windsurf team setup", "optimize for cascade".

Execute automate release processes with semantic versioning. Activate when users mention "release automation", "version bump", "changelog generation", "semantic release", or "publish release". Handles release engineering automation. Use when working with windsurf release automation functionality. Trigger with phrases like "windsurf release automation", "windsurf automation", "windsurf".

Build Windsurf extensions and integrate with VS Code extension API events. Use when building custom Windsurf extensions, tracking editor events, or integrating Windsurf with external tools via extension development. Trigger with phrases like "windsurf extension", "windsurf events", "windsurf plugin", "build windsurf extension", "windsurf API".

Generate benchmarking pipelines to compare forecasting models and summarize accuracy/speed trade-offs. Use when evaluating TimeGPT vs StatsForecast/MLForecast/NeuralForecast on a dataset. Trigger with "benchmark models", "compare TimeGPT vs StatsForecast", or "model selection".

Create and manage Shopify pages, blog posts, navigation, and SEO metadata. Workflow: determine content type, generate content, create via API or browser, verify. Use when creating pages, writing blog posts, updating navigation menus, managing redirects, or updating SEO metadata on a Shopify store.

Most job seekers spray and pray. This skill hunts.