Loading...
Loading...
Found 65 Skills
Build semantic search with Cloudflare Vectorize V2. Covers async mutations, 5M vectors/index, 31ms latency, returnMetadata enum changes, and V1 deprecation. Prevents 14 errors including dimension mismatches, TypeScript types, testing setup. Use when: building RAG or semantic search, troubleshooting returnMetadata, V2 timing, metadata index, dimension errors, vitest setup, or wrangler --json output.
Analyze, plan, and execute FireCrawl SDK upgrades with breaking change detection. Use when upgrading FireCrawl SDK versions, detecting deprecations, or migrating to new API versions. Trigger with phrases like "upgrade firecrawl", "firecrawl migration", "firecrawl breaking changes", "update firecrawl SDK", "analyze firecrawl version".
Build with Claude Messages API using structured outputs for guaranteed JSON schema validation. Covers prompt caching (90% savings), streaming SSE, tool use, and model deprecations. Prevents 16 documented errors. Use when: building chatbots/agents, troubleshooting rate_limit_error, prompt caching issues, streaming SSE parsing errors, MCP timeout issues, or structured output hallucinations.
Complete guide for OpenAI's Assistants API v2: stateful conversational AI with built-in tools (Code Interpreter, File Search, Function Calling), vector stores for RAG (up to 10,000 files), thread/run lifecycle management, and streaming patterns. Both Node.js SDK and fetch approaches. ⚠️ DEPRECATION NOTICE: OpenAI plans to sunset Assistants API in H1 2026 in favor of Responses API. This skill remains valuable for existing apps and migration planning. Use when: building stateful chatbots with OpenAI, implementing RAG with vector stores, executing Python code with Code Interpreter, using file search for document Q&A, managing conversation threads, streaming assistant responses, or encountering errors like "thread already has active run", vector store indexing delays, run polling timeouts, or file upload issues. Keywords: openai assistants, assistants api, openai threads, openai runs, code interpreter assistant, file search openai, vector store openai, openai rag, assistant streaming, thread persistence, stateful chatbot, thread already has active run, run status polling, vector store error
Manages the graceful decommissioning of underused or high-maintenance features. Plans deprecation cycles, handles data archiving, and generates migration paths for legacy users.
Build health audit worker (L3). Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build configuration issues. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
Production-grade API design patterns for REST, GraphQL, gRPC, and tRPC. Covers API architecture, OpenAPI/Swagger specs, versioning/deprecation, authentication/authorization, rate limiting, pagination, error models, contract testing, and developer documentation.
Build semantic search with Cloudflare Vectorize V2 (Sept 2024 GA). Covers V2 breaking changes: async mutations, 5M vectors/index (was 200K), 31ms latency (was 549ms), returnMetadata enum, and V1 deprecation (Dec 2024). Use when: migrating V1→V2, handling async mutations with mutationId, creating metadata indexes before insert, or troubleshooting "returnMetadata must be 'all'", V2 timing issues, metadata index errors, dimension mismatches.
Extracts technical API constraints from OpenAPI/Swagger specs and developer docs into a contract-ready API Access & Constraints Schedule with source traceability, risk flags, and change-control language. Use when drafting legal exhibits or schedules covering API access scope, rate limits, authentication, data fields, or deprecation terms for MSAs, SOWs, or order forms.
Use this skill when the user wants to add or update metadata in DataHub: descriptions, tags, glossary terms, ownership, deprecation, domains, data products, structured properties, documents, or field-level metadata. Triggers on: "add tag to X", "update description for X", "set owner of X", "add glossary term", "deprecate X", "create a domain", "create a glossary term", "add a document", or any request to modify DataHub metadata.
Source of truth for event taxonomy generation, data auditing, and governance best practices in Amplitude. Use when an agent needs to create, validate, audit, score, or recommend improvements to event tracking plans, naming conventions, property standards, data quality, or deprecation workflows. Covers naming rules, property standards, scoring frameworks, safe metadata operations, deprecation procedures, and AI readiness guidance.
Expert-level development skill for building, debugging, reviewing, and migrating Freshworks Platform 3.0 marketplace applications. REQUIRES Node.js 24.x + FDK 10.x installed BEFORE use—checks prerequisites and refuses to proceed without them. Does NOT install or manage FDK/Node—use fw-setup skill. Before fdk validate, follow this SKILL.md Manifest + toolchain gate (fw-setup if CLI wrong, /fdk-migrate on 2.x or legacy engines, then validate—never downgrade to FDK 9/Node 18 as a shortcut except LAST RESORT after six validate iterations). New apps default to FDK 10.0.1 and Node.js 24.x; FDK 9.x/Node 18.x allowed when explicitly requested with deprecation notice. Use for: (1) Creating Platform 3.0 apps (frontend, serverless, hybrid, OAuth), (2) Debugging validation errors, (3) Migrating Platform 2.x apps to 3.0, (4) Reviewing manifest.json, requests.json, oauth_config.json, (5) Implementing Crayons UI, (6) Integrating external APIs or OAuth providers, (7) Any Freshworks Platform 3.0 app development, FDK CLI, or marketplace submission task.