Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from this session — one IDE, fan-out, or model comparison. Relay the other runtime's stdout verbatim. Use on run in <ide>, compare <ide> vs <ide>, try on <model>, run across models.

Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques, compression strategies, memory architectures, multi-agent patterns, evaluation, tool design, and project development.

Use when building, refactoring, or documenting Graft apps and proxies, including when asked to create a tool server, API server, dual-protocol server, or MCP-HTTP bridge. Graft's core thesis: define tools once and serve them as both HTTP REST endpoints and MCP tools from the same server, with discovery, docs, and OpenAPI generated automatically. Covers concrete actions such as defining tools and handlers, configuring authentication middleware, setting up HTTP and stdio transports, generating OpenAPI documentation, wrapping existing APIs via proxy mode, and wiring up the full CLI workflow.

Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.

Use when writing, reviewing, or debugging pure Ruby code — idiomatic patterns, modern 3.x+ features (pattern matching, Data.define, endless methods), error handling conventions (raise vs fail, result objects), memoization, and performance idioms. For Rails use rails-guides. For testing use minitest. For code style use sandi-metz-rules.

Entry signal patterns with historical success rates. Use when deciding whether to open a position.

Use when reviewing a PR/MR by URL or the local working-tree diff — runs multi-perspective parallel agents (bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence) with confidence scoring and optional draft inline comments on the MR. Triggers for `/devflow:review` or any "review this PR/MR" request.

[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Research → Plan → Execute), integrate risks, and declare new skill. Use when facing novel problems that existing skills can't address.

Generates Tzatziki-based Cucumber BDD tests (.feature files) from a functional specification. Use this skill whenever a user wants to write Cucumber tests, add BDD scenarios, create feature files, generate tests, or test application behaviors with Gherkin — especially in Java/Spring projects using Tzatziki step definitions for HTTP, JPA, Kafka, MongoDB, OpenSearch, logging, or MCP. Also use when the user mentions writing integration tests, acceptance tests, or end-to-end tests in a project that already has Tzatziki/Cucumber dependencies, including TestNG-based setups.

Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.

Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says \"编译论文\", \"compile paper\", \"build PDF\", \"生成PDF\", or wants to compile LaTeX into a submission-ready PDF.

Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.

Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

Run an SEO + structured-data audit of the site (wraps `bun run seo:audit`) and verify per-page SEO wiring and JSON-LD. Use before pushing, or when asked to check SEO.

Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.

Use when writing or reviewing Go code in this repo that synthesizes audio with Speak v1 REST or Speak WebSockets. Route transcription work to deepgram-go-speech-to-text, voice conversation runtime work to deepgram-go-voice-agent, and repository maintenance work to deepgram-go-maintaining-sdk.

Run comprehensive joelclaw health checks, including postboot/daily checks for NAS, MinIO, Convex, Postgres, Typesense, Inngest, Panda/Flagg authority split, k8s, worker, Redis, OTEL, tests, repo sync, memory pipeline, and disk. Use when: 'system health', 'postboot check', 'daily system check', 'health check', 'is everything working', 'system status', 'how's the system', 'check everything', or at session start to orient.

Work with the @upstash/search TypeScript/JavaScript SDK, a serverless full-text and semantic search database with built-in reranking. Use when adding search to an app or site, creating a search index, upserting documents with searchable content and filterable metadata, running keyword, semantic, or hybrid search queries, reranking results, filtering with SQL-like or structured filter syntax, paginating with range, fetching or deleting documents, resetting an index, or checking index info. Also use when the user asks for site search, product, document, or knowledge-base search, or a managed search service that needs no cluster to run.

Use Neo4j GenAI Plugin ai.text.* functions and procedures for in-Cypher embedding generation, text completion, structured output, chat, tokenization, and batch ingestion. Covers ai.text.embed(), ai.text.embedBatch(), ai.text.completion(), ai.text.structuredCompletion(), ai.text.aggregateCompletion(), ai.text.chat(), ai.text.tokenCount(), ai.text.chunkByTokenLimit(), and provider configuration for OpenAI, Azure OpenAI, VertexAI, and Amazon Bedrock. Requires CYPHER 25. Replaces deprecated genai.vector.encode(). Use when writing pure-Cypher GraphRAG, embedding nodes in-graph, generating structured maps from prompts, or calling LLMs inside Cypher queries. Does NOT handle neo4j-graphrag Python library pipelines — use neo4j-graphrag-skill. Does NOT handle vector index creation/search — use neo4j-vector-index-skill.