5-phase structured planning methodology: Specification, Pseudocode, Architecture, Refinement, Completion. Enhances GFV planning mode with formalized phases and quality gates.
Automates PySpark DataFrame transformations including schema inference, partition pruning, and Delta Lake merge operations.
Creates, configures, and updates Databricks Lakeflow Spark Declarative Pipelines (SDP/LDP) using serverless compute.
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big da — from…
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data — from…
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data — from…
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data — from…
Evaluate sparse retrieval models on standard IR benchmarks (BEIR, MIRACL, mMARCO). Covers all IR metrics (nDCG@k, Recall@k, MAP, MRR), dataset loading, sparse corpus encoding to…
Unified framework for spatial omics data in Python. Use for integrating multiple spatial modalities and formats. Part of the scverse ecosystem.
Use when writing, editing, reviewing, or formatting JavaScript, TypeScript, Vue, Prettier, or ESLint code using Spatie conventions.
Use when writing, editing, reviewing, or formatting Laravel, PHP, Blade, routes, migrations, validation, or tests using Spatie conventions.
Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution. — from engineering/engineering-misc
Spawn a new terminal window to run CLI commands (ffmpeg, curl, python, etc.). Use for non-AI command execution. — from bg-szy/TOP-SKILLS
GitHub Actions pipeline for Speak integrations with mocked API tests and audio validation. Use when implementing ci integration, or managing Speak language learning platform…
Collect diagnostic information for Speak API issues: auth verification, audio format validation, session inspection, and network testing.
Deploy Speak language learning features to Vercel, Cloud Run, or containerized environments. Use when implementing deploy integration, or managing Speak language learning platform…
Configure Speak local development with mocked tutors and audio testing. Use when setting up a development environment, configuring test workflows, or building language learning…
Optimize Speak API latency with audio preprocessing, response caching, and connection pooling. Use when implementing performance tuning, or managing Speak language learning…
Handle Speak API rate limits with exponential backoff, request queuing, and optimization strategies. Use when implementing rate limits features, or troubleshooting Speak language…
Production architecture for Speak language learning apps: client, API gateway, assessment engine, and progress store.
[Code Quality] Use to validate a spec artifact''s decisions with the user across three contexts — a freshly-authored Feature Spec (idea-to-spec), an existing canonical spec before…
Testing implementations against formal specifications including RFC compliance, protocol adherence, and standards conformance verification.
The content contract for a design doc — what must be IN it, as against make-spec which owns how it LOOKS.
Mandatory default entry point for any non-trivial build/add/fix/implement/refactor request — drives work through explicit spec-driven-development phases (constitution check →…
6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.
Start a new project with a spec before code. Two phases: Vision (what/why) then Blueprint (how/order).
Interview the user relentlessly about every aspect of a plan, walking down each branch of the design tree and resolving dependencies between decisions one-by-one until a shared…
Recognize when a mission is a bulk edit and drive the occurrence-classification guardrail on the user's behalf.
Reverse-engineering specialist that extracts specifications from existing codebases. Use when working with legacy or undocumented systems, inherited projects, or old code — from…
Reverse-engineering specialist that extracts specifications from existing codebases. Use when working with legacy or undocumented systems, inherited projects, or old code — from…
Generate a UI feature plan (plan.md) and eval_criteria.yaml from NFRs, acceptance scenarios, and architecture preflight.
PO-facing entrypoint — grill a requirement into an approved brief (scenarios, best-effort requirements and edge cases under local IDs) via direct conversation, then open a…
Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I…
Make a minimal evidence-backed update to a non-plan product, architecture, API, schema, or behavior contract.
Use when medium-to-large changes need explicit requirements, technical design, and task planning before implementation, especially for multi-module work, unclear acceptance…
Use when discovering protocol specifications, whitepapers, architecture docs, EIPs, RFC-style documents, or technical docs from seed URLs.
Use when Claude Code needs to refactor code, tests, docs, specs, or project structure in a SpecDD project while preserving specified behavior, public contracts, scenarios,…
Legacy support for SpecFlow (.NET BDD framework that predates Reqnroll) - for projects that haven't migrated yet. Mirrors Reqnroll's API closely (Reqnroll is the SpecFlow fork).
Use when a task needs the judgment of a Special Effects Artist/Animator — planning a shot through the VFX pipeline (previz through comp), diagnosing why a shot "feels wrong,"…
Deploy and maintain profile-backed specialist agents by executing the full wiring directly, including SOUL setup, profile config, gateways, Telegram bot attachment, and live…
Explains specialized Synapse action classes for specific workflows. Use when the user mentions "BaseTrainAction", "BaseExportAction", "BaseUploadAction", "BaseInferenceAction",…
Convert requirements into structured technical specifications with architecture decisions
Systematic analysis and refinement of specifications, requirements, architecture designs, and project plans.
Answer questions about Speck specs, plans, tasks, requirements, progress, architecture, user stories, feature status, and constitution.
AI & LLM Systems Architect - Design RAG pipelines, vector search, semantic caching, evals, and tool-calling guardrails.
Software Architect - Make evidence-based system design decisions, document trade-offs and ADRs, and define modular, reliable implementation boundaries.
Docker Infrastructure & Security Hardening Specialist — Port ENV-first, range 8900-8999.
Realtime & Event Systems Engineer - WebSocket channels, Server-Sent Events, Message Queues, and Transactional Outbox workers.
SRE & Observability Specialist - OpenTelemetry distributed tracing, Prometheus metrics, structured logs, and resilience controls.
Check planned AI coding actions and patches against explicit project constraints through SpecLock MCP tools.
Provides final code cleanup after task review approval. Removes debug logs, temporary comments, dead code, optimizes imports, and improves readability.
Executes real end-to-end verification against a running application after specification implementation.
Systematic bugfix workflow with regression testing, auto-retry logic, and comprehensive validation. Auto-executes when user clearly wants to fix, debug, repair, resolve, broken,…
Use when you have Spectra objects in an R environment and need to apply Python MS algorithms (e.g., matchms similarity scoring, spectrum normalization, or filtering) that operate…
Use when when you have raw LC-MS/MS data files in mzML, mzXML, or vendor-specific formats and need to load them into a Java-based mass spectrometry analysis framework for…
Use when when you have raw MS/MS mass spectrometry data and need to submit it to the Mass2SMILES Docker inference container for structure and functional group prediction.
Use when when you have a pre-cleaned spectral library (e.g., GNPS, MoNA, or MTBLS1572) with an existing training/test boundary established by prior work (e.g., MSBERT), and you…
Use when you have raw or unprocessed MS/MS spectral data in standard metabolomics formats (MGF, mzML, mzXML, msp, or JSON) and need to import them into a Python-based workflow for…
Use when when you need to understand or modify how MS2Query routes query spectra through its dual-pathway architecture, or when integrating MS2Query into another tool and need to…
Use when after implementing or modifying a cross-language integration layer that wraps Python mass spectrometry functions (e.g., spectral matching, peak detection, normalization…