Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
brainstorming
A highly structured Socratic method for transforming vague ideas into validated software designs through autonomous research, phased questioning, and explicit validation gates.
using-ops-team
Provides five specialized operations agents for production environments: platform engineering, incident response, cloud cost optimization, infrastructure architecture, and security operations. Enforces strict dispatch protocols with clear domain boundaries and non-negotiable safety checks for production changes.
notebooklm
This skill enables Claude to query Google NotebookLM notebooks directly, providing source-grounded answers from uploaded documents. It automates browser sessions for authentication and querying, includes library management for multiple notebooks, and implements a follow-up mechanism to ensure complete answers.
create-meta-prompts
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
roadmap-integration
Manages product roadmap via GitHub Issues (brainstorm, prioritize, track). Auto-validates features against project vision (from overview.md) before adding to roadmap. Use when running /roadmap command or mentions 'roadmap', 'add feature', 'brainstorm ideas', or 'prioritize features'.
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume.
supabase
Database operations for Supabase: query/write/migration/logs/type generation. Triggers: query/statistics/export/insert/update/delete/fix/backfill/migrate/logs/alerts/type generation. Does not trigger for: pure architecture discussion or code planning. Write operations require confirmation; UPDATE/DELETE without WHERE is refused. MCP is optional — works with CLI/Console too.
github-issue-reader
This skill fetches GitHub issue data including comments, labels, assignees, and cross-references using the gh CLI. It outputs formatted markdown for planning and implementation context. The script handles multiple input formats and provides structured issue information.
peer-review
Provides structured guidance for evaluating scientific manuscripts across disciplines. Includes detailed checklists for methodology, statistics, ethics, and reporting standards like CONSORT and PRISMA. Helps reviewers systematically assess study rigor and identify common flaws in experimental design.
hmdb-database
Provides structured access to the Human Metabolome Database for metabolite lookup, chemical property retrieval, and biomarker data. Covers 220K+ metabolites with details on NMR/MS spectra, pathways, and clinical associations. Useful for metabolomics researchers needing reference data without manual web searching.
research
Research libraries, APIs, and patterns using searchGitHub and Exa tools. Finds real-world implementations and saves structured reports to docs/research/. Use when investigating technologies, debugging issues, or comparing options.
plan-orchestrator
A skill that orchestrates multiple specialized agents to build full-stack applications. It plans projects in phases, enforces a 'UI first' execution order, and provides detailed progress reports. It coordinates UI, backend, and design agents based on a clear workflow.
specification-phase
Provides standard operating procedures for the /specify phase including feature classification (HAS_UI, IS_IMPROVEMENT, HAS_METRICS, HAS_DEPLOYMENT_IMPACT), research depth determination, clarification strategy (max 3, informed guesses for defaults), and roadmap integration. Use when executing /specify command, classifying features, generating structured specs, or determining research depth for planning phase. (project)
generate-stock-reports
This skill automates company research by generating structured reports from web searches. It identifies companies by name or ticker, gathers recent news across product, management, financial, and analyst categories, and outputs markdown files with proper sourcing. The instructions clearly define trigger conditions, report structure, and handling of edge cases like ambiguous tickers.
research
A specialized Claude skill that documents existing codebases by coordinating parallel sub-agents to locate, analyze, and synthesize information. It enforces a strict 'documentarian' role, forbidding suggestions for improvement. Outputs structured research documents with metadata, file references, and historical context from a thoughts directory.
deep-research
A comprehensive research agent with rigorous methodology for systematic information gathering, verification, and structured documentation.
scikit-survival
This skill provides comprehensive guidance for survival analysis using scikit-survival in Python. It covers Cox models, ensemble methods, SVMs, and competing risks analysis with practical code examples. The documentation includes model selection flowcharts, data preparation steps, and performance evaluation metrics for time-to-event data.
increment-work-router
An intelligent work continuation system that automatically detects implementation intent and routes users to existing active work increments or creates new ones, bridging the gap between planning and execution for seamless workflow transitions.
discover-cloud
A gateway skill that automatically activates during cloud-related development tasks and provides access to 13 specialized AWS and GCP skills. It uses keyword triggers like 'cloud', 'AWS', 'serverless' to load relevant documentation. The skill organizes cloud knowledge into logical categories and enables progressive loading from gateway to specific skill details.
ai-prompt-engineering
Provides concrete prompt patterns and templates for building production AI systems with Claude. Focuses on structured outputs, RAG workflows, agent tool calling, and hidden reasoning. Includes decision trees, checklists, and versioned templates for immediate implementation.
writing-plans
Creates detailed implementation plans with file paths, code examples, and verification steps. Queries historical precedent to avoid past failures, validates plans against known issues, and provides multiple execution options for engineering teams.
angular-architect
This skill provides expert guidance for building Angular 15+ enterprise applications. It covers architecture planning, RxJS patterns, NgRx state management, and performance optimization with specific checklists and integration with tools like Nx, Jest, and Cypress. It's designed for teams needing structured Angular development workflows.
data-researcher
This skill provides structured data research workflows with SQL, Python, and web search capabilities. It follows a systematic approach from data planning to visualization, integrating multiple MCP tools for comprehensive data tasks. The checklist-driven methodology ensures quality and reproducibility.
finalize-phase
Completes feature/epic workflows after deployment with comprehensive walkthrough generation for epics (v5.0+), roadmap updates, artifact archival, documentation, and branch cleanup. Use after /ship-prod, /deploy-prod, or /build-local completes, or when user asks to finalize. (project)