cli-for-agents
>-
cli-for-agents
>-
docs
>-
gitnexus-cli
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\"
gitnexus-debugging
Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\"
gitnexus-exploring
Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: \"How does X work?\", \"What calls this function?\", \"Show me the auth flow\"
gitnexus-guide
Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\"
gitnexus-impact-analysis
Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\"
gitnexus-refactoring
Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: \"Rename this function\", \"Extract this into a module\", \"Refactor this class\", \"Move this to a separate file\"
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
mcp-for-agents
>-
prompt-leverage
Strengthen a raw user prompt into an execution-ready instruction set for Amp, Claude Code, Codex, or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.
ask-maestro
Router for choosing the next Maestro skill or lifecycle recipe.
maestro-audit
Audit a project using Maestro read-only: use for code review, architecture review, deepening opportunities, backlog proposals, harness-improvement findings, or repo-wide improvement audits without fixes.
maestro-card
Card work in a project using Maestro after design approval: use for implement, fix, verify, QA, close, release, continue, or unattended prompts like use loop, keep looping, work while away/asleep.
maestro-design
Design in a project using Maestro before implementation: use for brainstorm, plan, PRD synthesis, grilling/stress-test, domain model, deepening candidate, wording, workflow, skill/harness, card/task/feature, architecture, UX, or agent-process decisions.
maestro-research
Pre-design research for Maestro cards: creates or validates a same-card research.md receipt, maps context, stakeholders, hosting, unknowns, and the first design fork. Use before maestro-design when the user brings a new idea, zero-context feature, external/pasted plan, unfamiliar domain, stakeholder-heavy request, hosting-unclear work, or when research is missing, stale, skipped-risky, or needed for READY_FOR_DESIGN.
maestro-setup
Setup Maestro in a project using or adopting Maestro: use for init/install/sync/doctor, global skills, hooks, harness setup, or agent integration diagnosis/repair.
maestro-witness
Witness feature close: use after Maestro feature proof and QA pass, before feature close, to write current witness.md/advisor.md receipts, auto-invoke an independent advisor when allowed, apply risk-tier and human-demo policy, and emit Gate: APPROVED.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
maestro:api-design
REST API design patterns for resource naming, status codes, pagination, error responses, and versioning. Use during maestro:design when specifying API contracts, and maestro:implement when building endpoints.
maestro:article-writing
Long-form content writing for articles, guides, blog posts, and tutorials with distinctive voice. Use in any maestro phase when producing written content longer than a paragraph.
maestro:autonomous-loops
Patterns for autonomous Claude Code loops from simple pipelines to multi-agent DAG systems. Use during maestro:design when architecting automated workflows or multi-agent orchestration.
maestro:backend-patterns
Backend architecture patterns for Node.js, Express, and Next.js API routes. Use during maestro:implement when building server-side code, API routes, or backend services.
maestro:clickhouse-io
ClickHouse query optimization, analytics patterns, and data engineering for high-performance analytical workloads. Use during maestro:implement when building analytics queries or data pipelines with ClickHouse.
maestro:coding-standards
TypeScript/JavaScript/React/Node.js coding standards and best practices. Use during maestro:implement for code quality and maestro:review for review criteria on TS/JS projects.
maestro:configure-ecc
Interactive installer for Everything Claude Code skills and rules. Use during maestro:setup or project initialization to install and configure ECC skills.
maestro:content-engine
Multi-platform content creation for X, LinkedIn, TikTok, YouTube, and newsletters. Use in any maestro phase when producing social media content or marketing materials.
maestro:content-hash-cache-pattern
SHA-256 content hash caching for expensive file processing. Use during maestro:implement when adding caching layers with path-independent, auto-invalidating cache keys.
maestro:continuous-learning-v2
Instinct-based learning system with hooks, confidence scoring, and skill evolution. Use across all maestro phases for project-scoped pattern learning via session observation.
maestro:continuous-learning
Auto-extract reusable patterns from Claude Code sessions as learned skills. Use across all maestro phases to capture and reuse session learnings.
maestro:cost-aware-llm-pipeline
Cost optimization for LLM API usage with model routing, budget tracking, retry logic, and prompt caching. Use during maestro:implement when building LLM-powered features.
maestro:cpp-coding-standards
C++ coding standards based on C++ Core Guidelines for modern, safe, idiomatic C++. Use during maestro:implement for C++ code quality and maestro:review for C++ review criteria.
maestro:cpp-testing
C++ testing with GoogleTest and CTest, coverage analysis, and sanitizers. Use during maestro:implement when writing C++ tests and maestro:review when checking C++ test coverage.
maestro:database-migrations
Database migration best practices for schema changes, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and ORMs. Use during maestro:implement when modifying database schemas.
maestro:deployment-patterns
Deployment workflows, CI/CD pipelines, Docker containerization, and rollback strategies. Use during maestro:implement for deployment setup and maestro:review for production readiness.
maestro:django-patterns
Django architecture patterns, DRF APIs, ORM best practices, caching, and middleware. Use during maestro:implement when building Django features or REST APIs with Django REST Framework.
maestro:django-security
Django security best practices for authentication, CSRF, SQL injection, XSS prevention, and secure deployment. Use during maestro:review when reviewing Django security posture.
maestro:django-tdd
Django TDD with pytest-django, factory_boy, and DRF testing. Use during maestro:implement when writing tests for Django models, views, and API endpoints.
maestro:django-verification
Verification loop for Django: migrations, linting, tests with coverage, security scans, and deployment readiness. Use during maestro:review before Django releases or PRs.
maestro:docker-patterns
Docker and Docker Compose patterns for local development, container security, and multi-service orchestration. Use during maestro:implement for containerization and maestro:review for container security.
maestro:e2e-testing
Playwright E2E testing with Page Object Model, CI/CD integration, and flaky test strategies. Use during maestro:implement for E2E test writing and maestro:review for coverage verification.
maestro:eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD). Use during maestro:review to measure and validate session outcomes with eval metrics.
maestro:foundation-models-on-device
Apple FoundationModels framework for on-device LLM with guided generation and tool calling in iOS 26+. Use during maestro:implement when building on-device ML features for Apple platforms.
maestro:frontend-patterns
React and Next.js frontend patterns for state management, performance optimization, and UI best practices. Use during maestro:implement when building UI components or client-side features.
maestro:frontend-slides
Create animation-rich HTML presentations from scratch or convert PowerPoint files. Use in any maestro phase when building presentation slides or converting PPT/PPTX.
maestro:golang-patterns
Idiomatic Go patterns, best practices, and conventions for robust Go applications. Use during maestro:implement when writing Go code -- error handling, concurrency, interfaces, and project structure.
maestro:golang-testing
Go testing with table-driven tests, subtests, benchmarks, and fuzzing. Use during maestro:implement when writing Go tests following TDD methodology.
maestro:investor-materials
Pitch decks, one-pagers, investor memos, financial models, and fundraising materials. Use in any maestro phase when producing investor-facing documents.
maestro:investor-outreach
Cold emails, warm intros, follow-ups, and investor communications for fundraising. Use in any maestro phase when drafting investor-facing outreach messages.
Page 1 of 3 · 119 results