maister-copilot

Implement task directly with AI SDLC standards awareness (no planning mode)

Enter planning mode with AI SDLC standards awareness

Run automated code quality, security, and performance analysis on your code

Run pragmatic code review to detect over-engineering and ensure code matches project scale

Verify production deployment readiness with comprehensive checks

Comprehensive reality assessment of completed work to verify it actually works and is production-ready

Independent specification audit to verify completeness and clarity before implementation

Unified entry point — auto-classifies tasks and routes to appropriate workflow. ALWAYS execute when invoked via slash command.

Static code analysis agent identifying performance bottlenecks by reading source code, schema files, and query patterns. Detects N+1 queries, missing indexes, O(n^2) algorithms, blocking I/O, memory leak patterns, and caching opportunities. Optionally incorporates user-provided profiling data. Strictly read-only.

Pragmatic code review specialist detecting over-engineering, unnecessary complexity, and developer experience issues. Evaluates pattern appropriateness for project scale, identifies intrusive automation, and recommends simplifications. Strictly read-only.

Automated code quality, security, and performance analysis. Analyzes code for complexity, duplication, security vulnerabilities, performance issues, and best practices compliance. Can run standalone (via command) or as part of implementation verification. Provides actionable findings categorized by severity. Read-only - reports issues without fixing. Does not interact with users.

Merges raw findings from parallel Explore agents into a structured codebase analysis report. Deduplicates files, cross-references analysis with tests, assesses complexity and risk, and produces actionable recommendations.

Internal documentation management service. Executes docs-manager operations and returns results to the calling workflow.

Executes runtime browser verification using Playwright MCP tools to verify implementation behavior against specifications. Does NOT generate test files — performs live interactive verification with evidence collection.

Compares current vs desired state, identifies gaps with user journey and data lifecycle analysis. Reports findings for orchestrator to act on. Adapts analysis based on detected task characteristics.

Verifies implementation completeness across three dimensions - plan completion with code spot-checks, standards compliance with active reasoning from INDEX.md, and documentation completeness (work-log, spec alignment). Read-only analysis that reports findings without fixing. Does not interact with users.

Creates detailed implementation plans from specifications. Breaks work into task groups by specialty (database, API, frontend, testing), creates implementation steps with test-driven approach (2-8 tests per group), sets dependencies, and defines acceptance criteria. Does not interact with users.

Information gathering specialist executing systematic data collection across multiple sources including codebase, documentation, configuration files, and web resources. Maintains source citations and organizes findings with evidence.

Automated production deployment readiness verification. Analyzes configuration management, monitoring setup, error handling, performance scalability, security hardening, and deployment considerations. Provides GO/NO-GO deployment recommendation with categorized blockers and concerns. Read-only - reports issues without fixing. Does not interact with users.

Analyzes project codebase to detect tech stack, architecture, and conventions for documentation generation. Use for existing/legacy projects to auto-generate meaningful documentation.

Reality assessment specialist orchestrating multi-agent validation workflow. Validates functional reality vs claims, ensures work solves actual problems, detects false completions, and creates pragmatic action plans. Strictly read-only.

Research planning specialist creating structured research plans from research questions. Analyzes objectives, determines methodology, identifies data sources (codebase, documentation, web), and defines analysis frameworks.

Research synthesis specialist transforming collected information into actionable insights. Cross-references findings, identifies patterns and relationships, applies analytical frameworks, and generates comprehensive research reports.

Generates structured solution alternatives from research synthesis and user preferences. Produces multi-perspective trade-off analysis with scope guardrails and convergence recommendation. Non-interactive content generator.

Transforms selected solution approach into high-level architecture design with C4 diagrams, component mapping, and MADR decision records. Non-interactive content generator.

Specification audit specialist with senior auditor perspective. Independently verifies completeness, detects ambiguities, validates implementability with evidence-based assessment. Never trusts claims - examines codebase and uses Azure/GitHub CLI for external verification.

Creates comprehensive specifications from gathered requirements. Searches for reusable code, writes spec.md with reusability analysis, and self-verifies quality. Receives pre-gathered requirements - does not interact with users.

Task classification specialist analyzing task descriptions and issue references to classify into 5 workflow types (development, performance, migration, research). Supports GitHub/Jira integration, codebase context analysis, and confidence scoring.

Execute a single task group from an implementation plan with continuous standards discovery. Writes code, runs tests, returns structured execution report. Does NOT mark checkboxes - main agent handles progress tracking.

Runs the full test suite and analyzes results. Identifies test command from project config, executes all tests (not just feature tests), reports pass/fail counts, flags regressions in unrelated areas, and categorizes failures. Read-only - reports issues without fixing. Does not interact with users.

Generates ASCII mockups showing UI layout and integration with existing components. Analyzes codebase to identify current layout patterns, reusable components, and navigation structure. Creates annotated diagrams showing where new UI elements fit. Use for UI-heavy features and enhancements.

Generates end-user documentation with screenshots using Playwright. Creates easy-to-understand guides for non-technical users. Use after features are implemented to create user-facing documentation.

Analyzes codebase using adaptive parallel Explore subagents based on task complexity. Selects agent roles from a pool, launches Explore agents, then delegates report generation to codebase-analysis-reporter subagent.

Unified orchestrator for all development tasks. ALWAYS execute when invoked — never skip for 'straightforward' tasks. Phases adapt based on detected task characteristics rather than predetermined types. Use for any development work that modifies code.

Internal engine for managing project documentation and technical standards in .maister/docs/. Handles file operations, INDEX.md generation, and .github/copilot-instructions.md integration. Invoked by maister-init, standards-update, and standards-discover skills.

Execute implementation plans by delegating each task group to task-group-implementer subagent. Main agent coordinates prepares context, invokes subagent, processes output, marks checkboxes, updates work-log. Uses lazy standards loading from INDEX.md with keyword-triggered discovery.

Verify completed implementations for quality assurance. Delegates all verification work to specialized subagents - completeness checking, test execution, code review, pragmatic review, production readiness, and reality assessment. Compiles results into comprehensive verification report. Read-only verification - reports issues but does not fix them. Use after implementation is complete and before code review/commit.

Initialize AI SDLC framework with intelligent project analysis and documentation generation

Orchestrates the complete migration workflow from current state analysis through implementation to compatibility verification. Handles technology migrations, platform changes, and architecture pattern transitions with adaptive risk assessment, incremental execution, and rollback planning. Use when migrating technologies, platforms, or architecture patterns.

Shared orchestration patterns for all workflow orchestrators. NOT an executable skill - provides reference documentation for phase execution, state management, interactive mode, and initialization. All orchestrators reference these patterns.

Orchestrates performance optimization workflows using static code analysis to identify bottlenecks (N+1 queries, missing indexes, O(n^2) algorithms, blocking I/O, memory leaks). Accepts optional user-provided profiling data. Reuses standard specification, planning, implementation, and verification phases.

Interactive product/feature design orchestrator. Transforms fuzzy ideas into structured product briefs through collaborative exploration, iterative refinement, and visual prototyping. Adaptive phases detect design complexity and adjust depth.

Quick bug fix with TDD red/green gates and complexity escalation

Orchestrates comprehensive research workflows from question definition through findings documentation. Handles technical, requirements, literature, and mixed research types with adaptive methodology, multi-source gathering, pattern synthesis, and evidence-based reporting. Supports standalone research tasks and embedded research phase in other workflows.

Discover coding standards from project configuration files, code patterns, documentation, and external sources (PRs, CI/CD)

Update or create project standards from conversation context or explicit description