ai-virtuoso
claude2 AI engineering skills: LLM evals and LLM observability
43 skills
20 agents (specialists and roles), 3 team workflows, and the verification skill, plus headless wrapper skills for CI review, test gaps, migration planning, dependency audit, and refactor scans
Plugin agents-virtuoso from marketplace code-virtuoso in krzysztofsurdy/code-virtuoso. Commands read from the repo's manifest — 16 days ago.
acceptance-verifierAcceptance criteria compliance checker. Maps code changes against acceptance criteria one-by-one, reporting PASS/FAIL/PARTIAL/UNTESTED per criterion. Delegate when you need to verify that implementation satisfies its specification before merging.
architectSystem architecture agent for technical design, component boundaries, API contracts, technology choices, and ADRs. Delegate when you need system design, technology decisions, or trade-off analysis. Use proactively for design reviews.
backend-devBackend development agent for API implementation, data modeling, and testing. Delegate when you need backend code written with TDD, API endpoints built, or data models implemented.
cold-reviewerZero-context code reviewer. Reviews changes cold - no spec, no project knowledge, no domain context. Catches what familiarity blinds you to. Delegate when you want a fresh-eyes pass before merging, or as part of a multi-perspective review.
dependency-auditorAudit project dependencies for security vulnerabilities, outdated packages, and license issues. Delegate for dependency health checks.
doc-writerGenerate or update documentation from code changes - changelogs, API docs, migration guides. Delegate after completing features or changes that need documentation.
frontend-devFrontend development agent for UI implementation, component architecture, and testing. Delegate when you need UI components built, API integrations wired, or accessibility issues fixed.
implementerTDD implementation agent. Delegate when you have a concrete plan and want isolated red-green-refactor execution in a worktree.
instruction-auditorRead-only audit of a repository's agent instruction files (AGENTS.md, CLAUDE.md, rules, Cursor and Copilot instructions, GEMINI.md, skill descriptions). Delegate when instructions are ignored, a rules file keeps growing, before sharing or publishing instruction files, or when you need a review for s
investigatorRead-only deep exploration of a specific codebase area. Delegate when you need structured investigation of how something works, where something is used, or what a subsystem does.
migration-plannerAnalyze database migration files and produce safe migration plans with zero-downtime strategies and rollback paths. Delegate before running migrations.
plan-auditorAudits planning artifacts in two modes. Gate mode checks that requirements, design, and stories are aligned before implementation starts and returns READY, NEEDS WORK, or NOT READY. Change-impact mode traces a requirement change, blocker, or scope shift across the plan and drafts a change proposal.
product-managerProduct management agent for requirements gathering, PRD writing, prioritization, and acceptance criteria. Delegate when you need user stories, scope decisions, or prioritization analysis. Use proactively when requirements are unclear.
project-managerProject management agent using PRINCE2 principles for delivery planning, risk management, and progress tracking. Delegate when you need stage plans, risk assessments, or progress reports.
qa-engineerQA engineering agent for test planning, test case design, bug reporting, and release sign-off. Delegate when you need test plans written, bugs investigated, or release quality assessed. Use proactively after feature completion.
refactor-scoutScan code for structural health - code smells, duplication, complexity hotspots, and refactoring opportunities. Delegate for codebase health assessments.
researcherRead-only researcher that answers a question from local files, official docs and the web, and returns a sourced report with confidence labels. Delegate for "research X", "compare A and B", "what is the best practice for", "is this still recommended", or any fact that may have changed since training.
reviewerCode review agent. Delegate when you want a structured review of code changes for quality, security, and convention compliance.
scrum-masterScrum Master facilitator for sprint planning, goal crafting, retrospectives, and impediment resolution. Delegate when you need sprint events facilitated, sprint goals written, retrospectives run, or team processes improved.
test-gap-analyzerFind untested code paths in changed files - missing test cases, uncovered edge cases, and integration gaps. Delegate after implementation to verify coverage.
2 AI engineering skills: LLM evals and LLM observability
43 skills
6 framework skills: Symfony upgrade, PHP upgrade, Composer dependencies, Godot and Godot upgrade, and Vercel AI SDK
43 skills
6 knowledge skills: accessibility, context engineering, debugging, docs lookup, performance, and security
43 skills
8 playbook skills: spec-driven development, TDD, branch finishing, PR feedback, handoff, hooks and guardrails, game feature loop, and security research
43 skills
13 tool skills: rules writer, ticket writer, agent creator, skill writer, skill measure, plugin creator, research, brainstorming, communication style, PR message writer, report writer, stakeholder update writer, and UI review
43 skills
Claude Code only. A backlog-driven delivery loop that feeds the agent one small item at a time and accepts it only when verify commands pass and a write-boundary guard approves. Also opt-in guard hooks, a settings hardener, a setup audit (doctor), setup evals against vanilla Claude Code, and starter templates. Ships hooks, scripts, commands, and 2 skills
3 skills · 10 commands · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.