yellow-core

Run setup for all installed marketplace plugins. Checks local prerequisites, MCP visibility, environment variables, and plugin status, then offers interactive setup for plugins that need it.

Generate and install an adaptive Python statusline for yellow-plugins. Auto-detects installed plugins and their MCP servers, previews the result, and writes to ~/.claude/settings.json on confirmation. Re-run after installing new plugins.

Explore a feature or problem through iterative Q&A and optional research before planning. Produces docs/brainstorms/<date>-<topic>-brainstorm.md for /workflows:plan to auto-detect.

Document a recently solved problem to compound team knowledge into memory or solution docs

Transform feature descriptions into structured implementation plans

Session-level review of plan adherence, cross-PR coherence, and scope drift with autonomous P1 fix loop

Execute implementation plans systematically with testing and quality checks

Scan git worktrees, evaluate staleness, and remove stale worktrees with safeguards

Technology researcher specializing in discovering and synthesizing best practices from authoritative sources. Use when implementing new features, evaluating libraries, or establishing architectural patterns.

Git archaeology specialist. Traces the origins and evolution of code changes. Use when investigating why code exists, identifying experts for code areas, or understanding change patterns.

Expert repository research analyst. Analyzes repository structure, documentation, conventions, and implementation patterns. Use when exploring unfamiliar codebases or auditing existing projects.

Architectural compliance reviewer evaluating SOLID principles, component boundaries, coupling/cohesion, dependency direction, and API contract stability. Use when reviewing architectural decisions or assessing design quality of new features.

YAGNI enforcement and simplification analysis (pre-fix pass). Use when running full review passes to ensure code is minimal, removing unnecessary abstractions, premature optimizations, and unused features. For post-fix simplification, see code-simplifier (yellow-review).

Code pattern analysis specialist detecting anti-patterns, naming convention violations, duplication, and inconsistency across codebases. Use when reviewing PRs that introduce new patterns, new directories, new file type conventions, checking codebase consistency, or when changes touch agents/*.md, commands/*.md, skills/*/SKILL.md, or plugin.json files (plugin authoring convention checks).

Performance bottleneck analysis specialist. Identifies algorithmic complexity issues, database query problems (N+1), memory management concerns, caching opportunities, and network optimization. Use when reviewing code for performance issues or optimizing hot paths.

Language-idiomatic code reviewer for TypeScript, Python, Rust, and Go. Ensures code follows language-specific best practices, idioms, and conventions. Use when reviewing code in multi-language codebases or checking language-specific patterns.

Security audit specialist scanning for OWASP top 10 vulnerabilities, input validation issues, authentication/authorization flaws, hardcoded secrets, injection attacks, and XSS. Use when auditing code for security issues or reviewing changes that touch auth, input handling, or data access.

Test quality and coverage analysis specialist for full test suite audits. Evaluates test structure, naming conventions, edge case coverage, mock usage, and assertion quality. Use when auditing test suites, identifying coverage gaps, or improving test strategy. For PR-scoped test analysis, use pr-test-analyzer (yellow-review) instead.

Iterative brainstorm dialogue — questions, research, approaches, doc write. Input: feature topic or empty string. Output: docs/brainstorms/<date>-<topic>-brainstorm.md. Use when running /workflows:brainstorm.

Extract and document recently solved engineering problems using parallel subagents. Use when spawned by /workflows:compound to capture solutions, or after /review:pr to compound review findings into docs/solutions/ and MEMORY.md.

User experience flow analyst and requirements engineer. Examines specifications through the lens of the end user. Use when reviewing requirements, identifying gaps in specifications, or validating user journey completeness.

Reference guide for iterative brainstorm dialogues — question techniques, YAGNI, approach exploration, and research escalation. Use when running /workflows:brainstorm or authoring brainstorm-style agents.

Expert guidance for creating Claude Code skills and agents. Use when working with SKILL.md files, authoring new skills, creating slash commands, or designing agent workflows.

Git worktree management for isolated parallel development. Use when reviewing PRs in isolation, working on multiple features simultaneously, or when workflows offer worktree option.

Canonical patterns for ruvector recall/remember and morph discovery integration. Use when authoring commands or agents that should leverage institutional memory and advanced editing tools.