lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Collaborative requirements discovery session optimized for AI coding workflows. Creates task directories, seeds PRDs, runs codebase research, proposes concrete implementation approaches with trade-offs, and converges on MVP scope through structured Q&A. Use when requirements are unclear, multiple implementation paths…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Deep post-fix bug analysis across five dimensions: root cause categorization, fix failure analysis, prevention mechanisms, systematic expansion, and knowledge capture. Updates .trellis/spec/ guides with lessons learned to prevent recurring bugs. Use when a debugging session completes, after fixing a tricky bug, when…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Post-implementation verification across multiple code dimensions: cross-layer data flow, code reuse analysis, import path validation, and same-layer consistency checks. Identifies missed update sites, type mismatches, and duplicated constants. Use when changes span 3+ architectural layers, after modifying shared…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Validates recently written code against project-specific development guidelines from .trellis/spec/. Identifies changed files via git diff, discovers applicable spec modules, runs lint and typecheck, and reports guideline violations. Use when code is written and needs quality verification, to catch context drift…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Scaffolds a new skill file with proper naming conventions and structure. Analyzes requirements to determine skill type and generates appropriate content. Use when adding a new developer workflow skill, creating a custom skill, or extending the Trellis skill set.
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Pre-commit quality checklist covering lint, typecheck, tests, code-spec sync, API changes, database migrations, cross-layer verification, and manual testing. Blocks commit if infra or cross-layer specs lack executable depth. Use when code is written and tested but not yet committed, before submitting changes, or as a…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Analyzes changed files and improves unit test coverage using project-specific testing conventions from .trellis/spec/ unit-test specs. Determines test scope (unit vs integration vs regression), adds or updates tests following existing patterns, and runs validation. Use when code changes need test coverage, after…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Adapts an external skill into project-specific development guidelines in .trellis/spec/. Creates guideline sections, code example templates with .template suffix, and updates spec indexes. Use when integrating an external skill, adding a new skill's patterns to project conventions, or incorporating third-party skill…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Interactive three-part onboarding for new team members to the Trellis AI-assisted workflow system. Covers core philosophy (AI memory, project-specific knowledge, context drift), system structure and command deep-dives, real-world workflow examples, and guideline customization. Use when a new developer joins the…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Records completed work progress to .trellis/workspace/ journal files after human testing and commit. Captures session summaries, commit hashes, and updates developer index files for future session context. Use when a coding session is complete, after the human has committed code, or to persist session knowledge for…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or…
lxyer/multi-agent-collaboration-system
Skill Claude CodeCodex
Captures executable contracts and coding knowledge into .trellis/spec/ documents after implementation, debugging, or design decisions. Enforces code-spec depth for infra and cross-layer changes with mandatory sections for signatures, contracts, validation matrices, and test points. Use when a feature is implemented, a…
lxyer/multi-agent-collaboration-system
Agent Claude Code
Code quality check expert. Reviews code changes against specs and self-fixes issues.
lxyer/multi-agent-collaboration-system
Agent Claude Code
Issue fixing expert. Understands issues, fixes against specs, and verifies fixes. Precise fixes only.
lxyer/multi-agent-collaboration-system
Agent Claude Code
Multi-Agent Pipeline main dispatcher. Pure dispatcher. Only responsible for calling subagents and scripts in phase order.
lxyer/multi-agent-collaboration-system
Agent Claude Code
Code implementation expert. Understands specs and requirements, then implements features. No git commit allowed.
lxyer/multi-agent-collaboration-system
Agent Claude Code
Multi-Agent Pipeline planner. Analyzes requirements and produces a fully configured task directory ready for dispatch.
lxyer/multi-agent-collaboration-system
Agent Claude Code
Code and tech search expert. Pure research, no code modifications. Finds files, patterns, and tech solutions.
lxyer/multi-agent-collaboration-system
Command Claude Code
Read the relevant development guidelines before starting your task.
lxyer/multi-agent-collaboration-system
Command Claude Code
Guide AI through collaborative requirements discovery before implementation, optimized for AI coding workflows.
lxyer/multi-agent-collaboration-system
Command Claude Code
When debug is complete, use this command for deep analysis to break the "fix bug -> forget -> repeat" cycle.
lxyer/multi-agent-collaboration-system
Command Claude Code
Check if your changes considered all dimensions. Most bugs come from "didn't think of it", not lack of technical skill.
lxyer/multi-agent-collaboration-system
Command Claude Code
Check if the code you just wrote follows the development guidelines.