Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.trytrellis.app/llms.txt

Use this file to discover all available pages before exploring further.

What is Trellis?

AI’s capabilities grow like vines: full of vitality but spreading everywhere. Trellis is scaffolding for AI, guiding it along the path of your conventions. Supported platforms: Claude Code, Cursor, OpenCode, Codex, Kiro, Kilo, Gemini CLI, Antigravity, Windsurf, Qoder, CodeBuddy, GitHub Copilot, Droid, Pi Agent, plus any agent that reads the .agents/skills/ standard (Amp, Cline, Deep Agents, Firebender, Kimi Code CLI, Warp, and more).

One-Line Summary

Trellis is training wheels for AI coding assistants. It automatically injects your project specs into every AI session, so the AI writes code following your standards instead of improvising.
AI’s capabilities grow like vines, full of vitality but spreading everywhere. Trellis is scaffolding for AI, guiding it along the path of your conventions.

Comparison with Traditional Approaches

Dimension.cursorrulesCLAUDE.mdSkillsTrellis
Spec injection methodManually loaded each conversationAuto-loaded but easily truncatedUser-initiatedAuto-injection (hooks on capable platforms, prelude on others), precisely loaded per task
Spec granularityOne large fileOne large fileOne per SkillModular files, composed per task
Cross-session memoryNoneNoneNoneWorkspace journal persistence
Workflow enforcementNoneNoneNoneAuto-trigger skills + check sub-agent verify loop
Team sharingSingle userSingle userShareable but no standardGit-versioned Spec library
Platform supportCursor onlyClaude Code onlyPer platform14 configured platforms + shared skill ecosystem

Core Concepts at a Glance

ConceptDescriptionLocation
SpecYour coding standards, written in Markdown. AI reads specs before writing code.trellis/spec/
WorkspaceEach developer’s session logs, letting AI remember what was done last time.trellis/workspace/
TaskA work unit containing requirements docs and context configuration.trellis/tasks/
SkillAuto-triggered workflow modules: brainstorm, before-dev, check, update-spec, break-loopplatform-specific skills dir
Sub-agentSpecialized AI sub-process: trellis-research, trellis-implement, trellis-checkplatform-specific agents dir
CommandExplicit session entries: finish-work, continue, and manual start where neededplatform-specific commands dir
HookAuto-triggered scripts that inject context at session start, sub-agent launch, etc. (platforms with hook support).claude/hooks/, etc.
JournalSession log files recording what was done in each development session.trellis/workspace/{name}/journal-N.md

Why Trellis?

FeatureProblem Solved
Auto-InjectionRequired specs and workflows auto-inject into every conversation. Write once, apply forever
Auto-updated Spec LibraryBest practices live in auto-updated spec files. The more you use it, the better it gets
Skill-first WorkflowMost operations are auto-trigger skills. AI picks the right one without manual commands
Team SyncShare specs across your team. One person’s best practice benefits everyone
Session PersistenceWork traces persist in your repo. AI remembers project context across sessions

Quick Start

Install Trellis and set up your first project in 5 minutes.

Architecture

Understand specs, tasks, hooks, and workspaces.

Commands & Skills

Reference for slash commands (/start, /finish-work) and auto-trigger skills.

Writing Specs

Turn blank templates into executable contracts with trellis-update-spec.