trellis-meta

Guides customization of local Trellis workflow, hooks, agents, and platform files.

Updated Jun 9, 2026
One-click install
npx skills add https://github.com/gyc-12/Archipelago --skill trellis-meta-gyc-12
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trellis-meta
Source: https://github.com/gyc-12/Archipelago/tree/main/.cursor/skills/trellis-meta
Command: npx skills add https://github.com/gyc-12/Archipelago --skill trellis-meta-gyc-12

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? After running trellis init, AI assistants often lack a map of the generated .trellis/ directory and platform integration files, leading to edits in the wrong place (like node_modules or upstream source) instead of the user project. This Skill gives the AI a complete architectural model and customization entry points so local Trellis behavior is modified correctly. ## Core Features & Use Cases - Local Architecture Reference: Explains the three-layer model (workflow, persistence, platform integration) covering .trellis/workflow.md, tasks, specs, workspace journals, and context injection. - Platform File Map: Documents where hooks, settings, agents, skills, commands, and workflows live across Claude Code, Cursor, Codex, OpenCode, Kiro, Gemini, Copilot, and other platforms. - Customization Playbooks: Step-by-step guides for changing workflow phases, task lifecycle hooks, context loading, agent behavior, skills/commands, and spec structure. - Use Case: A user says "make the check agent run our lint command before reviewing." The AI reads the change-agents reference, locates the platform's trellis-check agent file, and edits it without touching upstream Trellis source. ## Quick Start Ask the AI to use the trellis-meta skill to change the planning-phase behavior in this project's .trellis/workflow.md.

Frequently Asked Questions about trellis-meta

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I customize Trellis workflow phases in my project?

Edit .trellis/workflow.md in your project, which is the local workflow source of truth. Update the Phase Index, phase sections, routing table, and the relevant [workflow-state:STATUS] blocks, then check that platform skills and commands still describe the same flow.

How do I change trellis-implement or trellis-check agent behavior?

Edit the platform agent file in your project, such as .claude/agents/trellis-implement.md or .cursor/agents/trellis-check.md. Keep role boundaries intact, specify read order (active task, PRD, JSONL, specs), and define write boundaries explicitly.

Which platforms does Trellis support for hooks and agents?

Trellis generates platform files for Claude Code, Cursor, OpenCode, Codex, Kiro, Gemini CLI, Qoder, CodeBuddy, GitHub Copilot, Factory Droid, and Pi Agent, plus workflow-based platforms like Kilo, Antigravity, and Windsurf. Actual directories depend on which trellis init flags were run.

Why does my AI agent not read the current task or specs?

Context loading fails when the session-start or sub-agent hooks are not registered, or the task JSONL manifests are missing entries. Run task.py current --source and task.py validate to confirm task state, then inspect the platform hook or agent prelude.

Should I edit node_modules or the Trellis npm package to customize behavior?

No. Customization targets are the generated files inside your project: .trellis/ and platform directories like .claude/ or .cursor/. Only modify upstream Trellis source when explicitly contributing a PR or changing the npm package itself.

Where should team coding conventions live in a Trellis project?

Put long-term engineering conventions in .trellis/spec/ under the appropriate layer with an index.md entry point. For project-specific AI capabilities, create a project-local skill rather than editing the public trellis-meta skill.