Trellis
Give AI coding agents persistent project memory and engineering standards
All Skills in This Repository (22)
Pure Emerald Level Indicatorstrellis-spec-bootstrap
Generates project-specific Trellis coding specs from real codebase analysis.
trellis-before-dev
Loads project coding guidelines from .trellis/spec before writing code.
trellis-brainstorm
Guides requirements discovery and produces PRD, design, and implementation planning artifacts.
trellis-break-loop
Analyzes fixed bugs across five dimensions and captures prevention knowledge into spec files.
trellis-session-insight
Searches and extracts past AI coding session dialogue via the trellis mem CLI.
trellis-check
Verifies code changes against specs, lint, type checks, tests, and cross-layer consistency.
trellis-meta
Guides AI agents in understanding and customizing local Trellis project architecture.
trellis-channel
Coordinates multi-agent collaboration through Trellis channel event logs, workers, and forum threads.
trellis-update-spec
Captures executable contracts and coding conventions into .trellis/spec/ markdown documents.
trellis-start
Initializes AI coding sessions by loading project context, tasks, and guidelines from .trellis.
trellis-finish-work
Archives completed tasks and records session journals to close out coding sessions.
first-principles-thinking
Decompose problems into axioms and derive solutions through structured first-principles reasoning.
Frequently Asked Questions
FAQPage SchemaHow to install Trellis?βΌ
Run `npx skills add mindfold-ai/Trellis --all -g -y` in your terminal to install the full skill suite globally.
What problem does Trellis solve for AI coding?βΌ
AI agents normally forget your project conventions every session. Trellis stores specs, tasks, and journals in your repo so any agent works to your engineering standards automatically.
Does Trellis work with Cursor and Codex?βΌ
Yes. Trellis supports 22 AI coding platforms including Claude Code, Cursor, Codex, OpenCode, and Gemini CLI with the same shared workflow.
How does Trellis keep AI code quality high?βΌ
It runs a plan-implement-verify-finish loop where a check sub-agent reviews every diff against your specs and runs lint, type-check, and tests before you commit.
Can non-developers use Trellis?βΌ
You describe tasks in plain language and the agent handles planning and code, but Trellis is built for software projects, so basic familiarity with a code repository helps.
Related Repositories in Software Engineering
View All in Software Engineeringβopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core