trellis-spec-bootstarp

Generate project-specific Trellis coding specs from real codebase analysis.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/dev2019zheng/codex-beacon --skill trellis-spec-bootstarp-dev2019zheng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trellis-spec-bootstarp
Source: https://github.com/dev2019zheng/codex-beacon/tree/main/.cursor/skills/trellis-spec-bootstarp
Command: npx skills add https://github.com/dev2019zheng/codex-beacon --skill trellis-spec-bootstarp-dev2019zheng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Generic spec templates produce placeholder-filled documentation that does not reflect how a repository actually works. This Skill bootstraps or refreshes .trellis/spec/ guidelines grounded in the real codebase, so future agents receive concrete, source-backed coding rules instead of boilerplate. ## Core Features & Use Cases - Repository Analysis: Uses GitNexus code knowledge graphs, ABCoder AST parsing, and direct source reads to map package boundaries, runtime layers, data flow, and error handling patterns. - Spec Decomposition and Writing: Splits spec work by package or layer only when the codebase justifies it, then writes rules with real file paths, examples, and anti-patterns. - Verification Pass: Checks for placeholder text, broken links, and index files that do not match the final spec set. - Use Case: After adopting Trellis in a monorepo, run this Skill to analyze each package and produce .trellis/spec/ docs that teach future agents the project's actual command handler, testing, and configuration conventions. ## Quick Start Analyze this repository and create project-specific Trellis spec files under .trellis/spec based on the real source code.

Frequently Asked Questions about trellis-spec-bootstarp

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

FAQPage Schema
How do I create Trellis spec files for my repository?

Initialize Trellis, then analyze the codebase with GitNexus, ABCoder, or direct source reads to identify packages and layers. Write spec files under .trellis/spec with concrete rules, real file paths, and anti-patterns drawn from the actual code.

What tools help analyze a codebase before writing coding specs?

GitNexus builds a code knowledge graph for module boundaries, execution flows, and impact analysis. ABCoder parses code into UniAST for exact signatures, types, and references. Direct source and test reads should confirm findings before they become spec rules.

Does this workflow require a specific AI agent or platform?

No, the workflow is platform-neutral and uses a single-agent model by default. GitNexus and ABCoder are optional MCP tools configured through whatever mechanism your agent host provides, and helper subagents are optional rather than required.

How do I set up GitNexus and ABCoder MCP servers?

Run npx gitnexus analyze from the repository root, then register npx -y gitnexus mcp as an MCP server. For ABCoder, install via go install, parse packages with abcoder parse, and register abcoder mcp pointing at the output directory.

When should spec work be split into multiple tasks?

Split by package when a package has its own conventions, or by layer when one package has distinct frontend, backend, CLI, or shared-library rules. Small libraries usually need only one focused spec pass rather than artificial decomposition.