trellis-spec-bootstarp

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

1|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/MaplumeX/Milesto --skill trellis-spec-bootstarp-maplumex
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: trellis-spec-bootstarp
Source: https://github.com/MaplumeX/Milesto/tree/main/.agents/skills/trellis-spec-bootstarp
Command: npx skills add https://github.com/MaplumeX/Milesto --skill trellis-spec-bootstarp-maplumex

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Teams adopting Trellis often end up with generic template specs that do not reflect their actual codebase, giving future agents misleading or empty guidance. This Skill bootstraps or refreshes .trellis/spec/ guidelines grounded in real source files, tests, and architecture. ## Core Features & Use Cases - Repository Analysis: Uses GitNexus code knowledge graphs, ABCoder UniAST parsing, and direct source reads to discover package boundaries, runtime layers, and core abstractions. - Spec Decomposition & Planning: Splits spec work by package or layer only when it matches real ownership boundaries, with a PRD-shaped task template for traceability. - Evidence-Backed Spec Writing: Writes spec files with concrete file paths, examples, and anti-patterns, then verifies no placeholder text or broken index files remain. - Use Case: After initializing Trellis in a monorepo, run this Skill to analyze each package with GitNexus and ABCoder, then produce tailored .trellis/spec/ docs that teach agents the project's actual conventions. ## Quick Start Ask the agent to bootstrap the Trellis specs for this repository by analyzing the codebase and filling .trellis/spec/ with project-specific guidance.

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 project-specific Trellis spec files?▼

Run the single-agent workflow: inspect the existing .trellis/spec tree, analyze the repository with GitNexus and ABCoder, decompose work by real package or layer boundaries, then write specs backed by actual source files and tests.

What tools analyze a codebase for spec generation?▼

GitNexus builds a code knowledge graph for module boundaries, execution flows, and blast radius, while ABCoder parses code into UniAST for exact signatures and type shapes. Direct source reads verify findings before they become spec rules.

Does this workflow require a specific agent platform or CLI?▼

No, the workflow is platform-neutral and uses a single-owner agent model. GitNexus and ABCoder are configured through whatever MCP mechanism the agent host provides, and helper subagents are optional.

How do I set up GitNexus and ABCoder MCP servers?▼

Run npx gitnexus analyze from the repo root and configure npx -y gitnexus mcp as the server command. For ABCoder, install via go install, parse packages with abcoder parse, and serve them with abcoder mcp pointing at the AST output directory.

When should spec work be split into multiple tasks?▼

Split only along real ownership boundaries: one task per package with distinct conventions, per layer with different rules, or per cross-cutting pattern spanning packages. A small library usually needs one focused spec pass.

How do I verify Trellis specs have no placeholder text?▼

Run grep -R for placeholder patterns like "To be filled" or "TODO: fill" inside .trellis/spec, then check that index.md files match the final spec set and every rule cites a real source file, test, or project document.