skills.rest
tower
towerOFFICIAL
Explore all skills by this author →
WebsiteGitHub

gather-context

Detect project stack and conventions to generate a structured project profile.

19|Updated Apr 1, 2026
Search Tags:#automation#codebase#conventions#project-context#profile#tower
One-click install
npx skills add https://github.com/tower/agentic-data-engineering --skill gather-context-tower
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gather-context
Source: https://github.com/tower/agentic-data-engineering/tree/main/.claude/skills/gather-context
Command: npx skills add https://github.com/tower/agentic-data-engineering --skill gather-context-tower

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Detects existing project stack, learns conventions from code, and produces a structured project profile at .tower/project-profile.md. Other skills read this profile in their Step 0 to adapt to existing codebases instead of assuming greenfield.

Core Features & Use Cases

  • Stack detection scans common project indicators (pyproject.toml, Towerfile, Tower reviews) and reports app type and signals.
  • Convention learning: extracts inferred patterns and writes a centralized project profile for downstream skills.
  • Quick setup: creates .tower/project-profile.md and enables contextual automation across workflows.

Quick Start

Run the gather-context skill on your repository to generate a comprehensive project profile at .tower/project-profile.md.

Frequently Asked Questions about gather-context

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

FAQPage Schema
How do I detect existing project conventions and stack automatically?▼

To detect project conventions automatically, you can run a context-gathering process that scans code and configuration files to generate a structured project profile for downstream automation.

What is a project profile and when do I need to generate one?▼

A project profile is a structured document recording your stack and inferred code patterns. You need to generate one when you want automation tools to adapt to an existing codebase instead of assuming a greenfield setup.

How do I bootstrap setup for an existing codebase without starting from scratch?▼

You can bootstrap setup for an existing codebase by analyzing project indicators like pyproject.toml to extract conventions, writing the results to a centralized profile file that other workflows read at activation.

Can I use project context detection for data engineering workflows?▼

Yes, project context detection applies to data engineering and software projects, scanning configuration files to identify app types and signals so downstream skills can adapt to existing infrastructure.

Does the project profile generation read metadata from pyproject.toml?▼

Yes, profile generation optionally reads Tower metadata and dependencies from pyproject.toml and Towerfile to enrich the structured project profile output.

What are the limitations of auto-detecting project context?▼

Auto-detecting project context relies on scanning common project indicators, so it may miss custom or undocumented conventions that are not reflected in your code and configuration files.

Related Skills

Explore More Software Engineering Skills→
tankpkgtankpkg
1

@tank/tank-project-setup

Detects project stack and configures Tank skills and CI/CD pipelines.

Official
Intermediate
rubykachurubykachu
1

skill-scaffold

Generate project-level AI agent skills and convention files for codebases.

Community
Advanced
zxpmailzxpmail
18

dev-planner

Transform Product-Spec.md into structured development plans with phased milestones.

Community
Advanced
cinjoffcinjoff
1

map-codebase

Analyze software codebase structure and documentation using parallel agents.

Community
Advanced