welcome-ai-badger

Scaffolds repositories with ai-badger agent instructions, personas, and skills via detection scripts.

2|Updated Jul 18, 2026
One-click install
npx skills add https://github.com/Arasz/ai-badger --skill welcome-ai-badger-arasz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: welcome-ai-badger
Source: https://github.com/Arasz/ai-badger/tree/main/features/common/skills/welcome-ai-badger
Command: npx skills add https://github.com/Arasz/ai-badger --skill welcome-ai-badger-arasz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jsonschema, and includes scripts (resource) and references (resource) components.

What problem does it solve? Setting up a repository with consistent AI coding agent configuration (CLAUDE.md, copilot-instructions, personas, invariants, skills) is manual and error-prone. This Skill automates onboarding by detecting a repo's stacks and agents, then generating a tailored .ai-badger/ directory plus each agent's discovery files. ## Core Features & Use Cases - Automated Detection: detect.py proposes stacks (with transitive requires), coding agents (claude/copilot/hermes/pi), source control platform, and build/test/lint commands from the target repo. - Deterministic Scaffolding: scaffold.py builds .ai-badger/ (config.json, manifest.json, CLAUDE.md, agents/, instructions/, invariants/, skills/) and writes agent discovery copies, preserving hand-authored files and keep-marker regions. - Validation & Recovery: validate.py checks the authored config against the JSON schema, and a structured error-recovery table guides fixes for common failures. - Use Case: Point it at a new or mature repository, confirm the proposed config, and get a complete, idempotent agent-instruction setup with provenance recorded in manifest.json. ## Quick Start Ask the agent to run welcome-ai-badger to scaffold this repository with ai-badger agent instructions and confirm the detected stacks.

Frequently Asked Questions about welcome-ai-badger

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

FAQPage Schema
How do I set up Claude Code or Copilot instructions in an existing repo?

Run the detect script to propose a config, author config.json with your project summary and persona routing, validate it, then run scaffold.py. It writes CLAUDE.md, .github/copilot-instructions.md, and the .ai-badger/ source-of-truth directory while preserving hand-authored files.

How does repository stack detection work in ai-badger?

detect.py matches each stack's detectionSignals globs from index.json against the repo, plus dependency heuristics from package.json and .csproj files. It expands transitive requires and filters to stacks the framework knows.

Will scaffolding overwrite my existing CLAUDE.md file?

No. A discovery file without the ai-badger managed header is treated as hand-authored and left untouched; the scaffold emits a preserved note. Pass --overwrite-agent-files to force the old copy-over behavior.

How do I decline a skill or persona after scaffolding?

Name it in the exclude section of config.json, for example {"skills": ["mcp-index"]}. Deleting the delivered file does not work because the next refresh regenerates it.

What dependencies does the welcome-ai-badger scaffold flow need?

The framework scripts require Python 3 with the jsonschema package, installed via pip from the framework's engine/requirements.txt. A valid framework root with index.json, schemas/, and features/ must also be locatable.

How do I update an already-scaffolded project with new framework releases?

Use the den-refresh skill instead of re-running welcome. It re-scaffolds with your existing config.json without re-detection, preserves seed-once files like state.json, and reports what changed.