feed-badger

Contributes reusable project improvements back to the ai-badger framework as draft pull requests.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Improvements made inside a project — new skills, personas, invariants, or instructions — often stay trapped in that repo instead of benefiting the shared ai-badger framework. This Skill detects those additions, generalizes them, and opens a draft PR against the framework for human review. ## Core Features & Use Cases - Candidate Detection: detect_additions.py diffs .ai-badger/ against manifest.json and emits new and changed files as structured JSON candidates. - Generalization Workflow: Guides classification of each candidate as agnostic, generalizable, or project-specific, stripping repo names, domain terms, and absolute paths before placement. - Guarded Draft PRs: open_pr.py stages only explicitly declared paths, scans them for credential-shaped literals, and opens a draft PR via gh — never auto-merging. - Use Case: After refining a code-review persona in a scaffolded project, run this Skill to detect the change, generalize it, place it under the right stack/feature path, and open a draft PR to Arasz/ai-badger. ## Quick Start Ask the agent to feed the reusable improvements in this repo back to the ai-badger framework as a draft PR.

Frequently Asked Questions about feed-badger

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

FAQPage Schema
How do I contribute a skill or persona back to the ai-badger framework?

Run detect_additions.py to list new or changed files in .ai-badger/, classify and generalize the reusable ones, place them in an ai-badger checkout under the correct stack/feature path, then run open_pr.py to open a draft PR against Arasz/ai-badger.

How does feed-badger detect which files changed in a project?

It diffs the .ai-badger/ directory against manifest.json, which records what the framework originally scaffolded. Files not in the manifest are new candidates; files whose content hash differs from the recorded hash are changed candidates.

Can I use feed-badger on a repo not scaffolded by ai-badger?

No. Detection relies on .ai-badger/manifest.json for provenance, so the repo must have been scaffolded by welcome-ai-badger first. Without a manifest, the detection script exits with an error.

Does feed-badger merge contributions automatically?

No. Contributions are always opened as draft PRs via gh pr create --draft, and a human reviews and merges them. Auto-merging is explicitly forbidden by the Skill's rules.

What prevents secrets from being committed in a contribution PR?

open_pr.py scans every declared path for credential-shaped literals before staging anything and refuses the PR if a finding occurs, naming the file and pattern shape. It is a guard over known literal shapes, not a proof of cleanliness.

Why does open_pr.py require the --path argument?

The --path flag is required and repeatable so only explicitly declared paths are staged with git add. This prevents unrelated dirty files in the checkout from accidentally riding along in the contribution PR.