Skill Detail

Prepare Evidence-Backed Open Source Contribution Proposals with ContribAI

Use ContribAI when an agent should analyze a repository, respect maintainer consent, and prepare bounded draft contribution proposals with evidence receipts.

Code Quality & ReviewMulti-Framework
Code Quality & Review Multi-Framework Published
⭐ 246 GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill prepare-evidence-backed-open-source-contribution-proposals-with-contribai Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
At a glance
Tools required
ContribAI CLI; Git; Rust stable for source builds or the published release installer; optional GitHub token and model API key for connected workflows.
Install & setup
Install a release with curl -fsSL https://raw.githubusercontent.com/tang-vu/ContribAI/main/install.sh | sh, or clone the repository and run cargo install –path crates/contribai-rs –locked. Start with contribai demo, contribai analyze, contribai target, contribai run, contribai patrol, or contribai mcp-server before enabling any submit flow.
Author
tang-vu
Publisher
Open Source
Last updated
Aug 10, 2026
Quick brief

Use ContribAI when an agent/operator needs to analyze an open source repository and prepare small, reviewable contribution proposals under maintainer-governed admission rules. The operator runs ContribAI in read-only analysis mode by default, checks repository consent through a manifest or approved issue label, creates a bounded proposal, records an evidence capsule, and only submits a draft pull request when explicit write capability, current consent, validation checks, and human review all pass.

How it works

What this skill actually does

Invoke this instead of using a coding assistant or GitHub workflow normally when the hard problem is not code generation, but responsible contribution admission: proving consent, bounding changed paths and line counts, protecting governance files, preserving the base revision, and making review evidence explicit before any external write.

The scope boundary is maintainer-consent and evidence governance for AI-assisted open source contributions. This is not a general browser automation, GitHub automation, or LLM coding product listing; it is a constrained proposal pipeline for accountable contributors and maintainers.