
from swe-af712
Orchestrates a coordinated multi-agent engineering workflow to plan, implement, test, and merge production-grade changes across single or multiple repositories.
SWE-AF provides a runtime that spins up a coordinated team of AI agents (planning, coding, review, QA, merge, verification) to execute software engineering work as a directed acyclic graph. It supports local and GitHub-driven workflows, producing draft PRs, execution artifacts, and verification reports. Use it to automate feature implementation, cross-repo coordination, and integration testing.
Inferred support for model-backed coding runtimes and CLI-driven backends such as Claude Code, OpenCode-style providers, and generic LLM coding agents (e.g., Codex/GLM/Gemini-like toolchains).
SWE-AF is a multi-agent autonomous software engineering fleet that orchestrates planning, coding, review, QA, and merge workflows via DAG-based parallelism. No bundled scripts were found — the SKILL.md is purely instructional documentation. The documentation is thorough with clear installation steps, configuration tables, and endpoint references, but lacks any executable scripts to validate runtime behavior.
No scripts present — static analysis only. The skill is documentation-only with no executable content. All curl examples target localhost, no external data exfiltration. Legitimate multi-agent orchestration tool.