analyzer
01syahiidkamil/Software-Engineer-AI-Agent-Atlas
Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
393 2mo ago A 0 tokens
comparator
02syahiidkamil/Software-Engineer-AI-Agent-Atlas
Agent Claude Code
Compare two outputs WITHOUT knowing which skill produced them.
393 2mo ago A 0 tokens
grader
03syahiidkamil/Software-Engineer-AI-Agent-Atlas
Agent Claude Code
Evaluate expectations against an execution transcript and outputs.
393 2mo ago A 0 tokens
Agent
Reviews a worker's diff for semantic HTML, ARIA correctness, keyboard navigation, focus order, and color contrast. Dispatch only on tasks that touch UI/markup/styling — skip entirely for backend, CLI, or data-only tasks.
0 1mo ago A 51 tokens
original MIT
architecture
05Agent
Reviews a worker's diff for coupling, layering violations, SOLID breaches, and contract adherence against the repo's existing module boundaries. Dispatch on any task that adds a module, crosses an existing boundary, or defines/consumes a shared interface.
0 1mo ago A 51 tokens
original MIT
Agent
Reviews a worker's diff for missing public-API docs, README/doc drift, and comments that no longer match the actual behavior. Dispatch on tasks that add/change a public interface, CLI flag, config option, or documented behavior.
0 1mo ago A 48 tokens
original MIT