sarkarsaurabh27

sarkarsaurabh27/agent-loop-learning

Command Claude Code

Load and present a specific best-practice reference document by topic keyword.

sarkarsaurabh27/agent-loop-learning

Command Claude Code

Goal: execute on issues found. Apply concrete, benchmark-backed improvements to the agent in this repo.

sarkarsaurabh27/agent-loop-learning

Command Claude Code

Goal: review and show only. Audit an agent design against the best-practice reference docs and surface findings. Do not modify any files, write code, or execute fixes. The user (or /improve-agent) decides what to do with the findings.

sarkarsaurabh27/agent-loop-learning

Cursor rule Cursor

Load and present a best-practice reference document. Triggers when user asks for best practices on a topic, or asks to learn about orchestration, memory, tools, security, prompting, verification, or performance.

sarkarsaurabh27/agent-loop-learning

Cursor rule Cursor

Generate targeted improvement recommendations for an agent component. Triggers when user asks to improve an agent, or mentions a specific component (orchestration, memory, tools, security, performance, prompting, verification).

sarkarsaurabh27/agent-loop-learning

Cursor rule Cursor

Review or audit any agent design against the best-practice reference docs in this repo. Triggers when user asks to review, audit, or check an agent design.