Builds reusable agent skills from a short brief by filling in the requirements it leaves out and pulling working procedures from public docs, repositories and papers. It then packages the admitted procedures as installable skills you can reuse.
@agentsopeCross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric — is…
@agentsopeSOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format +…
@agentsopeScreens biomedical / life-science papers for signs of data fabrication, image manipulation, and statistical anomalies, using the…
@agentsopeUniversal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix…
@agentsopeDecision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural…
@agentsopeCoder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k…
@agentsopeSOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules…
@agentsopeSplit a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a…
@agentsopeSOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory,…
@agentsopeSOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace +…
@agentsopeBuild and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks…
@agentsopeOperating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when…
@agentsopeIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
