agentsope

Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechan...

SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules / AGENTS.md) so that a coder...

Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edi...

SkillAlchemy — 一念落地，万象成形。输入任意想法或蒸馏目标，输出可安装的 SKILL.md。 内部编排 Lens（看清问题）和 LEAP（执行蒸馏/融合）。用户唯一入口。 Use when 用户说「蒸馏」「生成 skill」「融合」「我想做 X 但不知道从哪下手」。

Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step...

Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule...

Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric — is single-agent + tools enough?...

SkillAlchemy — 一念落地，万象成形。输入任意想法或蒸馏目标，输出可安装的 SKILL.md。 内部编排 Lens（看清问题）和 LEAP（执行蒸馏/融合）。用户唯一入口。 Use when 用户说「蒸馏」「生成 skill」「融合」「我想做 X 但不知道从哪下手」。