cursor-debate
io.github.go-go-golems/docmgr/cursor-debate
发起研究先行、多视角的辩论,基于具体代码库证据探讨复杂技术决策(权衡取舍、架构选型、集成策略)。当用户要求“辩论”方案、比较选项,或在决策前需要结构化探索时使用。
“Cursor” 共 783 个结果
io.github.go-go-golems/docmgr/cursor-debate
发起研究先行、多视角的辩论,基于具体代码库证据探讨复杂技术决策(权衡取舍、架构选型、集成策略)。当用户要求“辩论”方案、比较选项,或在决策前需要结构化探索时使用。
io.github.go-go-golems/docmgr/cursor-remarkable-upload
通过本地上传脚本将 Markdown(含 docmgr 工单文档)作为 PDF 上传到 reMarkable 设备,支持安全的 dry-run 与可选的工单结构镜像。当用户要求把文档发送到 reMarkable、为 reMarkable 将 Markdown 导出为 PDF,或排查 rmapi/pandoc/xelatex 问题时使用。
io.github.go-go-golems/docmgr/cursor-docmgr
使用 docmgr CLI 管理工单式文档(创建工单、添加文档、用 file-note 关联代码文件、更新变更日志与检索)。当用户询问 docmgr 用法、需要 docmgr 命令序列,或想要 docmgr 最佳实践(file-note、引用、doctor)时使用。
io.github.YPares/agent-skills/cursor-agent-supervisor
把范围明确的委派给子智能体,例如让某个子智能体按一组规格实现功能。当任务不需要了解整个项目的宽泛背景时应使用本技能。
v0.24.3
io.github.vshulcz/claude-codex-cursor-agent-memory-deja-vu
Local memory & session search across forty-nine coding agents: Claude Code, Codex, Cursor.
v1.1.1
io.github.tnvolman/arch-cursor-plugin
Paid theological review of faith text (arch_review) plus free offline KJV verse lookup (kjv_lookup).
v2.1.0
net.ts.tail45da3a.cursor/qwen-mcp
Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.
v4.1.0
site.chatgpt.cursoraikk.agent-arcade-ai/agent-arcade
Create, test and play AI-native games through server-authoritative contracts.
v1.0.1
io.github.CursorTouch/Windows-MCP
面向 Windows 操作系统计算机使用的 MCP 服务器。
io.github.cursor/plugins/poteto-mode
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
io.github.cursor/plugins/setup-pstack
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
io.github.cursor/plugins/interrogate
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Adversaries try to break a change or design, and only findings proven by a run survive.
io.github.cursor/plugins/arena
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
io.github.cursor/plugins/reflect
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
io.github.cursor/plugins/recall
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.
io.github.cursor/plugins/no-comments
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
io.github.cursor/plugins/how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
io.github.cursor/plugins/architect
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
io.github.cursor/plugins/principle-prove-it-works
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
io.github.cursor/plugins/advisor
顾问模式。在关键检查点咨询更强(或不同)的模型:重大决策前、卡在错误上时、以及宣布任务完成前。当用户输入 /advisor、要求开启或关闭顾问、选择顾问模型,或显式请求更强/不同模型给出第二意见时使用。切勿自行启用。
io.github.cursor/plugins/typescript-best-practices
TypeScript 最佳实践。在读取或编辑任意 .ts、.tsx 文件时使用。
io.github.cursor/plugins/triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
io.github.cursor/plugins/reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
io.github.cursor/plugins/orchestrate
仅当用户显式输入 `/orchestrate <目标>` 时使用:拆解大型任务,通过 Cursor SDK 派生并行云代理 worker/子规划者/校验者的树,并收集结构化交接结果;切勿自主调用。