关于
This skill handles both team goals/KPIs and individual tasks through the `hivemind` CLI, replacing the legacy tasks system. Use it when users mention objectives, milestones, or any actionable work items. It requires CLI execution only—file writes won't sync to shared team storage.
快速安装
Claude Code
推荐npx skills add activeloopai/hivemind -a claude-code/plugin add https://github.com/activeloopai/hivemindgit clone https://github.com/activeloopai/hivemind.git ~/.claude/skills/hivemind-goals在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Hivemind Goals — CLI only (Hermes)
⚠️ CRITICAL: On this runtime (Hermes), you MUST use the hivemind shell CLI for goals + KPIs. DO NOT use write_file on ~/.deeplake/memory/goal/... paths — those writes go to the local filesystem and never reach the team-shared hivemind_goals table. Other team members will NOT see them.
The hivemind-memory skill describes a generic memory layout — it does NOT apply to goals/KPIs. For goals/KPIs, use the CLI below.
Commands (invoke via terminal tool)
hivemind goal add "<text>" # create goal, prints goal_id
hivemind goal list [--mine|--all] # list (default --mine)
hivemind goal done <goal_id> # mark closed
hivemind goal progress <goal_id> <opened|in_progress|closed>
hivemind kpi add <goal_id> <kpi_id> <target> <unit> [name] # add KPI to goal
hivemind kpi list <goal_id> # list KPIs for goal
hivemind kpi bump <goal_id> <kpi_id> <delta> # increment current (int)
Workflow when the user expresses a goal
hivemind goal add "<short description>"— capture stdout, that's thegoal_id(UUID).- If the user explicitly asks for KPIs:
hivemind kpi add <goal_id> <slug> <target> <unit>per KPI. - Tell the user the goal_id and that it is now team-visible in Deeplake.
Capture a task for later (with resumable context)
When the user parks a tangential task mid-session — "save this for later", "remind me to …", "don't let me forget …", "let's do X later" — store enough context to resume cold later, not just a one-liner. Tag it --agent capture so parked side-tasks are separable from hand-made goals:
hivemind goal add --agent capture "Add rate-limiting to the webhook handler
Start here: add a per-IP token bucket on the handler entry path
Files: src/webhook/handler.ts:120-160, src/webhook/limits.ts
Branch: feat/webhook-hardening
Run: pnpm test webhook
Why: bursty clients hammer the endpoint; defer until retry-backoff lands"
Line 1 is the label (what goal list shows). Fill Start here / Files / Branch / Run / Why from the conversation; Start here: matters most. Pass the whole package as one double-quoted argument so the newlines are preserved.
Resume a parked task (automatic context transfer)
When the user says "let's work on that task / goal" or "pick up the <X> task":
hivemind goal list --mine— match the user's reference to agoal_id.hivemind goal get <goal_id>— prints the full package (goal listshows only the first line, so always usegoal get). Read it as your working context.hivemind goal progress <goal_id> in_progress— mark it started.- Begin from
Start here:using theFiles/Branch/Runlines. Continue as if the context was never lost.
What NOT to do
- Do NOT call
write_fileon any path under~/.deeplake/memory/goal/or~/.deeplake/memory/kpi/. - Do NOT do
mkdir/cat >to create those files manually via terminal. - Do NOT auto-generate KPIs unless the user explicitly asks.
If the user wants to inspect goals you created, run hivemind goal list --mine (terminal) and present the output.
GitHub 仓库
常见问题
什么是 hivemind-goals Skill?
hivemind-goals 是一个 Claude Skill,作者为 activeloopai。Skill 将 Claude 按需加载的说明和资源打包,让 Claude 无需额外提示即可执行与 hivemind-goals 相关的任务。
如何安装 hivemind-goals?
使用本页的安装命令:将 hivemind-goals 作为插件添加到 Claude Code,或将其仓库克隆到 skills 目录,然后重启 Claude 以加载该 Skill。
hivemind-goals 属于哪个分类?
hivemind-goals 属于元分类。
hivemind-goals 可以免费使用吗?
可以。hivemind-goals 已收录在 AIMCP,可免费安装。
相关推荐技能
Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
