关于
This skill lets developers query an AST-derived code graph to answer structural questions about their codebase, like finding callers, imports, or definitions. It automatically rebuilds from the repository and is accessed via a local Deeplake mount, requiring no build process. Use it for impact analysis, understanding architecture, or navigating dependencies.
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-graph在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Hivemind Code Graph
A deterministic, AST-derived map of the current repository — every function,
class, method, interface, type, enum, const, and module, plus the edges between
them (calls, imports, extends, implements, method_of). It is queried as
synthesized files under the Deeplake mount; there are no real files on disk and
no network call in the read path.
The graph builds and refreshes automatically (on Stop / SessionEnd, gated by a rate limit + git diff). You never run a build command — just read it.
Use it as a fast INDEX to locate the few files/symbols that matter, then open
them with Read to answer. It is not a substitute for the source.
When to use this skill
Activate when the user asks a structural / relational question about the code:
- "What calls
pushSnapshot?" / "Who uses this function?" - "What does
deeplake-pull.tsimport?" / "What depends on X?" - "Where is
GraphSnapshotdefined?" / "Find the function that handles Y." - "What are the main subsystems / the architecture here?"
- "If I change this signature, what's affected?" → use
impact/<symbol>(transitive blast radius)
When NOT to use this skill
- Reading the body of a symbol you already located → use
Readon the real source file. The graph gives location + relationships, not full source. - Code that isn't committed/built yet — the graph can lag uncommitted edits. If a file's mtime is newer than the build timestamp, read the live source.
- Languages outside TypeScript, JavaScript, and Python (Go, Rust, …) — the
extractor covers those three, with cross-file
calls/importsresolved for named imports. For anything else, fall back to grep/read.
Path cheat sheet
cat ~/.deeplake/memory/graph/index.md
# Overview: node/edge counts, kind breakdown, top files by node count.
cat ~/.deeplake/memory/graph/query/<pattern> # START HERE (the 2-in-1)
# Search + expand the top matches with their 1-hop neighbors (callers,
# callees, imports, heritage). Multi-token AND: query/<a>+<b>.
cat ~/.deeplake/memory/graph/find/<pattern>
# Case-insensitive substring search on node id + label (max 50 hits).
# Prints numbered handles [1] [2] ... saved for this worktree.
cat ~/.deeplake/memory/graph/show/<handle-or-pattern>
# <handle>: a digit from a prior find/ (e.g. 3).
# <pattern>: a substring → unique node detail, or a candidate list.
# Output: the node + its 1-hop neighbors grouped by edge relation.
cat ~/.deeplake/memory/graph/neighborhood/<file>
# Every symbol in a file + its cross-file neighbors (callers/callees/imports).
cat ~/.deeplake/memory/graph/impact/<pattern>
# Transitive dependents — the blast radius of changing a symbol.
cat ~/.deeplake/memory/graph/path/<from>/<to>
# Shortest dependency path between two symbol patterns (trace a flow across files).
cat ~/.deeplake/memory/graph/layers # architectural layers / subsystems
cat ~/.deeplake/memory/graph/tour # deterministic guided walkthrough
Workflow
- Broad? Start at
index.mdto see subsystems and the biggest files. - Looking for a symbol?
find/<name>(orquery/<name>) → pick the handle. - Want relationships?
show/<handle>/neighborhood/<file>→ callers/callees, imports. - Tracing a flow?
path/<from>/<to>. Change impact?impact/<symbol>. - Need the actual code? Take the
source_file:lineandReadit — don't answer from the graph alone.
Anti-patterns (read these)
- "Incoming (0)" does NOT mean dead code. Cross-file
callsare resolved for named imports (TS/JS/Python), but instance-method dispatch (obj.method()), dynamic calls, and nested/inner functions are NOT — a zero-incoming symbol may still be reached via one of those. Confirm in the source before calling it unused. - The graph can be stale. It rebuilds at most once per rate-limit window. The SessionStart inject prints the build age; if it's old or you've just edited a file, prefer the live source for that file.
- Don't try to build it. There is no user-facing build step in normal use; the hooks handle it. Just read the mount.
find/is lexical, not semantic. It matches substrings, not meaning —find/authwon't surfacelogin/credentialsunless those strings appear in the id/label. Try multiple keywords if the first misses.
GitHub 仓库
常见问题
什么是 hivemind-graph Skill?
hivemind-graph 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-graph 相关的任务。
如何安装 hivemind-graph?
使用本页的安装命令:将 hivemind-graph 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-graph 属于哪个分类?
hivemind-graph 属于元分类。
hivemind-graph 可以免费使用吗?
可以。hivemind-graph 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。
