跳到正文
cccskills
免费在 GitHub 公开

cognee-architecture

Explain a repository's architecture (modules, routes, storage, services), find risky hotspots, draw a Mermaid diagram of the code graph, or review how far a change reaches, from Cognee's code graph.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Explain architecture from code facts

Visible search progress

Before running a Cognee search, send one short user-visible progress sentence, for example: "Searching Cognee for the earlier decision…" or "Checking Cognee's code graph for callers of this function…". Name Cognee in the normal working text before the tool call; keep this to one update per related search batch. Afterwards, describe relevant findings, an empty result, or a failed search accurately. Do not claim Cognee improved the answer merely because a search ran.

Run "${CLAUDE_PLUGIN_ROOT}/scripts/cognee-doctor.sh" --json and check cognee_server before these queries. architecture, insights, and diagram output require server 1.6.3 or newer. For an older or unknown version, explain the requirement and stop these operations; do not silently replace them with invented architecture. Index with the existing cognee-code skill if no graph exists.

Cloud indexing requires a git URL, for example:

"${CLAUDE_PLUGIN_ROOT}/scripts/cognee-index-repo.sh" https://github.com/org/repo --wait 60

Cloud facts reflect pushed commits. Identify that revision/freshness when local changes have not been pushed and re-indexed. Cloud servers cannot read local paths.

Use these existing search commands (the code dataset resolves from the checkout; add --dataset <name> for a different indexed repository):

"${CLAUDE_PLUGIN_ROOT}/scripts/cognee-search.sh" "architecture" --code --code-query '{"operation":"architecture","diagram":"mermaid"}'
"${CLAUDE_PLUGIN_ROOT}/scripts/cognee-search.sh" "hotspots" --code --code-query '{"operation":"insights","diagram":"mermaid"}'
"${CLAUDE_PLUGIN_ROOT}/scripts/cognee-search.sh" "process_payment" --code --code-query '{"operation":"impact_analysis","targets":["process_payment"],"diagram":"mermaid"}'
"${CLAUDE_PLUGIN_ROOT}/scripts/cognee-search.sh" "changes" --code --code-query '{"operation":"delta"}'

architecture gives the module, route, storage, and service map. insights gives Enola explainer findings and their supporting facts. impact_analysis follows the named target's dependencies; replace the example with the user's actual symbol. delta describes changes from the last index, not an arbitrary unindexed diff.

Cite fact names, files, and lines when explaining findings. Separate structural facts from your interpretation of risk. Render diagram.source in a Mermaid block when requested; if the result has no diagram, say so. Ask for an exact candidate when a seed is ambiguous. Verify important claims against source before editing.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

codebase

免费

Use when indexing a code repository into Cognee's code graph or querying it (callers, impact analysis, paths, endpoints) from Antigravity.

中文简介正在准备中。当前显示原文说明。

topoteretes/cognee-integrations1012026年10月22日 更新

codebase

免费

Use when indexing a code repository into Cognee's code graph or querying it (callers, impact analysis, paths, endpoints) from Codex.

中文简介正在准备中。当前显示原文说明。

topoteretes/cognee-integrations1012026年10月22日 更新

Index a repository (local path or git URL) into Cognee's code graph and answer exact structural queries with no LLM calls: callers, dependencies, impact of changing a symbol, call paths, endpoints, re-index changes.

中文简介正在准备中。当前显示原文说明。

topoteretes/cognee-integrations1012026年10月22日 更新

A digest of a week or more of the user's own coding-agent sessions (default 7 days): sessions per day and project, most-edited files and the lessons Cognee learned, written up as shipped, decided and still open.

中文简介正在准备中。当前显示原文说明。

topoteretes/cognee-integrations1012026年10月22日 更新

A multi-day digest of the user's own coding-agent sessions — sessions per day and project, most-edited files, and every lesson Cognee distilled into the knowledge graph in that window. Use only when the user explicitly asks for a weekly digest, a retro, a recap or report of their recent sessions, or asks for the `cognee-digest` skill by name. Not for questions about code or the current task.

中文简介正在准备中。当前显示原文说明。

topoteretes/cognee-integrations1012026年10月22日 更新

Use when an agent must stand up the OpenClaw↔Cognee integration with FalkorDB as the vector + graph store. This skill is SELF-CONTAINED — it tells you to generate every file (Dockerfile, sitecustomize.py, docker-compose.yaml) from the exact contents below, build a custom Cognee image that loads the FalkorDB adapter, run Cognee + FalkorDB together, self-verify the adapter registered, and point the OpenClaw cognee plugin at it (including per-agent graphs). No other files in this directory are required.

中文简介正在准备中。当前显示原文说明。

topoteretes/cognee-integrations1012026年10月22日 更新

查看 topoteretes 的全部技能

报告此技能的问题