跳到正文
cccskills
免费在 GitHub 公开

cognee-search

Search Cognee memory. Session memory is automatically searched on every prompt via hooks. Use this skill explicitly for permanent knowledge graph search, filtered category search, or when you need more results than the automatic lookup provides.

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.md3.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Cognee Memory Search

Search both session memory and the permanent knowledge graph, optionally filtered by data category.

Automatic session search

Session memory is searched automatically on every user prompt via the user-prompt-submit hook. You do not need to run this skill to access current-session context.

Data categories

Knowledge is organized into three categories via node_set:

CategoryNode setContains
useruser_contextUser preferences, corrections, personal facts
projectproject_docsRepository docs, code context, architecture decisions
agentagent_actionsTool call logs, reasoning traces, generated artifacts

Instructions

Use the cognee_recall tool to search Cognee memory. It calls the running Cognee server (POST /api/v1/recall) directly in-process — no shell, no subprocess.

One broad search is usually enough — the user-prompt-submit hook already injects session/trace/graph context every turn, so avoid running many targeted searches.

Search via the cognee_recall tool

cognee_recall(query="your search query", top_k=10, scope="auto")
  • scope="auto" — session cache + permanent graph (default)
  • scope="graph" — permanent graph only
  • scope="session" — current session only

Filter by category (optional)

Categories (user_context / project_docs / agent_actions) filter by node set. Use a direct curl to pass node_name:

curl -s -X POST "${COGNEE_BASE_URL:-http://localhost:8011}/api/v1/recall" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: ${COGNEE_API_KEY:-}" \
  -d '{"query": "...", "top_k": 5, "only_context": true, "scope": ["graph"], "node_name": ["project_docs"]}'

Ground-truth a suspicious result (debugging)

The server is authoritative. If a search returns empty but you expect content, confirm directly — do not conclude "not found" from an empty result without checking:

curl -s -X POST "${COGNEE_BASE_URL:-http://localhost:8011}/api/v1/recall" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: ${COGNEE_API_KEY:-}" \
  -d '{"query": "...", "top_k": 5, "only_context": true, "scope": ["graph"]}'

If the response is an {"error": ...} object rather than a list, the server was reachable but rejected/failed the request — that's an error, not "no results".

Understanding results

Results include a _source field:

  • "session" — from the session cache (current conversation)
  • "graph" — from the permanent knowledge graph

Session entries tagged with [category:agent] are automatic tool call logs.

Decision table

SignalAction
Need current session contextAlready automatic, no action needed
User explicitly says "search cognee"cognee_recall(query="...")
"what does the codebase do" / "what did we do last time"cognee_recall(query="...", scope="graph")
Need a specific categoryuse the node_name curl form above
Auto context insufficientcognee_recall(query="...", scope="session")
Result empty but you expect contentGround-truth via the curl above before concluding "not found"

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 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

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

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。

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

查看 topoteretes 的全部技能

报告此技能的问题