Tooluck logoTooluck
SKILL.md

atlas-graph-query

Agent skill froma5c-ai/babysitter

Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)

How to install atlas-graph-query

install atlas-graph-query
# install the babysitter pack with the skills CLI
npx skills add a5c-ai/babysitter

# or add only this skill to Claude Code: copy the folder

plugins/atlas-unified/skills/atlas-graph-query/

# into

~/.claude/skills/atlas-graph-query/ (all projects)

.claude/skills/atlas-graph-query/ (one project)

plugins/atlas-unified/skills/atlas-graph-query/SKILL.md

MITFull file
1# atlas-graph-query
2
3A thin reference for the Atlas knowledge-graph MCP tool surface so any agent
4(including sub-agents) can query the graph without re-deriving conventions. The
5server URL is wired natively by the `atlas` plugin and is overridable via
6`ATLAS_MCP_URL`. Never invent node ids — only use ids returned by these tools.
7
8> **Position: this is the SECONDARY / enrichment layer.** The `atlas` plugin is
9> scan-first — it inventories your REAL systems by scanning your actual sources
10> (Azure via read-only `az`, git repos, local directories) and process/data
11> mining them. The graph queries below are used ONLY to add best-practice /
12> comparison context to those already-discovered real systems. Do NOT use the
13> graph as the primary content, and never pad a real inventory with generic
14> catalog nodes. Tie every graph lookup back to a real scanned system.
15
16## Tools
17
18### `mcp__atlas__atlas_public_search`
19Full-text/semantic search over the graph. Key params: `q` (query), optional
20`kind` filter, `limit`. Prefer it to find seed/anchor nodes from need terms.
21
22### `mcp__atlas__atlas_public_record`
23Fetch one node's full record by `id` (fields + edges). Use `expandNeighbors` to
24pull immediate relations in one call. Prefer it to read detail once you have ids.
25
26### `mcp__atlas__atlas_public_neighbors`
27Traverse the graph from a node. Key params: `id`, `depth`, `edges` (edge-kind
28filter), `kinds` (node-kind filter). Prefer it to expand a subsystem from anchors.
29…

Excerpt shown under the repository's MIT license.

More skills in babysitter

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates