Skip to content
Back to skills

Graph Read

ASecurity

Read and resolve Potpie Context Graph entities, views, timelines, and status.

  • 247 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 8, 2026
businessbackend

Works with

  • cli

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned September 8, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill graph-read --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Graph Read?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Graph Read
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-graph-read/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-graph-read)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: graph-read
description: "Read and resolve Potpie Context Graph entities, views, timelines, and status."
metadata:
  disco-role: operating
disable-model-invocation: true
license: Apache 2.0
---

# Potpie graph read

Use this sub-skill when the task is about discovering, resolving, searching, or inspecting information already stored in Potpie's Context Graph.

## Read this when

- The user asks about `potpie resolve`, `potpie search`, `potpie graph catalog`, `potpie graph read`, `potpie graph search-entities`, `potpie graph describe`, `potpie graph neighborhood`, `potpie graph inspect`, `potpie graph export`, `potpie timeline recent`, or `potpie graph status`.
- A graph read returns empty, unsupported, or ambiguous results.
- You need to choose between root convenience commands and the graph workbench read surface.

## Do not use this for

- Writing memories, proposals, inbox, quality, or nudge operations: read `../graph-write/SKILL.md`.
- Pot/source binding before reads: read `../workspace-boundaries/SKILL.md`.
- Runtime/daemon availability: read `../runtime/SKILL.md`.
- Provider credential acquisition: read `../auth-integrations/SKILL.md`.

## Operating procedure

1. Use `resolve` for intent-driven context packages and `search` for broad memory search.
2. Use `graph catalog` to discover supported subgraphs, views, includes, and entity labels before constructing a detailed read.
3. Use `graph read` for named views and included context; use `graph search-entities` when you first need canonical entity keys.
4. Use `graph describe`, `graph neighborhood`, and `timeline recent` for entity-level explanation, graph locality, and recent events.
5. Diagnose empty results by checking scope filters, source/pot binding, include support, and daemon/backend readiness before assuming the memory is absent.

## References

- `references/workflow.md` — read command matrix, named views, includes, scopes, and identity-resolution choices.
- `references/troubleshooting.md` — unsupported includes, empty-vs-unsupported results, scope mismatch, ranking, and daemon symptoms.

## Verification notes

- Safe native candidates include graph CLI contract, graph-surface-lite contract, read orchestrator, P9 reader, envelope, ranking, timeline endpoint, graph views, and scope-match tests.
- No accelerator backend is required for read-side CLI/contract verification.

Files in this skill

  • SKILL.md2.3 KB
  • references/troubleshooting.md2.5 KB
  • references/workflow.md3.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.