Skip to content
Back to skills

Graphify Status

ASecurity

Report knowledge-graph label coverage across every graphify-enabled project on this machine — communities, labels, and how many nodes still render as "Community NN". Use on `/graphify-status`, or when asked which graphs are stale, unlabelled, or degraded.

  • 3 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added September 5, 2026
ai-agentsbashnode

Security analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned September 22, 2026

npx -y skills add bravros/bravros --skill graphify-status --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Graphify Status?

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

Security grade badge for Graphify Status
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bravros-graphify-status/badge)](https://www.skillsdirectory.com/skills/bravros-graphify-status)

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: graphify-status
description: Report knowledge-graph label coverage across every graphify-enabled project on this machine — communities, labels, and how many nodes still render as "Community NN". Use on `/graphify-status`, or when asked which graphs are stale, unlabelled, or degraded.
trigger: /graphify-status
---

# /graphify-status

> Read [briefing.md](references/briefing.md) on demand for detailed context and instructions.

One table, every graphify project on the machine, answering a single question: **does `graphify query` return real names, or is it still handing back `Community 417`?**

## Quick Start

Run the scanner:

```bash
uv run ~/.agent_config/skills/graphify-status/scripts/graphify-status.py
```

Print the table verbatim. Do not re-measure by hand or re-format it — the script is the source of truth.

Options:
- `--json`: machine-readable rows instead of table
- `--depth N`: walk depth per root (default 3)
- `--no-prompt`: skip auto-generating labelling prompts
- `<root> ...`: scan specific roots instead of the defaults (`~/Code`, plus `~/Sites` if present)

## Key Rules

- **Degraded graphs**: If a run reports degraded coverage, follow the prompt verdict in `/tmp/graphify-label/<project>-relabel-prompt-N.md`.
- **Merge results**: Merge completed label JSONs using `merge-missing-labels.py` (additive, never overwrites without `--force`).
- **Never use `collate-labels.py`** for partial relabels.

Files in this skill

  • SKILL.md1.4 KB
  • references/briefing.md8.4 KB
  • scripts/emit-relabel-prompt.py8.4 KB
  • scripts/graphify-status.py8.6 KB
  • scripts/merge-missing-labels.py7.1 KB
  • skill.yaml2.1 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.