Skip to content
Back to skills

Ask

ASecurity

Ask the zerograph index a question, an id or a symbol, then read the top hits

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agents

Works with

  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned November 11, 2026

npx -y skills add devmaxxx/zerograph --skill ask --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ask?

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

Security grade badge for Ask
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/devmaxxx-ask-zerograph/badge)](https://www.skillsdirectory.com/skills/devmaxxx-ask-zerograph)

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: ask
description: Ask the zerograph index a question, an id or a symbol, then read the top hits
---

Call the zerograph MCP server's `ask` tool with `question` set to what the user gave (<question | ID | Symbol>)

Pass the words as typed. Set `seeds: 8` only when the user wrote `--seeds 8` or asked for a wider
search, and `bodies: true` only when they asked for full requirement text. Never set `rerank`: it
spends model tokens, and that is the user's call.

Each top-level line of the answer is a seed, `path:line` first; a `└` line is a neighbour one hop
from the seed above it.

1. Open the top two or three seeds at their `path:line`, a window around the line, not
   the whole file. Skip a seed whose headline plainly answers something else.
2. Answer from what you opened, citing `path:line`. Nothing printed holds it: say so, and offer one
   rephrase or a wider search, not a directory walk.
3. A literal string, an env var or a flag is a text search's question, not the graph's: use rg.

Files in this skill

  • SKILL.md1009 B
  • agents/openai.yaml130 B

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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

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