Skip to content
Back to skills

Oracle

ASecurity

Bundles prompts and files with the Oracle CLI. Use when explicitly requesting that CLI or preparing a focused unresolved question for an external model.

  • 81 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 8, 2026
tools

Works with

  • cli

Security analysis

A100/100

Scanned September 8, 2026

npx -y skills add edmundmiller/dotfiles --skill oracle --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Oracle?

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

Security grade badge for Oracle
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/edmundmiller-oracle/badge)](https://www.skillsdirectory.com/skills/edmundmiller-oracle)

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: oracle
description: Bundles prompts and files with the Oracle CLI. Use when explicitly requesting that CLI or preparing a focused unresolved question for an external model.
---

# Rules

## The Oracle

- Oracle bundles a prompt plus the right files so another AI (GPT 5 Pro + more) can answer. Use when stuck/bugs/reviewing.
- Run `npx -y @steipete/oracle --help` once per session before first use.

## Self-improvement

- Codify repeated corrections in the smallest durable surface that owns them:
  - reusable procedure → update an existing skill; create one only after repeat evidence
  - repository fact or convention → nearest `AGENTS.md` or canonical document
  - parseable invariant → hook, lint, test, or validator
  - truly universal scope, authority, or evidence invariant → propose a bounded
    `config/agents/core.md` change
- Do not create a second global rule bundle or put project facts in the thin core.
- Keep the active task in scope. Report a useful learning when writing it would
  require broader authority.
- Update agent memory only when the user explicitly requests a memory change.

## Tool-specific memory

- Actively think beyond the immediate task.
- When using or working near a tool the user maintains: if you notice patterns, friction, missing features, risks, or improvement opportunities, jot them down.
- Do **not** interrupt the current task to implement speculative changes.
- When note-taking is authorized, use the repository's existing idea or
  improvement location instead of creating a parallel convention:
  - `reference/ideas/<tool-name>.md` — new concepts or future directions
  - `reference/improvements/<tool-name>.md` — enhancements to existing behavior
- These notes are informal, forward-looking, and may be partial.
- Otherwise report the observation without changing files.

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.