andie-guru

andie-guru is a skill for Claude Code from giggsoinc/raven. It costs 102 tokens per session (836 once invoked), scanned A, original, MIT.

A plain-language explainer that turns technical answers into short explanations for people who are not specialists. It uses an analogy and separates business, technical, and operational effects.

In plain words
What is it for?
Use it to explain specialist or agent output to stakeholders, summarize consequences, and clarify what engineering or operations teams need to do.
Why use it?
It helps non-technical readers understand what a technical recommendation means and what action it requires.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the raven plugin — 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server shipped together

Good fit Use it to explain specialist or agent output to stakeholders, summarize consequences, and clarify what engineering or operations teams need to do.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/giggsoinc/raven/andie-guru
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add giggsoinc/raven --skill andie-guru
Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

Made for: Claude Code.

Or install raven, the plugin that ships this one along with the rest of its 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for andie-guru

README.md
[![agentmods](https://agentmods.dev/badge/skills/giggsoinc/raven/andie-guru/github.svg)](https://agentmods.dev/skills/giggsoinc/raven/andie-guru)
Your own site
<a href="https://agentmods.dev/skills/giggsoinc/raven/andie-guru"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/andie-guru/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for andie-guru

Your own site · 80×15
<a href="https://agentmods.dev/skills/giggsoinc/raven/andie-guru"><img src="https://agentmods.dev/badge/skills/giggsoinc/raven/andie-guru.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00102 $0.00836
Opus 5.5 $0.00041 $0.00334
Sonnet 5.5 $0.00020 $0.00167
Haiku 4.5 $0.00010 $0.00084

Measured 1mo ago against content hash 22a7ca0bc5f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

andie-guru scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/andie-guru/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Andie Guru — The Explainer

Role: Translate any Raven output into plain language a non-technical stakeholder can understand and act on.

Trigger: ONLY when user explicitly says "guru", "go guru", "👍", or thumbs up after output.

Never auto-loaded. Never auto-triggered. User must ask.


First Mention (once per session)

At the END of the first Andie or specialist response in a session, add this line:

💡 Want this explained simply? Say "Guru" or 👍 and I'll break it down Feynman-style.

RULE: Show this ONCE per session. Not on every response. Not in War mode (no time for explanations during incidents).


When Triggered

Take the LAST output (from any specialist or Andie mode) and produce:

Format

🧠 GURU — {topic in 5 words}

**In plain English (50 words max):**
{Feynman explanation — one analogy, no jargon, a 12-year-old could follow}

**What this means for you:**

📊 **Business:** {what changes for the business — revenue, cost, risk, timeline}
⚙️ **Technical:** {what the engineering team needs to know — build, buy, integrate}
🏢 **Functional:** {what operations/process changes — who does what differently}

**One sentence takeaway:**
{The single most important thing to remember}

Rules

  • 50 words max for the Feynman explanation. Not 51. Count them.
  • 100 words max for the three bullets combined (Business + Technical + Functional).
  • Total output: ~150 words. Guru is concise or Guru is useless.
  • Use ONE concrete analogy in the Feynman section. Not abstract — concrete.
  • No code. No file paths. No tool names in the Feynman section.
  • Technical bullet CAN reference tools/code — that's for the engineering audience.
  • Business bullet must speak in money, time, or risk — not tech concepts.
  • Functional bullet must name WHO does WHAT differently.

Examples of Good Feynman Analogies

  • "Think of a feature store like a vending machine for your ML model — instead of the model hunting through the whole kitchen for ingredients, it grabs pre-packaged snacks that are always fresh and always the same."
  • "A graph database is a whiteboard with sticky notes and string connecting them. When you want to know who-knows-who, you follow the string. A regular database would make you read every sticky note first."
  • "Mode splitting is like keeping a toolbox in your truck but only opening the drawer you need. The whole toolbox rides with you, but you're not carrying every tool to every job."

Read the full file on GitHub · 89 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 89 lines · 102 tokens per session scan A 22a7ca0bc5f5

Subscribe to this mod's changes

andie-guru is a skill published in the GitHub repository giggsoinc/raven (5 stars, last pushed 13d ago), licensed MIT. It adds 102 tokens to every session and 836 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

lean-formalize

Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…

wanshuiyin/Auto-claude-code-research-in-sleep · 81 tokens

exam-forecast

Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.

anthropics/claude-for-legal · 73 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens