Skip to content
Back to skills

Concept Glossary

ASecurity

Names the concept whenever the user describes something that has an established term — in engineering, design, marketing, product, psychology, business, or everyday life — then silently logs it to a running GLOSSARY.md with a plain-English definition and the real context it came up in. Use continuously; also use when the user asks what they've learned, wants to search the glossary, or wants it exported.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 6, 2026
ai-agentsgodatabase

Works with

  • cli

Security analysis

A100/100

Scanned September 6, 2026

npx -y skills add Fred-In-tech/learn-as-you-build --skill concept-glossary --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Concept Glossary?

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

Security grade badge for Concept Glossary
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fred-in-tech-concept-glossary/badge)](https://www.skillsdirectory.com/skills/fred-in-tech-concept-glossary)

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: concept-glossary
description: "Names the concept whenever the user describes something that has an established term — in engineering, design, marketing, product, psychology, business, or everyday life — then silently logs it to a running GLOSSARY.md with a plain-English definition and the real context it came up in. Use continuously; also use when the user asks what they've learned, wants to search the glossary, or wants it exported."
---

# Concept Glossary — Name It, Then Log It

Most people can describe a concept long before they know its name. Handing them the name converts a fuzzy paragraph into a single word they can recall, search, and say out loud to a colleague.

## When to Activate

**Always on.** Trigger on the *description*, not the vocabulary — the user is explaining a thing without knowing the word for it.

Also activate on: *"what have I learned"*, *"what's that term for…"*, *"show my glossary"*, *"quiz me"*, or any export/publish request.

## The Move

One short line, then continue the work:

> "What you're describing is called **[term]** — [one-line plain-English definition]."

Then keep going. This is an aside, not a detour.

### Examples

> **User:** "I want the button to feel like it's pushing back when you tap it."
> **You:** That's **haptic affordance** — a physical cue confirming the interface registered your input. Adding it now…

> **User:** "Why does the second one feel cheaper at the same price?"
> **You:** **Anchoring** — the first number your brain sees becomes the ruler for everything after.

> **User:** "It's slow because we ask the database once per row instead of all at once."
> **You:** That's the **N+1 query problem**. Batching it now.

## Rules

1. **Name it once, briefly.** No history lesson unless asked.
2. **Only real, established terms.** Never invent a label to seem clever. If no genuine term exists, say so plainly — a confidently-used fake term will embarrass the user in front of an expert.
3. **Never interrupt the task.** One line, then back to work.
4. **Skip it when they clearly already know the term.**
5. **Correct gently.** If they're using a term slightly wrong, note the distinction in a few words.
6. **Most-used term wins.** If several fit, give the common one; mention a cousin only if genuinely useful.

## Logging

Every named term is appended to `GLOSSARY.md` — **silently**. Never announce the logging; the one-line aside is the entire visible footprint.

### Entry format

```markdown
### <Term>
**Field:** <Engineering | Design | Marketing | Product | Psychology | Business | Finance | Film/Video | General>
**Definition:** <one plain-English sentence — no jargon defining jargon>
**Came up when:** <the real thing they were doing, in their words where possible>
**Date:** YYYY-MM-DD
```

### Logging rules

1. **Append-only.** Never rewrite or delete past entries — the history is the value.
2. **No duplicates.** Grep first. If the term exists but the new context is richer, append a second `**Came up when:**` line to the existing entry.
3. **Plain-English definitions.** If the definition needs its own glossary lookup, rewrite it. Test: would it make sense read aloud to someone outside the field?
4. **`Came up when` is mandatory and specific.** "While pricing the upgrade screen" — not "discussing pricing." Context is the memory hook; a term with no anchor is a flashcard nobody recalls.
5. **Correct, don't delete.** If a logged term turns out to be misapplied, strike it with a short note. Seeing the mistake is worth more than a clean file.

## Retrieval

| Ask | Do |
|---|---|
| "What have I learned?" | Summarize by field, newest first, with counts |
| "What was that term about X?" | Grep definition + context, return the entry |
| "Show my glossary" | Render the file, grouped and readable |
| "Quiz me" | Show `Came up when` + `Definition`, hide the term, ask them to name it |

## Export & Publish

Portable by design — plain Markdown.

**Publishing is outward-facing. Confirm scope before the first push.** Once a destination is approved, routine updates there don't need re-confirmation; a *new* destination always does.

**Sanitize before any public push.** Terms and definitions are generic, but `Came up when` lines may name real clients, unreleased products, or internal numbers. Genericize them — "while building a courier dispatch flow", not the client's name. Keep the full detail in the local copy.

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…