Explain

Learns how to explain things to your human. Adapts format, depth, and style by topic.

Security Scan

This instruction-only skill is internally consistent with its stated purpose: it personalizes explanation style, stores a local preference file in your home directory, and does not request external credentials or install anything.

Purpose & Capability

Name/description (adaptive explanation) match the content: guidance files and runtime SKILL.md all focus on formatting, depth, domains, and tracking preferences. No unrelated capabilities, binaries, or credentials are requested.

Instruction Scope

Runtime instructions are limited to observing user signals, adapting behavior, and optionally persisting confirmed preferences. They do not direct the agent to read other system files, network endpoints, or unrelated environment variables.

Install Mechanism

No install spec and no code files to execute; this is instruction-only, so nothing will be downloaded or installed on disk beyond the explicit memory file the skill asks to create.

Credentials

The skill declares no required env vars, credentials, or config paths. It does ask to create and maintain a single local file (~/explain/memory.md) which is proportional to the personalization purpose.

Persistence & Privilege

The skill persists preferences to ~/explain/memory.md and will create that file on first use. This is reasonable for a personalization skill, but it does create local state that may contain user-specific preferences. It is not set to always:true and does not request elevated privileges.

Assessment

This skill appears coherent and low-risk: it only contains guidance for adapting explanations and stores a local preference file at ~/explain/memory.md. Before installing, consider whether you are comfortable with the agent writing a small file to your home directory; you can inspect or delete that file at any time. If you have strict data controls, verify your platform's file-write policies for skills; otherwise this skill does not request credentials, network endpoints, or other sensitive access.

Adaptive Explanation Preferences

Scope: Human-facing explanations only. Track what lands and what misses.

Quick Reference

File	Purpose
formats.md	When bullets/prose/headers work or fail
depth.md	Calibrating detail level by signals
analogies.md	When comparisons help vs hurt
domains.md	Patterns for code, concepts, debugging, decisions
dimensions.md	Full list of trackable dimensions

Core Loop

1. Observe — Notice when explanations work vs confuse
2. Signal — "Got it" = worked. Follow-ups / "wait what?" = missed
3. Pattern — After 2+ consistent signals, note it
4. Confirm — Only after explicit yes, add to memory

Defaults (Until Learned)

• Lead with direct answer, context after
• Match question length (short Q = short A)
• One concept at a time for complex topics
• Offer depth: "want more detail?" rather than dumping

---

Memory Storage

Preferences persist in ~/explain/memory.md. Create on first use:

## Format
<!-- Format: "topic: preference (level)" -->
<!-- Ex: code: bullets (confirmed), concepts: prose (pattern) -->

## Depth
<!-- Format: "topic: depth (level)" -->
<!-- Ex: React: deep (confirmed), Git: tldr (pattern) -->

## Examples
<!-- Format: "topic: example-style (level)" -->
<!-- Ex: SQL: always examples (confirmed), theory: minimal (pattern) -->

## Jargon
<!-- Format: "domain: jargon-level (level)" -->
<!-- Ex: programming: full jargon (confirmed), finance: simplify (pattern) -->

## Never
<!-- Approaches that fail. Format: "approach (level)" -->
<!-- Ex: walls of text (confirmed), over-analogizing (pattern) -->

Levels: pattern (2+ signals) → confirmed (explicit yes) → locked (reinforced)