Add a learned pattern (lesson) that Ralph will remember for future stories.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill lesson --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Lesson?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-lesson)More formats (shields.io, HTML) on the badges page.
---
description: Add a learned pattern (lesson) that Ralph will remember for future stories.
---
# Add Lesson
The user wants to add a lesson - a pattern or rule that Ralph should remember for all future work.
**Get the pattern from the user.** Ask:
1. What's the pattern or rule? (e.g., "Always use select_related for foreign keys")
2. What category? (frontend, backend, general, testing)
**Then run:**
```bash
npx agentic-loop lesson "THE PATTERN HERE" CATEGORY
```
**Examples:**
```bash
npx agentic-loop lesson "Never hardcode AI model names - use env vars" backend
npx agentic-loop lesson "Always add data-testid for Playwright tests" frontend
npx agentic-loop lesson "Use useCallback for event handlers passed to children" frontend
npx agentic-loop lesson "Always paginate list endpoints" backend
```
**After adding, confirm:** "Added lesson. Ralph will include this in every future story prompt."
**To see all lessons:**
```bash
npx agentic-loop lessons
```
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...