Learn From This

When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented it. The skill library should grow from real failures, not hypothetical improvements. Every painful debugging session is a skill waiting to be written.

62 stars 2 forksLearning & Education

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ElliotJLT/Claude-Skill-Potions --skill learn-from-this
Manual install
git clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/learn-from-this ~/.claude/skills/learn-from-this

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Learn From This

<purpose>
The best skills come from real pain. When something goes wrong - wasted hours,
misunderstood requirements, broken code that looked correct - there's a lesson
embedded in that failure. This skill extracts that lesson and encodes it as a
new skill, so the same mistake becomes impossible to repeat.
</purpose>

## Why This Matters

<philosophy>
Most skill libraries are written in advance, based on what someone THINKS will
be useful. They're theoretical. Abstract. Generic.

The best skills are written AFTER failure, based on what actually went wrong.
They're specific. Battle-tested. Born from real pain.

This skill is meta: it creates other skills. The skill library becomes a
living document of hard-won lessons. Every entry is a scar that healed into
armour.
</philosophy>

## When To Activate

<triggers>
Trigger at session end or mid-session when you observe:

**Wasted Time:**
- Spent >30 minutes on something that should have taken 5
- Went down a wrong path and had to backtrack significantly
- Debugged something that had an obvious cause (in hindsight)

**Misunderstandings:**
- Built the wrong thing because requirements weren't clarified
- Made assumptions that turned out to be wrong
- Solved an XY problem instead of the real problem

**Repeated Patterns:**
- Made the same type of mistake twice in one session
- Hit a failure mode you've seen before
- Caught yourself doing something you know is bad practice

**Near Misses:**
Read the full skill on GitHub

Details

Skill name
learn-from-this
Path
skills/learn-from-this/SKILL.md
License
MIT
Repo updated
12 February 2026

FAQ

What does the Learn From This skill do?

When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented it. The skill library should grow from real failures, not hypothetical improvements. Every painful debugging session is a skill waiting to be written.

How do I install the Learn From This skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill learn-from-this. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Learn From This popular?

It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.

Related skills

Agent Audit

62

ElliotJLT/Claude-Skill-Potions

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

AI, LLMs & Agents

Battle Plan

62

ElliotJLT/Claude-Skill-Potions

Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.

Software Development

Breadcrumbs

62

ElliotJLT/Claude-Skill-Potions

Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.

Productivity & Notes

Skill Forge

62

ElliotJLT/Claude-Skill-Potions

When Claude discovers a non-obvious solution, unusual pattern, or hard-won insight during a session, automatically forge it into a new skill. Don't just note the learning - create the actual skill file so future sessions benefit immediately. This is the flywheel: work → discovery → skill → smarter future sessions → repeat.

Learning & Education

Event Study

36

dariia-m/my_claude_skills

Use this skill whenever the user wants to conduct an event study, create event study plots, test for parallel trends, implement difference-in-differences designs, or work with any panel data estimation that involves pre/post treatment comparisons. Trigger on phrases like "event study", "parallel trends", "pre-trends", "dynamic treatment effects", "leads and lags", "TWFE", "two-way fixed effects", "staggered adoption", "staggered treatment", "difference-in-differences", "DiD", "Sun and Abraham", "Callaway and Sant'Anna", "de Chaisemartin", "Borusyak", "did_multiplegt", "fixest", "did2s", "bacon

Learning & Education11

Continuous Learning V2

32

joneqian/claude-skills-suite

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Learning & Education

Browse the most popular Claude skills, all learning & education skills, or write your own with the skills generator.