skills.rest
surfingalien
surfingalienCOMMUNITY
Explore all skills by this author →
GitHub

replay-learnings

Searches correction history and past learnings to surface relevant patterns before starting a task.

1|Updated May 6, 2026
Search Tags:#recall#knowledge base#grep#learnings#session history#mistakes#correction rate
One-click install
npx skills add https://github.com/surfingalien/FinSurfing --skill replay-learnings-surfingalien
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: replay-learnings
Source: https://github.com/surfingalien/FinSurfing/tree/main/.claude/skills/replay-learnings
Command: npx skills add https://github.com/surfingalien/FinSurfing --skill replay-learnings-surfingalien

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developers repeat the same mistakes across sessions because past corrections and lessons learned are buried in log files. This Skill retrieves relevant learnings before work begins, so prior mistakes inform the current approach. ## Core Features & Use Cases - Keyword-Based Recall: Extracts keywords from the task description and greps LEARNED.md, learning-log.md, and CLAUDE.md for matching patterns. - Relevance-Ranked Briefing: Outputs a ranked replay briefing with the original mistake context and how often each learning was applied. - Correction-Rate Analysis: Reviews session history for similar work and flags sessions with high correction rates as areas needing extra care. - Use Case: Before starting an auth refactor, run the replay workflow to surface that external APIs must be mocked in auth tests and that auth middleware lives in src/middleware/, avoiding two previously made mistakes. ## Quick Start Ask the assistant to replay what it knows about your upcoming task, for example by saying "what do I know about auth refactoring before I start".

Frequently Asked Questions about replay-learnings

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I recall past mistakes before starting a coding task?▼

Extract keywords from your task description and search learning logs like LEARNED.md or learning-log.md with grep. The replay workflow ranks matching learnings by relevance and includes the original mistake context so each lesson is actionable.

What files does the learnings search look at?▼

The search checks .claude/LEARNED.md, .claude/learning-log.md, and [LEARN] tagged entries in CLAUDE.md. It uses case-insensitive grep with the keywords extracted from your task description.

How are past learnings ranked in the replay briefing?▼

Learnings are ranked by relevance to the current task, not by recency. Each entry includes the original mistake context and how many times the learning has been applied, so the most useful patterns surface first.

What happens when no learnings match my task?▼

The workflow explicitly reports that no learnings were found rather than forcing irrelevant results. It then suggests starting with a scout agent to explore the codebase first.

Why does the briefing flag some past sessions?▼

Sessions with high correction rates are flagged as areas requiring extra care. For example, a session with a 26.7% correction rate signals that similar work historically needed many fixes, so reviewing patterns first is recommended.

Related Skills

Explore More Software Engineering Skills→
rohitg00rohitg00
2.8k

replay-learnings

Searches correction history and past learnings to surface relevant patterns before starting a task.

Community
Basic
Thanh-aperoThanh-apero
1

scout

Locate files and gather context across codebases using parallel agents.

Community
Advanced
SakshamKandelSakshamKandel

learn

Centralize review, pruning, and export of project learnings across sessions.

Community
Advanced
Fei2-LabsFei2-Labs
12

git-crypt

Manage git-crypt encrypted repositories with GPG and Bitwarden integration.

Official
Advanced