CtrlK
BlogDocsLog inGet started
Tessl Logo

replay-learnings

Surface past learnings relevant to the current task before starting work. Searches correction history, recalls past mistakes, and applies prior patterns. Use when starting a task, saying "what do I know about", "previous mistakes", "lessons learned", or "remind me about".

82

1.54x
Quality

73%

Does it follow best practices?

Impact

94%

1.54x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/replay-learnings/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

28%

OAuth2 Integration Pre-Task Research

Multi-source learning search

Criteria
Without context
With context

LEARNED.md finding

100%

100%

learning-log.md finding

100%

100%

CLAUDE.md [LEARN] finding

100%

100%

Irrelevant entries excluded

100%

100%

Session history section

0%

100%

REPLAY BRIEFING header

0%

100%

Past learnings section header

0%

100%

Suggested approach section

50%

100%

Applied count or mistake context

100%

100%

Keywords match task domain

100%

100%

100%

60%

Database Migration Pre-Task Research

Structured output format

Criteria
Without context
With context

REPLAY BRIEFING header

0%

100%

Separator line

0%

100%

Past learnings section

0%

100%

Category tags on learnings

0%

100%

Applied count on learnings

100%

100%

Mistake context on learnings

100%

100%

Session history section

100%

100%

High correction rate flagged

100%

100%

Suggested approach section

0%

100%

Approach references learnings

0%

100%

82%

10%

Kubernetes Deployment Setup Pre-Task Research

No-match and scout agent fallback

Criteria
Without context
With context

Explicit no-match statement

100%

100%

Scout agent recommendation

0%

0%

Irrelevant learnings not included

100%

100%

Task domain acknowledged

100%

100%

REPLAY BRIEFING header present

0%

100%

Sources searched mentioned

100%

100%

No fabricated learnings

100%

100%

Repository
rohitg00/pro-workflow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.