insights-report
Generate a comprehensive cross-session insights report by analyzing all captured session logs in `.github/sessions/`. Use when reviewing patterns across sessions or preparing retrospectives.
Install with Tessl CLI
npx tessl i github:0xrabbidfly/eric-cartman --skill insights-report83
Quality
76%
Does it follow best practices?
Impact
99%
1.62xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/insights-report/SKILL.mdEvaluation results
98%
45%Dev Velocity Review for Q1 Planning
Report section completeness
Executive Summary section
50%
100%
Executive Summary named fields
0%
100%
Project Areas section
75%
100%
Top Goals section
37%
100%
What's Working Well section
100%
100%
Where Things Go Wrong section
100%
100%
Tool Usage Patterns section
100%
100%
File Patterns section
25%
100%
Suggestions subsections
20%
100%
Session Outcomes section
50%
100%
Timeline section
0%
75%
Key Insights section
100%
100%
Without context: $0.2596 · 1m 31s · 8 turns · 11 in / 4,620 out tokens
With context: $0.9879 · 4m 47s · 32 turns · 290 in / 15,633 out tokens
100%
15%Backend Refactor Retrospective
Session data extraction accuracy
Correct session count
100%
100%
Correct date range
100%
100%
Outcome distribution - fully
100%
100%
Outcome distribution - unclear
100%
100%
Top modified file identified
100%
100%
Tool usage - most used tool
100%
100%
Recurring challenge identified
100%
100%
Key insight aggregation
100%
100%
Common command sequence
62%
100%
Timeline accuracy
0%
100%
Appendix lists all sessions
50%
100%
Duration aggregation
100%
100%
Without context: $0.2577 · 1m 27s · 9 turns · 14 in / 5,057 out tokens
With context: $0.6302 · 2m 59s · 23 turns · 26 in / 9,446 out tokens
100%
54%Copilot Workflow Improvement Report
Suggestions section and report footer
Quick Wins subsection
0%
100%
Process Improvements subsection
25%
100%
copilot-instructions.md Additions subsection
90%
100%
copilot-instructions.md code blocks
100%
100%
Features to Try subsection
37%
100%
Suggestions reference session patterns
100%
100%
Footer - skill attribution
0%
100%
Footer - session count reference
0%
100%
No-sessions message format
50%
100%
Where Things Go Wrong suggestions
0%
100%
Features relevant to patterns
80%
100%
Without context: $0.3102 · 2m · 13 turns · 20 in / 5,028 out tokens
With context: $0.7704 · 3m 40s · 28 turns · 190 in / 11,572 out tokens
- 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.