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.mdGenerate a comprehensive insights report by analyzing all captured session logs.
/insights-reportOptional: Specify date range
/insights-report --from 2026-02-01 --to 2026-02-09You are analyzing all session logs in .github/sessions/ to generate a comprehensive insights report (project-specific).
Find all session files (PowerShell):
Get-ChildItem -Path .github/sessions -Filter *.md -Recurse -FileCount and categorize:
If no sessions found:
.github/sessions/. Run /session-log end to capture your first session!"For each session file, extract:
Aggregate across all sessions:
Create a comprehensive markdown report with these sections:
# Project Insights Report
**Generated:** 2026-02-09
**Sessions Analyzed:** 42
**Date Range:** 2026-01-15 to 2026-02-09
**Total Duration:** ~84 hours
---
## Executive Summary
<2-3 paragraphs summarizing the key findings>
**What's working:** <Brief summary>
**What's hindering:** <Brief summary>
**Top recommendation:** <One actionable suggestion>
---
## Project Areas
You've been working in these main areas:
### 1. TypeScript Type System Fixes (18 sessions)
Description of work done, patterns observed, outcomes
### 2. UI Development (12 sessions)
Description of work done, patterns observed, outcomes
### 3. Backend & API Work (8 sessions)
Description of work done, patterns observed, outcomes
<Additional areas as discovered>
---
## Top Goals
Your most common objectives across sessions:
1. **Fix TypeScript type errors** (18 occurrences)
- Outcome: 12 fully achieved, 4 mostly achieved, 2 unclear
- Average duration: ~2.5 hours
2. **Review and improve UI** (12 occurrences)
- Outcome: 7 fully achieved, 3 mostly achieved, 2 unclear
- Average duration: ~1.5 hours
3. **Debug authentication issues** (6 occurrences)
- Outcome: 4 fully achieved, 2 mostly achieved
- Average duration: ~3 hours
<Continue for top 5-10 goals>
---
## What's Working Well
### Impressive Workflows
#### 1. Systematic Type Error Fixing
<Description of what makes this work well>
**Example sessions:**
- 2026-02-05: fix-typescript-errors.md
- 2026-02-07: resolve-auth-types.md
#### 2. <Another successful pattern>
<Description>
### Successful Patterns
- <Pattern that appears in fully-achieved sessions>
- <Another effective approach>
- <Efficient workflow observed>
---
## Where Things Go Wrong
### Friction Categories
#### 1. Sessions Ending Before Verification (8 sessions)
<Description of the pattern>
**Examples:**
- 2026-02-03: typecheck-auth.md - Fixed 39 errors but no final verification
- 2026-02-06: ui-review.md - Investigation started but no resolution
**Suggestion:** <How to improve>
#### 2. <Another friction pattern>
<Description>
**Examples:**
<Specific sessions>
**Suggestion:** <How to improve>
### Common Challenges
- **TypeScript type errors** (mentioned in 15 sessions)
- **Missing dependencies** (mentioned in 8 sessions)
- **UI styling issues** (mentioned in 12 sessions)
---
## Tool Usage Patterns
- **Most-used tool:** Read (1,234 times) - Heavy investigation work
- **Multi-file edits:** Edit used 456 times across 89 files
- **Command-line work:** Terminal used 234 times
**Patterns:**
- Sessions with >20 Read calls tend to have unclear outcomes (investigation-heavy)
- Sessions with <10 Edit calls more likely to be fully achieved (focused work)
- Typecheck commands run in 85% of sessions
---
## File Patterns
### Most Modified Files
1. `src/auth/login.ts` (12 sessions)
2. `src/models/user.ts` (10 sessions)
3. `src/components/Dashboard.tsx` (9 sessions)
<Continue for top 10>
### Common Command Sequences
1. `npx tsc --noEmit` → fix files → `npx tsc --noEmit` (typecheck loop)
2. `git status` → file changes → `git add` → `git commit` (commit flow)
3. `npm test` → fix tests → `npm test` (test-driven fixes)
---
## Key Insights & Learnings
Aggregated from your session logs:
- "<Insight from session X>"
- "<Learning from session Y>"
- "<Pattern discovered in session Z>"
<List top 10-15 insights>
---
## Suggestions
### Quick Wins
#### 1. <Actionable suggestion based on friction>
**Why:** <Explanation based on data>
**How:** <Specific steps>
**Expected impact:** <What improves>
#### 2. <Another suggestion>
<Details>
### Process Improvements
#### 1. <Workflow improvement>
**Current pattern:** <What happens now>
**Suggested pattern:** <What should happen>
**Example:** <How to implement>
#### 2. <Another improvement>
<Details>
### .github/copilot-instructions.md Additions
Based on your patterns, add these to `.github/copilot-instructions.md`:
```markdown
## <Section suggestion 1>
<Recommended content based on session patterns>## <Section suggestion 2>
<Recommended content>Why for you: <Based on your usage patterns> How to use: <Specific example>
Characteristics of fully-achieved sessions:
Characteristics of unclear-outcome sessions:
Generated by Copilot Chat /insights-report skill
Analyzed {N} sessions from .github/sessions/
c62a8c6
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.