insights — Claude Code skill: analytics and installation
The insights skill turns project memory and session history into analytics on corrections, saved learnings, and coding activity. Ask for a report to spot recurring patterns.
MIT ★ 2,966 updated 2026-09-29
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflowWhat insights does
insights builds a report from project memory and session history. It can show current-session activity, learning categories, frequently or rarely applied entries, correction patterns, and productivity metrics. Session duration and changed-file counts are among the example metrics.
The skill reads .claude/LEARNED.md, .claude/learning-log.md, and CLAUDE.md, and checks Git history and git diff --stat. It treats a correction as a case where the user redirects, fixes, or overrides an agent’s work. The report therefore depends on what the project has recorded in memory and history.
What it helps with
- check activity in the current session
- spot categories that prompt repeated agent corrections
- find saved learnings that are rarely applied
- compare correction patterns across sessions
Example prompts for the agent
- Show me the stats for my current session.
- Build a correction heatmap by category.
- Which saved learnings have not been applied lately?
How to install insights
1Plugin marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflowThis installs the whole pro-workflow plugin with all its skills
2Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill insights -a claude-code3Manually: put the files in place
~/.claude/skills/insights/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/insights/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill insights -a codex2Manually: put the files in place
.agents/skills/insights/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill insights -a cursor2Manually: put the files in place
.cursor/skills/insights/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rohitg00/pro-workflow skills/insights2Manually: put the files in place
.github/skills/insights/SKILL.md1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill insights -a gemini-cli2Platform CLI
gemini skills install https://github.com/rohitg00/pro-workflow --path skills/insightsManually: put the files in place
.devin/skills/insights/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about insights
How do I install insights in Claude Code?
Run /plugin marketplace add rohitg00/pro-workflow, then run /plugin install pro-workflow@pro-workflow.
What does insights do?
It analyzes project memory and session history to report on coding activity, saved learnings, agent corrections, and productivity metrics.
What data does insights use?
It reads .claude/LEARNED.md, .claude/learning-log.md, and, when needed, CLAUDE.md; it also checks Git history and change statistics. A correction means the user redirected, fixed, or overrode agent output.
Source text
SKILL.md · MIT
---
name: insights
description: Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics. Computes stats from project memory and session history. Use when asking for stats, statistics, progress, how am I doing, coding history, or dashboard.
user-invocable: true
---
# Session Insights
Surface patterns from learnings and session history.
## Trigger
Use when asking "show stats", "how am I doing", "analytics", "insights", "heatmap", or "correction rate".
## Data Sources
Gather data from these locations before computing metrics:
```bash
# Session history and learnings
cat .claude/LEARNED.md 2>/dev/null || cat CLAUDE.md | grep -A999 "LEARNED"
cat .claude/learning-log.md 2>/dev/null
# Session activity
git log --oneline --since="today" --author="$(git config user.name)"
git diff --stat
```
A **correction** is any instance where the user redirected, fixed, or overrode agent output during a session. Count `[LEARN]` entries and explicit correction markers in session history.
## What It Shows
### Session Summary
```
Session Insights
Duration: 47 min
Edits: 23 files modified
Corrections: 2 self-corrections applied
Learnings: 3 new patterns captured
Context: 62% used (safe)
```
### Learning Analytics
```
Learning Insights (42 total)
Top categories:
Testing 12 learnings (29%)
Navigation 8 learnings (19%)
Git 7 learnings (17%)
Quality 6 learnings (14%)
Most applied:
#12 [Testing] Run tests before commit — 15 times
#8 [Navigation] Confirm path for common names — 11 times
Stale learnings (never applied):
#15 [Editing] Prefer named exports — 0 times (45 days old)
```
### Correction Heatmap
```
Correction Heatmap
By category (all time):
████████████ Testing 34 corrections
████████ Navigation 22 corrections
██████ Git 18 corrections
████ Quality 12 corrections
Hot learnings (most corrected, least learned):
- [Testing] Mock external deps — corrected 8x, learned 0x
→ Consider: /learn-rule to capture this permanently
Cold learnings (learned but never applied):
- [Editing] Use named exports — learned 45 days ago, applied 0x
→ Consider removing if no longer relevant
```
### Productivity Metrics
```
Productivity (last 10 sessions)
Avg session: 35 min
Avg edits/session: 18
Correction rate: 12% (improving)
Learning capture: 2.1 per session
```
## Guardrails
- Use actual data from project memory and session history.
- Surface actionable suggestions, not just numbers.
- Flag recurring corrections that should become permanent rules.
- Identify stale learnings that may no longer be relevant.
## Output
Formatted analytics report with:
- Current session stats
- Category breakdown
- Most/least applied learnings
- Correction trends with suggestions
- Productivity metrics over time
© Rohit Ghumare · MIT · rohitg00/pro-workflow