Stats
Actions
Tags
From erne-universal
Runs session evaluation script to analyze coding session quality, files changed, tests, builds, and hooks; generates retrospective report with metrics, patterns, feedback, and recommendations.
How this command is triggered — by the user, by Claude, or both
Slash command
/erne-universal:erne-retrospectiveThe summary Claude sees in its command listing — used to decide when to auto-load this command
# /erne-retrospective — Session Analysis You are executing the `/erne-retrospective` command. This is **script-driven** — it runs the session evaluation pipeline. ## What This Does Analyzes the completed coding session to evaluate quality, identify improvements, and suggest harness enhancements. ## Process 1. **Run the evaluation script:** This script analyzes: - Files created/modified during the session - Test results and coverage changes - Build success/failure history - Hook trigger patterns (which rules fired, which were ignored) - Time spent in different phases (planning, codin...
You are executing the /erne-retrospective command. This is script-driven — it runs the session evaluation pipeline.
Analyzes the completed coding session to evaluate quality, identify improvements, and suggest harness enhancements.
node .claude/hooks/scripts/evaluate-session.js
This script analyzes:
## Session Retrospective
### Work Summary
- Files changed: 12
- Tests added: 8
- Tests passing: 47/47
- Build status: Success
### Quality Metrics
- Type safety: 100% (no new `any`)
- Test coverage delta: +3.2%
- Bundle size delta: +8KB
### Patterns Observed
- [GOOD] Consistent use of error boundaries
- [GOOD] All new components have tests
- [IMPROVE] 3 files missing JSDoc on public API
- [IMPROVE] 2 effects missing cleanup
### Harness Feedback
- Rule `common/state-management.md` triggered 5 times → Well calibrated
- Rule `expo/patterns.md` never triggered → May need broader globs
- Hook `lint-staged.cjs` caught 2 issues → Working as intended
- Suggestion: Add rule for consistent error message format
### Recommendations
1. Add error message formatting rule
2. Review expo/patterns.md glob coverage
3. Consider adding pre-commit test hook
npx claudepluginhub jubakitiashvili/everything-react-native-expo/coachAnalyzes development sessions from session-log.jsonl for actionable coaching insights on workflow adoption, prompt quality, efficiency, and code quality. Default: last session + 5-session trend; supports --last N and --all flags.
/review-gladiatorReviews session history observations, clusters patterns, generates workflow recommendations, and suggests changes or existing solutions.
/insightsSurfaces analytics on coding sessions, workflow learnings, correction patterns, heatmaps, and productivity metrics with trends and suggestions. Supports session, learnings, corrections, heatmap subcommands.
/wrapAnalyzes current coding session via git status and agents, suggests documentation updates, automation opportunities, follow-up tasks, and executes selected actions. Supports quick commit with message.
/retroAnalyzes a session for improvements — identifies time waste, user feedback, project knowledge, workflow bugs, and tool issues. Generates a structured retro report and suggests actionable changes.
/fullRuns multi-agent parallel evaluation on the current project using collector, safety-evaluator, completeness-evaluator, design-evaluator, and synthesizer (~5-10min).