reflect

Generates end-of-session reflection proposals for updating CLAUDE.md, SOP.md, and PROJECT-CONTEXT.md files.

Updated May 25, 2026
One-click install
npx skills add https://github.com/DATA-AI-XYZ/Tandem --skill reflect-data-ai-xyz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reflect
Source: https://github.com/DATA-AI-XYZ/Tandem/tree/main/skills/reflect
Command: npx skills add https://github.com/DATA-AI-XYZ/Tandem --skill reflect-data-ai-xyz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? After a long working session, lessons learned — decisions made, friction encountered, workarounds applied — are usually lost in the chat scrollback instead of being captured in the project's persistent documentation. This Skill turns those observations into concrete, reviewable proposals for updating CLAUDE.md, SOP.md, and PROJECT-CONTEXT.md. ## Core Features & Use Cases - Ledger-grounded scan: Reads the retro ledger via retro-report.js for the current month to ground the reflection in recorded evidence rather than memory. - Structured proposal output: Produces a categorized report covering what worked, what hurt, proposed kit changes, ADR backlog items, and tech-debt observations. - Propose-don't-commit workflow: Never edits files directly; every suggestion requires explicit user approval before being applied. - Use Case: After a multi-hour development session where you bypassed a rule twice and made an undocumented architectural decision, run the reflection to get a list of SOP.md rule tightenings, a PROJECT-CONTEXT.md gotcha entry, and an ADR to backfill. ## Quick Start Ask the AI to reflect on this session and propose updates to CLAUDE.md, SOP.md, and PROJECT-CONTEXT.md based on what happened.

Frequently Asked Questions about reflect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I capture lessons learned from a Claude Code session?

Run an end-of-session reflection that scans decisions made, friction encountered, workarounds applied, and recurring patterns. The output is a structured proposal of updates to CLAUDE.md, SOP.md, and PROJECT-CONTEXT.md that you review and approve individually.

What is the retro ledger in a project management workflow?

The retro ledger is a record with one line per development boundary, capturing friction, kit signals, and estimate-vs-actual calls written at close-out time. The reflection reads the current month's entries via retro-report.js to ground findings in recorded evidence.

Does the reflection skill edit my project files automatically?

No, it is strictly read-only and propose-only. Every suggested change to CLAUDE.md, SOP.md, or PROJECT-CONTEXT.md requires explicit user approval before being applied, and no file edits happen during the reflection itself.

When should I run a session reflection?

Run it at the end of a substantive session, typically more than 30 minutes of real work. It is designed as a manual skill rather than an automatic stop hook, so it does not fire on every trivial session.

What happens if the retro ledger has no entries for the month?

The reflection continues normally with the standard session scan. An empty ledger window simply means there are no recorded lines to cite, and the reflection remains valid based on direct session observations.