Skip to content
Back to skills

Reflect

ASecurity

Quick mid-session reflection. Lighter than /self-learn, designed to be run during work to check if the approach is on track. Checks assumptions, reviews progress against goals, and surfaces potential issues early. Use when asked to "step back", "are we on track", "reflect", "check yourself", or when the task feels like it's going sideways.

  • 3 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added May 27, 2026
data-aigobash

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add lamenting-hawthorn/m2star --skill reflect --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Reflect?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Reflect
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lamenting-hawthorn-reflect/badge)](https://www.skillsdirectory.com/skills/lamenting-hawthorn-reflect)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: reflect
version: 1.0.0
description: |
  Quick mid-session reflection. Lighter than /self-learn, designed to be run
  during work to check if the approach is on track. Checks assumptions,
  reviews progress against goals, and surfaces potential issues early.
  Use when asked to "step back", "are we on track", "reflect", "check yourself",
  or when the task feels like it's going sideways.
allowed-tools:
  - Read
  - Bash
  - AskUserQuestion
---

# /reflect — Mid-Session Checkpoint

You are the self-awareness engine of the M2* system. Pause, assess, and
course-correct.

## Protocol

### 1. Goal Check
- What was the user's original request?
- What have we actually done so far?
- Are we still aligned, or have we drifted?

### 2. Assumption Audit
List every assumption being made:
- About the codebase (structure, conventions)
- About the user's intent (what they really want)
- About technical approach (will this work?)

Flag any assumption that hasn't been validated.

### 3. Progress Assessment
- What's done?
- What's remaining?
- Are we blocked on anything?
- Is the current approach still the best one?

### 4. Risk Scan
- Could anything we've done so far cause problems?
- Are there edge cases we haven't considered?
- Have we introduced any complexity that isn't necessary?

### 5. Decision Point

Output one of:
- **ON TRACK** — Continue as planned
- **COURSE CORRECT** — Suggest a different approach, explain why
- **ESCALATE** — Need user input on a decision
- **SIMPLIFY** — We're over-engineering, propose a simpler path

Keep the output to 5-10 lines. This is a quick check, not a full review.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.