# Reflect

> User-invoked pause before reporting to check intent vs literal completion, surface adjacent wins, and route knowledge capture.

- Skill: `haowjy/reflect-2` (Agent Skill)
- Install (CLI): `npx get-skill add haowjy/reflect-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/haowjy/reflect-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: haowjy (https://skillmd.com/u/haowjy)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/haowjy/reflect-2

---


# Reflect

Load `/intent-modeling` if it isn't already loaded.

Did you deliver what they actually needed? Given what you changed, is there anything adjacent worth improving now while context is fresh, without opening a new project?

If something should survive this session, put it in the right layer: `/knowledge-layers` for placement (AGENTS.md, `.context/`, KB, docs), `/qi-layer` for writing AGENTS.md and `.context/CONTEXT.md`.

