reflectlisted

# reflect - Reflection Skill Read memory and context to reflect deeply. Design principle: "Reflection first, sending second." ## Table of Contents - [Nature of This Skill](#nature-of-this-skill) - [Invocation](#invocation) - [Reflection Process](#reflection-process) - [Output](#output) - [Essay Elements](#essay-elements) --- ## Nature of This Skill This is an **agent-driven skill** with no standalone implementation code. The reflection process is executed by `agents/essay-writer.md`. For execution flow diagram, see `agents/essay-writer.md` → **Execution Flow** section. --- ## Invocation | Source | Agent | Description | |--------|-------|-------------| | `/essay` | essay-writer.md | Primary invocation | | `/essay wait` | essay-writer.md | Scheduled (one-time) | | `/essay schedule` | essay-writer.md | Scheduled (recurring) | For CLI options, see `commands/essay.md` → **Command Structure** section. --- ## Reflection Process ### 1. Load Context Read specified files as material for reflection. **Recommended context**: - Memory digest files (GrandDigest, etc.) - Personal notes or journals - Project documentation **Additional context** (AI may read as needed): - Hierarchical digests - Recent conversation logs - Identity/persona files ### 2. Deep Reflection (ultrathink) Use extended thinking to contemplate: - Insights emerging from context - Unresolved questions - What to communicate to the user - What doesn't need to be said ### 3. Delivery Decision **Deliver**