Thin Prompts, Thick Artifacts
trq212 · x · 2026-07-16
The author proposes a prompt design principle: - **thin prompts**: Keep prompts as lean as possible - **thick artifacts + context**: Build deep context and artifacts - **thin skills**: Keep the skills themselves lightweight The core idea is to avoid piling all complexity into the prompt, and instead separate and manage structure, context, and reusable skills independently.
Related event: Prompt Engineering Best Practices: Thin Prompts, Thick Context(2 posts)→
More from coding & agent
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21
- X post asks whether Cursor Composer, built on Kimi models, would also be banned — max_paperclips · 2026-07-21
- A developer’s Codex usage is draining pooled enterprise credits at a small company — Distinct_Relation_62 · 2026-07-21