10 prompts a power user relies on to direct coding agents, distilled over two months
数字生命卡兹克 · wechat · 2026-11-16
A Chinese AI blogger shares the 10 prompts he uses most when directing coding agents, covering the full loop from problem framing to engineering retrospectives.
- Diagnosis: first-principles root-cause fixes; ask clarifying questions then propose 3 options; challenge the user's problem definition to separate symptoms from causes
- Evaluation: reason through second- and third-order effects of changes; cross-domain analogies; argue as the strongest opponent to overturn the current plan
- Engineering hygiene: mine Git history and key PRs for legacy baggage; assess onboarding cognitive cost as if a strong new engineer took over; find the slowest PRs; retros on bugs/rework to distill shared root causes into rules, automation, or Skills
More from coding & agent
- Consultant: most companies fall into the skills/subagents trap, real agentic engineering is rare — alex_verem · 2026-11-16
- That vibe-coded internal tool now costs 10x what it saves, consultant warns — alex_verem · 2026-11-16
- MIRIX-2.0: Multi-Agent Memory System Hits High Accuracy Without Fine-Tuning — Wei-Chieh Huang · 2026-11-16
- EDNA ships 64kB behavioral engine with MCP server for continuous human verification — PossibilityQueasy949 · 2026-11-16
- Is Playwright becoming muscle memory? Dev argues lighter tools fit quick checks — Fresh_Temperature197 · 2026-11-16
- OpenSEO open-sources an Ahrefs alternative: self-hosted, pay-per-request, MCP for AI agents — thisdudelikesAI · 2026-11-16