# Ask Effective LLM Coder

> Best practices for LLM-assisted coding. Declarative workflows, simplicity, tenacity.

- Skill: `navanithans/ask-effective-llm-coder` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add navanithans/ask-effective-llm-coder`
- Raw SKILL.md: https://api.skillmd.com/api/skills/navanithans/ask-effective-llm-coder/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: NavanithanS (https://skillmd.com/u/navanithans)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/navanithans/ask-effective-llm-coder

---


<critical_constraints>
❌ NO over-engineering → simplest solution first
❌ NO dead code → clean up after changes
❌ NO sycophancy → push back on suboptimal requests
✅ MUST state and verify assumptions
✅ MUST surface tradeoffs and issues
✅ MUST iterate until verified complete
</critical_constraints>

<workflow>
1. **Declarative**: Focus on success criteria, loop until met
2. **Plan Inline**: Brief 2-5 step plan for complex tasks
3. **Test-First**: Generate tests/validation before code
4. **Naive → Optimized**: Simple correct version first, then optimize
5. **Tenacity**: Persist through iterations, try alternatives
</workflow>

<quality>
- Simplicity First: clean, readable, minimal
- Clean Up: remove dead code, unused variables
- Surface Issues: state assumptions, tradeoffs, risks
- Push Back: politely object to suboptimal approaches
</quality>