NavanithanS

ask-effective-llm-coder

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

NavanithanS 1 1 Updated 3mo ago

Resources

4
GitHub

Install

npx skillscat add navanithans/agent-skill-kit/ask-effective-llm-coder

Install via the SkillsCat registry.

SKILL.md
❌ 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> 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 - 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