Developer Tools●●Solid
A Claude Skill that teaches Rails conventions for LLM calls
Finally, Rails conventions for LLM calls instead of scattered API code in controllers.
Solve My ProblemBig Brain
nagstler
103mo ago
Back to browse
GitHub Repository
An Agent Skill that audits a codebase for LLM API calls and reports which ones can be replaced with deterministic logic — without rewriting code by default.
3 stars
A Claude Code skill that tells Claude when not to use Claude
by metravod·May 17, 2026·1 point·0 comments
AI Analysis
●●●BangerBig BrainSolve My Problem
Traffic-light audit system beats vague 'optimize your LLM spend' advice from competitors.
Strengths
- •Classifies calls by task type with specific deterministic replacement suggestions per category.
- •Cost estimates per call let you calculate actual ROI before making changes.
- •Audit-first approach prevents accidental rewrites—replacement is opt-in after review.
Weaknesses
- •Claude Code skill format limits adoption to that ecosystem only.
- •No automated migration path—teams must manually implement each replacement.
Category
Target Audience
Engineering teams overspending on LLM APIs, CTOs optimizing AI costs
Similar To
LangSmith · Helicone · Braintrust
Similar Projects
AI/ML●Mid
ClaudeMap – Google Maps for your codebase, runs as a Claude Code skill
Visual codebase maps when Cursor and Sourcegraph Cody already do this.
Eye CandyShip It
Quinnaho
101mo ago
AI/ML●Mid
Claude Code skills for building LLM evals
Structured eval workflow for Claude Code when LangSmith and Braintrust already exist.
Niche GemShip It
paulaq
201mo ago
Developer Tools●●Solid
Devopsiphai – A Claude Code skill to audit DevOps around 5 questions
ARC framework grades DevOps health but it's still a Claude Code skill wrapper.
Niche GemBig Brain
sanhajio
102mo ago
AI/ML●●●Banger
Centrality – Visualize your how Claude Code operates on your codebase
Live codebase graph showing exactly where Claude Code reads, writes, and spends tokens.
Eye CandySolve My ProblemShip It
sorenjmadsen
201mo ago
AI/ML●Mid
The Agent Skills Standard – A modular approach to LLM context
Modular context folders beat monolithic prompts for scaling AI agent instructions.
Big Brain
muhammad-shafat
302mo ago