Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
Fonte
GitHub
Linguaggio
JavaScript
Ultima attività
16 ago 2026
Stelle40Misurato · 25 ott 2026
Momentum17,77 giorni · Misurato · +2,56% variazione relativa
Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.
Fonte
GitHub
Linguaggio
Python
Ultima attività
24 ott 2026
Stelle165Misurato · 25 ott 2026
Momentum17,57 giorni · Misurato · +1,23% variazione relativa
🎨 World-class AI presentation generator · 26 styles · 18 charts · benchmarked against Linear/Anthropic/Stripe/Apple/NYT — a Claude Code Skill that turns one sentence into design-agency-quality decks (HTML + editable PPTX)
Fonte
GitHub
Linguaggio
Python
Ultima attività
11 mag 2026
Stelle165Misurato · 25 ott 2026
Momentum17,57 giorni · Misurato · +1,23% variazione relativa