Scaffold, audit and migrate CLAUDE.md files from inside Claude Code: /claude-md-new builds one from battle-tested templates using your repo's real commands; /claude-md-audit grades an existing one and returns worst-first fixes; /claude-md-migrate rewrites a bloated file into the lean verified style.
Autonomous dev pipeline generator. /autocode-flow:autocode-new scans & configures, /autocode-flow:autocode auto-executes plan → tdd → code → test → verify with zero human intervention.
AI Dev OS - A development OS for AI-assisted coding. Systematically improves AI development quality through a 4-layer model (Philosophy → Principles → Guidelines → AI Frames).
The most comprehensive agent skill set for real Rust: ownership over clone and unwrap, errors and APIs that survive review, async and unsafe done right, plus disciplined porting into Rust.
1 17d agoA
tokens not measured
originalBSD-3-Clause
Structured software development workflows for Claude Code, aligned with Opus 4.8 at xhigh/max effort. Eleven reusable subagents drive brief generation, plan generation, task decomposition, automated batch implementation, and multi-angle parallel review. v3 follows five design rules: workflow SOP stays, business rules…
Fase Zero do Agent-Driven Protocol (ADP): as 2 primeiras fases do metodo spec-driven para Claude Code. grill-me (a IA te entrevista ate o escopo ficar redondo) + to-prd (a conversa vira um PRD de verdade) + CLAUDE.coringa.md (convencoes para adaptar ao seu projeto). Gratis. O protocolo completo (6 fases, 4 gates…
Zero-dependency sound notifications for Claude Code. Plays audible alerts via PermissionRequest and Stop hooks — know when Claude needs approval or has finished, without watching the terminal. macOS / Linux / Windows.
A set of coding-governance practices for Claude Code, an AI coding assistant. The description identifies it as the Claude Code version of ACGM, but gives no further details.
A set of working rules for Claude Code, Anthropic’s coding assistant, aimed at keeping long-running development work on track. It checks destructive actions, grounds work in evidence, and avoids claims that cannot be supported.
מגדיל ראש — do more than the literal ask. Ships the complete feature, not the happy path: edge-case checklists per domain, asks the right scoping questions first, reports terse.
Route tasks between Claude Code and Codex CLI — Subscription Efficiency Maximizer. Automatically routes tasks to the optimal CLI based on task type and budget.
Route tasks between Claude Code and Codex CLI — Subscription Efficiency Maximizer. Automatically routes tasks to the optimal CLI based on task type and budget.
Advisor Strategy skill for Claude Code — spawns a stronger model (Opus) as a strategic advisor for architecture, security, debugging, and performance decisions.