Agentic Os Skills banner
rohitguta2432 rohitguta2432

Agentic Os Skills

Development community

Description

44 Claude Code agent skills as an installable plugin marketplace — engineering, content, SEO, productivity, planning, trading & growth. One repo, whole team, auto-updating. Works in Claude Code & Codex.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Agentic OS Skills — Claude Code Skills Library & Plugin Marketplace

**41 production agent skills for Claude Code and Codex, organized as installable plugins by department.** One GitHub repo as the single source of truth for your whole AI setup — install once, auto-update everywhere.

Skills are SOPs for AI agents: markdown playbooks that teach Claude Code exactly how you want a task done, so it one-shots proposals, posts, reviews, and reports instead of you re-explaining preferences every session.

This is the skills backend of my [Agentic OS](https://github.com/rohitguta2432/agentic-os) — the interactive galaxy visualization of the full skill graph.

Install

In Claude Code:

/plugin

Then **Marketplaces → Add marketplace** and paste:

rohitguta2432/agentic-os-skills

Install the department plugins you want (e.g. `engineering`, `content-marketing`). Enable **auto-update** so skill improvements propagate to every machine and teammate automatically.

What's inside

`engineering` — 16 skills

Software engineering skills — spec-driven development, autonomous dev pipelines, code review, TDD, git guardrails, architecture audits, WhatsApp AI bot architecture on AWS, and production-readiness grading for AI agents.

Skill What it does
agentgrade Audit any AI agent codebase for production readiness. Grades the repo against five pillars — evaluation, observability, data foundation, orchestration, gover...
autodev Launch, monitor, resume, or stop a fully autonomous autodev pipeline run (spec → analyze → implement → push → review → test in an isolated git worktree, live...
code-review Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding st...
fable-mode Emulate Claude Fable 5's reasoning depth and tool-use efficiency on smaller models (Opus 4.8, Sonnet). Enforces hypothesis-first debugging, assum