vibe-code

Plugin vibe-code from marketplace rygentic-harness in rhawk117/rygentic-harness. Commands read from the repo's manifest — 10 days ago.

Skills (11)

• build-a-loop

  Design a reliable agent loop from a plain description of the work. Picks the loop shape, defines what one iteration may touch, sets the evidence each success criterion needs, writes a stop condition that measures progress instead of counting turns, and emits a LOOP.md contract plus the Claude Code c

• create-agents-md

  Generate an evidence-based AGENTS.md for the current repository by dispatching two explorer subagents (toolchain and verification, conventions and structure), and optionally a CLAUDE.md that imports it with @AGENTS.md. Use it to create, regenerate, audit or merge repository instruction files: AGENTS

• create-hooks

  Interactive builder for Claude Code hooks. Use it to create, add or set up a hook, or to ask what hooks would suit a repository. It asks how the hook ships (project, project-local, personal, plugin), when it runs and what it is for (failure mode, context injection, tracking), takes one or several pl

• create-mcp

  Interview-driven builder for MCP servers in Python (uv project, official `mcp` SDK, src layout with one package per tool). Use it to create, scaffold, design or add an MCP server for Claude Code. It asks where the server is installed (plugin, project, local or user scope), whether it is local only o

• create-rules

  Interactive builder for Claude Code rule files (Markdown files under .claude/rules/ with optional paths frontmatter and an XML-sectioned body). Use it to create, add, write or scaffold a rule, a set of coding conventions or a style guide for Claude, or to ask how paths scoping works, even when the u

• create-skill

  Interactive Claude Code skill creator, scenario-first. Use it to create, write, scaffold, improve, test or evaluate a skill (SKILL.md plus optional scripts, references and assets). It asks where the skill ships (personal, project, plugin), sets invocation and tool pre-approvals by checkbox, takes a

• create-subagent

  Interactive builder for Claude Code subagents (agent files with YAML frontmatter and an XML-sectioned Markdown body). Use it to create, scaffold, design or add a subagent, specialist agent, reviewer agent or persona, or to ask how to write an agent file, even when the user only describes the job ("I

• humanizer

  Rewrite or review prose to remove signs of AI-generated writing (puffery, AI vocabulary, em dashes, chatbot artifacts, stacked hedging, formulaic structure) while keeping every fact and the author's voice. Use when editing, reviewing, or humanizing text, Markdown files, docs, READMEs, PR description

• plan-plugin

  Planning interview for a Claude Code plugin; ends in a phased plan and an empty plugin shell, never a build. Use whenever the user wants to create, design, plan, scope or extend a Claude Code plugin, says "I want a plugin that...", "bundle our X conventions", "package this for the team", "what shoul

• promptlint

  Use when writing, improving, or reviewing a coding-agent prompt for Claude Code.

• tune-skill-descriptions

  Tunes Claude Code skill descriptions so the right skill loads for the right request. It runs the vibe-code tune loop over a labeled trigger set: real headless Claude Code routing (or fresh subagents) judges which skills each request loads, Claude proposes one rewrite at a time, the loop keeps a rewr

Similar plugins