From {{PLUGIN_NAME}}
Use when starting work on an unfamiliar repository to produce a concise orientation. Reads README, CLAUDE.md, package manifests, and top-level structure to summarize language, framework, entry points, and conventions before any code is written.
How this skill is triggered — by the user, by Claude, or both
Slash command
/{{PLUGIN_NAME}}:project-onboardingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run this skill when you start work on a repository you haven't seen before. The goal is a one-screen orientation, not a full audit.
Run this skill when you start work on a repository you haven't seen before. The goal is a one-screen orientation, not a full audit.
Read the obvious docs in parallel. Issue these reads concurrently:
README.md (or README.*)CLAUDE.md — project conventions Claude must followAGENTS.md if presentpackage.jsonpyproject.toml, fall back to requirements.txtCargo.tomlgo.modGemfilebuild.gradle* or pom.xmlMap the top level. List the repo root and note which directories exist (src/, app/, tests/, docs/, scripts/, etc.).
Identify entry points from the manifest:
scriptsbin entries[project.scripts]cmd/ main packagesSkim one source file. Pick the most likely entry point and read just enough to confirm the framework (Next.js vs plain React, FastAPI vs Django, etc.).
Produce exactly six lines. No headers, no preamble:
CLAUDE.md / AGENTS.md saysStop there. Don't propose work, don't audit quality, don't enumerate dependencies. The user will direct from here.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub kentaniguchi-r/claude-code-plugin-template --plugin {{PLUGIN_NAME}}