By YuZh98
Scaffold Python projects, normalize CHANGELOGs, automate releases, and run pre-PR audits.
Invoke for /audit-diff, "audit this PR", "audit the diff", "pre-merge audit", "second opinion on this change", or any pre-PR independent review of a Python diff against the project's GUIDELINES.md / CLAUDE.md / DESIGN.md. Scaffold-aware delta from the harness-level audit-diff skill: knows this plugin's project-brief paths and ships the 11-dimension framework (with two-axis mode flags, primary-dim rule, drift sweeps, meta-principles) as a static spec plus per-dimension checklists, a surface-detection script, a coordinator brief, and a report template. The skill itself does NOT spawn agents; the model or user reading this skill drives orchestration using whatever dispatch mechanism the runtime provides. Required (per global rules §3) before merging any PR that touches business logic, schema, or production behavior; skip only for docs-only / dependabot grouped-minor / single-file typo PRs. Distinct from general code review: this is the structural pre-merge gate, not freeform feedback. Do NOT trigger on changelog edits ("normalize CHANGELOG" → changelog-normalizer), scaffolding requests ("new repo" / "spin up project" → new-project), or release-flow phrasings ("cut a release" / "ship vX.Y.Z" / "tag and push" → release-helper).
Invoke for any request to normalize, clean up, reformat, lint, fix, or check the style of a CHANGELOG.md file. Trigger on "normalize changelog", "fix changelog format", "clean up CHANGELOG entries", "check changelog style", "make the changelog consistent", "lint CHANGELOG.md", or `/changelog-normalize`. Use this — not freeform editing — whenever a CHANGELOG already exists and needs to conform to Keep-a-Changelog structure: canonical subheadings in spec order, commit/PR refs on every entry, no process narrative. Voice (imperative vs descriptive) is the author's choice — the skill validates structure and process-narrative content, not voice. Single responsibility: reformat existing entries. Does NOT invent, add, or remove changelog content. Skip for: writing release notes from scratch, summarizing commits into a new changelog, cutting a release / tagging a version / "release vX.Y.Z" / "ship X.Y.Z" (use `release-helper`, which composes this skill as its pre-step), or non-CHANGELOG markdown.
Invoke for /new-project or any request to create, start, scaffold, bootstrap, initialize, or spin up a new Python project or Python GitHub repository from scratch. Use this — not general coding — when the user wants a fresh Python repo that doesn't exist yet, with or without mentioning specific tooling. Automates GitHub repo creation, linting, testing, type checking, pre-commit hooks, and coverage in one step. Skip for: existing projects, non-Python languages, or questions about what templates contain.
Invoke for /release, "cut a release", "ship vX.Y.Z", "tag and push a release", "publish version X.Y.Z", or any request to perform the release sequence on an existing Python project that follows Keep-a-Changelog. Rotates [Unreleased] → versioned section, commits, annotated-tags, pushes, then bumps pyproject metadata to the next dev cycle. Use this — not ad-hoc git commands — whenever the user wants to release, even if they don't say "skill". For existing projects being released, not /new-project scaffolding. Skip for: non-Python projects without pyproject.toml, projects without a Keep-a-Changelog CHANGELOG.md, or pre-release / RC / alpha / beta tags (this skill handles final vX.Y.Z releases only).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Python project scaffold with mature rule-guarding wired from commit 1. Fork or clone, run one command, get a green-CI project ready for your first feature.
Starting a new Python project well takes ~30 minutes of repetitive setup: venv, ruff, pyright, pytest, coverage, pre-commit hooks, GitHub Actions matrix, dependabot, issue templates, CHANGELOG scaffolding, ADR ledger, type-hint discipline, src layout. Get it wrong and you spend the first week of every project hunting drift instead of writing code. This scaffold ships every convention pre-wired so you start at "first feature" instead of "first config."
A Python scaffold + Claude Code plugin for developers who want a well-structured, well-rule-guarded baseline from commit 1, plus AI helpers that automate lifecycle steps (scaffold a new project, normalize CHANGELOG, run releases, audit pre-PR diffs).
The scaffold ships with the conventions the SE discipline broadly agrees on, wired up from commit 1 — tests, CI, CHANGELOG, ADRs, type hints, pre-commit hooks. The plugin layers on AI-assisted helpers for the steps you do repeatedly.
This is not a tutorial. It assumes you already know Python and SE practices and want a working example to start from rather than configuring from scratch. Pair it with docs/concepts.md (glossary) and docs/enforcement-model.md (architecture) inside any scaffolded project.
Non-negotiable hygiene/safety rules the scaffold pins via tests, hooks, and CI:
| Rule | Why |
|---|---|
No print() in production code | Use logging — print() pollutes stdout and indicates leftover debug. |
| No secrets in repo | Pattern scan for API keys, AWS access IDs, OpenAI-style keys, bearer tokens. |
| Type hints on public functions | Self-documenting API; catches signature mistakes at type-check time. |
| No mutable default args | Python language gotcha — shared state across calls. |
| Parameterized SQL only | SQL injection is a bad habit even in personal tools. |
src/ layout exists | Structural — many downstream pinning tests assume this layout. |
| Keep-a-Changelog structural format | [Unreleased] section; subheadings drawn from the KaC vocabulary (Added / Changed / Deprecated / Removed / Fixed / Security, in 1.1.0 spec order). Voice and tone are your choice. |
| Pre-commit hooks | Formatting, EOF newline, merge-conflict markers, YAML/TOML validity — all configured. |
CI matrix across requires-python | Every supported runtime gets exercised. |
| Linter + formatter + type checker + test runner + coverage gate exist | Tools wired into CI from commit 1. The specific values (coverage %, line length, etc.) are configurable. |
These rules are pinned by tests/test_rules.py and tests/test_cohesion.py and run on every commit.
These have sensible defaults but no mechanical enforcement — change without forking:
| Default | How to change |
|---|---|
| Coverage threshold = 80% | Edit [tool.coverage.report] fail_under in pyproject.toml. |
| Conventional-commit prefixes (suggested) | Use them, skip them, or pick a different convention — the scaffold doesn't lint commit messages. |
| CHANGELOG entry voice (recommended: describe WHAT changed and WHY it matters) | Document your project's preferred voice in your CONTRIBUTING.md. The plugin's changelog-normalizer validates structure but doesn't rewrite voice. |
| Summary paragraph before bullets in CHANGELOG versions | Recommended for top-down readability, not enforced. |
| ADR for hard-to-reverse architectural decisions | Strongly recommended — docs/adr/ template included. Not mechanically enforced. |
Bullet glyph (- vs *) | Pick one and be consistent within your project. |
| Line wrap width, prose style, etc. | Pick what fits your project. |
The plugin (separately versioned in plugins/new-project/) layers on more opinionated tooling — see its README.md for what it adds and how to override.
python3 scripts/init-project.py
You'll be asked for project name, description, license, Python floor. Everything else (package name, year, author, GitHub username) is auto-derived from git config and gh CLI. The script stages the substituted tree to a tmpdir, atomically swaps it to the repo root, removes scaffold-only files, optionally resets git history, and makes the first commit.make test to confirm the green CI baseline.npx claudepluginhub yuzh98/python-project-scaffold --plugin python-project-scaffoldComplete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.