본문으로 건너뛰기
cccskills
무료GitHub에 공개

repo-scaffold

Initialize GitHub repositories with standard files and configuration. Generates LICENSE, CONTRIBUTING.md, SECURITY.md, issue/PR templates, CI config, and .gitignore. Detects project type and adapts templates accordingly.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구GitHub

실행 점수 미검증

설치 방법 보기

포함된 파일(4)

  • SKILL.md6.6 KB
  • EXAMPLES.md4.6 KB
  • LICENSE1.0 KB
  • REFERENCE.md13.4 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Repo Scaffold

Initialize GitHub repositories with standard files and configuration. This skill generates LICENSE, CONTRIBUTING.md, SECURITY.md, CODEOWNERS, .gitignore, .editorconfig, YAML-based issue templates, PR template, CI config skeleton, and optional safety files. It detects project type from existing files and adapts all templates accordingly.

Install

claude skill install repo-scaffold

When to Use

This skill should be used when:

  • Setting up a new GitHub repository from scratch
  • Adding missing standard files to an existing repository
  • Standardizing repository configuration across projects
  • Preparing a private repo for open-source release

Usage

/repo-scaffold [repo-path] [--license MIT|Apache-2.0|ISC] [--public] [--ci github-actions|none]
FlagDefaultDescription
repo-path. (cwd)Path to the git repository root
--licenseMITLicense type (MIT, Apache-2.0, ISC, GPL-3.0, BSD-2-Clause)
--publicoffInclude .public-repo, .pii-allowlist, .commit-msg-blocklist
--cigithub-actionsCI provider skeleton (github-actions or none)

Procedure

Step 1: Validate Repo Path

Confirm the target path is an initialized git repository (contains .git/). If not, halt and inform the user. Never run git init without explicit permission.

Step 2: Scan Existing Files

Inventory the repo root and .github/ directory for any files this skill would generate. Build a conflict list. Never overwrite existing files. If conflicts exist, present them and ask which to skip or replace.

Step 3: Detect Project Type

Identify the primary language and tooling by checking for marker files:

Marker FileProject Type
package.jsonNode.js / JavaScript / TypeScript
pyproject.toml, setup.py, requirements.txtPython
Cargo.tomlRust
go.modGo
Multiple markersMulti-language
None of the aboveGeneric

If multiple markers are found, treat as multi-language and combine relevant patterns.

Step 4: Generate Files

Generate each file with language-appropriate content. Refer to REFERENCE.md for templates, patterns, and format specifications.

4a. LICENSE

Prompt the user for license choice if --license was not provided. Default to MIT. Insert the current year and the repo owner's name (from git config user.name or ask). See REFERENCE.md license comparison table for guidance.

4b. .gitignore

Generate language-appropriate ignore patterns based on the detected project type. Combine patterns for multi-language repos. Always include OS-level ignores (.DS_Store, Thumbs.db) and editor ignores (.vscode/, .idea/).

4c. CONTRIBUTING.md

Generate a fork-branch-PR contribution guide. Include:

  • Fork and clone instructions
  • Branch naming conventions (feat/, fix/, docs/)
  • Code style notes (link to linter config if detected)
  • Commit message format
  • PR checklist

4d. SECURITY.md

Generate a security policy with:

  • Supported versions table (populate from package version if detectable)
  • Vulnerability reporting instructions (email-based, not public issues)
  • Response timeline expectations

4e. CODEOWNERS

Scan the top-level directory structure and generate a CODEOWNERS file. Map directories to the repo owner by default. Add comments explaining how to customize.

4f. .editorconfig

Generate settings appropriate to the detected project type:

  • Indent style and size
  • End-of-line character
  • Trim trailing whitespace
  • Insert final newline
  • Charset (utf-8)

4g. .github/ISSUE_TEMPLATE/bug-report.yml

Generate a YAML form-based bug report template with fields: description, steps to reproduce, expected behavior, actual behavior, environment, and optional screenshots. See REFERENCE.md for YAML form spec.

4h. .github/ISSUE_TEMPLATE/feature-request.yml

Generate a YAML form-based feature request template with fields: problem statement, proposed solution, alternatives considered, and additional context.

4i. .github/pull_request_template.md

Generate a PR template with sections: summary of changes, type of change (checkboxes), testing performed, and checklist.

4j. .github/workflows/ci.yml

Generate a CI skeleton for GitHub Actions (unless --ci none). Include:

  • Trigger on push to main and pull requests
  • Language-appropriate setup step
  • Lint step (ESLint, ruff, clippy, golangci-lint)
  • Test step (language-appropriate test runner)
  • Placeholder comments for additional steps

4k. Optional: Safety Files (when --public)

When --public is passed, also generate:

  • .public-repo — Empty marker file indicating the repo is public
  • .pii-allowlist — One regex per line; starts with a comment header explaining usage
  • .commit-msg-blocklist — One term per line; starts with a comment header and common defaults

Step 5: Present Plan

Before writing any files, present the full list of files to be created with a one-line description of each. Show which files were skipped due to conflicts. Ask the user to confirm before proceeding.

Step 6: Write Files

Write all confirmed files. Report each file as it is written.

Step 7: Summary

Print a summary table:

  • Files created (with paths)
  • Files skipped (with reason)
  • Suggested next steps (e.g., review CODEOWNERS, customize CONTRIBUTING.md, add secrets to CI)

Key Principles

  1. Never overwrite existing files. Always scan first, flag conflicts, and ask.
  2. Always ask before writing. Present the plan and get explicit confirmation.
  3. Language-appropriate defaults. Detect the project type and tailor every template.
  4. Minimal but complete. Generate the standard set every well-maintained repo needs, nothing more.
  5. Composable. Each file stands alone. Re-run the skill later to add missing files without disrupting existing ones.

References

  • REFERENCE.md — License comparison, .gitignore patterns, YAML template spec, CI skeletons, CODEOWNERS syntax, .editorconfig settings, SECURITY.md and CONTRIBUTING.md templates
  • EXAMPLES.md — Worked examples for Node.js, Python, and public repo scaffolding

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

A/B and multivariate testing methodology. Design experiments, calculate sample sizes, determine statistical significance, avoid common pitfalls, and interpret results. Platform-agnostic framework applicable to landing pages, emails, ads, pricing, and product features. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, or conversion experiments.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1772026년 5월 15일 업데이트

Google and Meta paid media account structure evaluation. Audits campaign/ad set architecture against conversion volume minimums, budget thresholds, and targeting overlap. Identifies over-segmentation, under-segmentation, budget fragmentation, and structural anti-patterns blocking algorithmic learning. Provides consolidation roadmaps with migration plans. Use when inheriting accounts, quarterly health checks, or before scaling budgets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1772026년 5월 15일 업데이트

Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) specialist. Optimize content and websites to appear in AI-generated answers from ChatGPT, Perplexity, Claude, Google AI Overviews, and other LLM-powered search experiences. Use when the user asks about AI search optimization, AEO, GEO, AI Overviews, appearing in AI answers, LLM citations, or optimizing for generative search.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1772026년 5월 15일 업데이트

brand-dna

무료

Extract brand identity from a website URL — voice, colors, typography, imagery, values, and target audience — into a structured brand-profile.json. The profile feeds downstream skills (seo-content-writer, email-composer, frontend-design, pro-deck-builder, cross-platform-audit) for brand-consistent output. Use when the user says brand DNA, brand profile, extract brand, analyze brand, brand voice, brand identity, brand colors, or brand style guide.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1772026년 5월 15일 업데이트

Develop brand voice, tone matrices, messaging frameworks, and brand book documentation. Use when the user asks about brand voice, tone of voice, brand guidelines, messaging framework, or brand consistency.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1772026년 5월 15일 업데이트

braze

무료

Braze customer engagement platform expertise. Audit campaigns, Canvases, segments, messaging channels, and data architecture. Use when the user asks about Braze, customer engagement, push notifications, in-app messaging, cross-channel orchestration, or lifecycle marketing at scale.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

thatrebeccarae/claude-marketing1772026년 5월 15일 업데이트

thatrebeccarae의 스킬 모두 보기

이 스킬의 문제 신고