Cloneify

End-to-end conductor for cloning a piece of software. Walks the user through four gated phases — scope → deep research → plan (grilled + Codex-reviewed) → a paste-ready build prompt — composing the deep-research and grill-me-codex skills along the way. Use this whenever the user wants to clone, rebuild, reimplement, or make their own version of an existing app or tool ("clone WhisperFlow", "build my own Superhuman", "I want a local version of X", "reverse-engineer this app into a spec", "let's clone something"), or asks for a repeatable research→plan→build pipeline for replicating software. Tr

43 stars 5 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add cth9191/cloneify --skill cloneify
Manual install
git clone --depth 1 https://github.com/cth9191/cloneify.git /tmp/cloneify
mkdir -p ~/.claude/skills
cp -r /tmp/cloneify/. ~/.claude/skills/cloneify

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# cloneify

A guided pipeline that turns "I want to clone X" into a single paste-ready prompt
that builds it. You are the conductor: you run four phases, **stop at every gate
for the user's go-ahead**, and compose two existing skills (`deep-research`,
`grill-me-codex`) rather than reinventing them.

The real deliverable is **Phase 3's goal-prompt** — one self-contained block the
user pastes into a fresh Claude Code session to actually build the clone. Phases
0–2 exist to make that prompt *correct*: scoped, researched, and hardened.

## Why gates matter

Each phase is expensive and consequential (research burns tokens; grilling takes
real user time; the plan steers everything downstream). The user must stay in the
driver's seat. **Never auto-advance.** Finish a phase, show what you produced,
then ask the explicit gate question and wait. If the user wants to revise the
previous phase instead of moving on, loop back — don't force forward.

## Run folder & state

Pick a short kebab-case slug for the target (e.g. `whisperflow`, `superhuman`,
`raycast`).

**Where the run folder lives — resolve this BEFORE writing any file.** Artifacts
must land in the **user's project, next to where they'll actually build**, NOT
inside this skill's own base directory. The base directory named in the skill
invocation is where the skill *lives*, never where its output goes. Concretely:

- The run folder is `<run-root>/clone-run/`, where `<run-root>` is a directory in
Read the full skill on GitHub

Details

Skill name
cloneify
License
MIT
Repo updated
3 July 2026

FAQ

What does the Cloneify skill do?

End-to-end conductor for cloning a piece of software. Walks the user through four gated phases — scope → deep research → plan (grilled + Codex-reviewed) → a paste-ready build prompt — composing the deep-research and grill-me-codex skills along the way. Use this whenever the user wants to clone, rebuild, reimplement, or make their own version of an existing app or tool ("clone WhisperFlow", "build my own Superhuman", "I want a local version of X", "reverse-engineer this app into a spec", "let's clone something"), or asks for a repeatable research→plan→build pipeline for replicating software. Tr

How do I install the Cloneify skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add cth9191/cloneify --skill cloneify. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cloneify popular?

It lives in cth9191/cloneify, which has 43 GitHub stars and 5 forks.

Related skills

Design

43

aws-samples/sample-kiro-cli-multiagent-development

Start a new plan interactively — clarify the problem, research, then write plan.md and tasks.md. Use when asked to design, scope, plan, or start a new plan or feature.

Research & Science

Deep Research Framework

43

hamletlg/deep-research-pipeline

Methodology for conducting rigorous, multi-source, deep-dive research. Includes PICO framing, scope boundaries, depth matrices, anti-hallucination guardrails, chaining strategies, and professional output structures. Use for complex topics requiring exhaustive analysis.

Research & Science

Lead Research Assistant

52

ArogyaReddy/ComposioHQ-awesome-claude-skills

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

Research & Science11

Gtm Pipeline:setup

77

keinsaasforever/gtm-pipeline-skills

Onboarding skill — walks a new user through installation, API key configuration, PhantomBuster agent IDs, first client setup (auto-research from domain + 5 refinement questions), and a skill tour. Run this first after cloning the repo. Also triggers on "set up gtm skills", "configure gtm", "gtm onboarding", "first time setup".

Research & Science

Scientific Fa Translation Skill

43

isArman/scientific-fa-translation-skill

Translate scientific documents, papers, articles, books, and technical docs (any software/science stack—not tied to one product) into academic Persian (Farsi) with strict RTL/bidi and untranslated English technical terms. Also reviews an existing Persian translation against these rules. Use when the user asks to ترجمه, translate a paper/article/book/docs, راست‌چین, RTL, PDF, چاپ, Persian scientific translation, or invokes scientific-fa-translation / scientific-fa-translation-skill. Do NOT use for coding, explaining code, commit messages, UI copy, literary translation, or casual Persian chat.

Research & Science

Paper Explainer

47

PompeiiChan/skills-ExplainPaper

AI论文解读工具。面向产品经理、运营等非技术背景但对AI感兴趣的读者,将晦涩的学术论文转化为图文并茂的通俗研报:讲清楚”这个技术解决什么问题、有多厉害、对业务意味着什么”,配以极简科技风插图,并输出莫兰迪风格的 HTML 单文件。

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.