convez.ai
SkillProdutividadeIntermediário
AliceLJY

Digital Clone Skill

AliceLJY/digital-clone-skill

Crie clones digitais que falam como você a partir do seu corpus de dados

Ver no GitHub
InicialPluginScore · de 0 a 100

Skill para Claude Code que converte histórico de conversas e escritos em um clone digital funcional. Guia o usuário através de 6 estágios — desde coleta e limpeza de corpus até extração de personalidade, geração de system prompt e verificação — com dois modos: Self Mode (clonar a si mesmo) e Mentor Mode (clonar figuras públicas).

Instalação

$npx convez-ai AliceLJY/digital-clone-skill

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 4 semanas
Versão
v3.3.0
Issues abertas
0
Contribuidores
2

Casos de uso

  • Criar um assistente digital personalizado baseado em suas conversas e escritos
  • Clonar a personalidade de mentores ou figuras públicas para orientação
  • Gerar system prompts precisos a partir de análise de voz e comportamento

Veredito

Ferramenta ambiciosa e bem-estruturada para síntese de personalidade em IA. Excelente para quem quer criar assistentes especializados, mas requer disciplina na coleta e limpeza de corpus — a qualidade do clone depende diretamente da qualidade dos dados de entrada.

README

A tradução para o português deste README ainda está na fila.

Digital Clone

Corpus-Driven Digital Clone Skill for Claude Code

Collect your AI conversations, extract your personality, deploy a clone that talks like you.

A Claude Code Skill that turns conversation history and writings into a digital clone — guiding you through corpus collection, cleaning, personality extraction, system prompt generation, and verification. Optional Bun-based CLI/MCP tools are included for mechanical data preprocessing.

MIT License Claude Code

English | 简体中文


What It Does

The Skill walks you through a 6-stage pipeline, entirely conversational — no runtime dependencies required:

StageNameWhat Happens
1Target ProfilingIdentify the clone target and map data sources
2Data HuntingCollect raw corpus (transcripts, articles, research)
3Data RefiningClean, dedup, PII sanitization, quality assessment
4Soul ForgingExtract personality, generate System Prompt
5VerificationTrap-question testing with pass criteria (target: ≥80%)
6DeploymentPlatform-specific deploy guide (NotebookLM / bot / generic LLM)

Two Modes

  • Self Mode — clone yourself from local AI conversations and writings
  • Mentor Mode — clone a public figure via 6-angle parallel research (primary voice, live reactions, external views, decisions, social fragments, timeline)

Quick Start

Install the Skill (this is the whole installation):

mkdir -p ~/.claude/skills/digital-clone
curl -o ~/.claude/skills/digital-clone/SKILL.md \
  https://raw.githubusercontent.com/AliceLJY/digital-clone-skill/main/SKILL.md

Then in Claude Code:

帮我克隆自己 / "Clone myself from my articles and CC transcripts" 帮我克隆纳瓦尔做数字导师 / "Clone Naval as my digital mentor"

The Skill handles everything conversationally, stage by stage, with your approval at each step. All outputs go to ./clone-workspace/ in your current directory.


Optional: CLI Preprocessing Tools

Requires Bun. The CLI does not run on Node.js (it uses Bun's TypeScript module resolution). If you don't use Bun, skip this section entirely — the Skill covers the full pipeline on its own.

For large corpora (thousands of transcript files), the CLI does the mechanical work faster than in-conversation processing:

git clone https://github.com/AliceLJY/digital-clone-skill.git
cd digital-clone-skill
bun install

bun run src/cli.ts init --target "Your Name" --mode self
bun run src/cli.ts ingest --source all
bun run src/cli.ts refine
bun run src/cli.ts quality

Important: the workspace path is relative to where you run the commands. If you preprocess with the CLI, start your Claude Code session in the same directory so the Skill finds ./clone-workspace/. The refined corpus separates *-user.md (your voice — used for personality extraction) from *-assistant.md (AI replies — reference only, excluded from Soul Forging).

CommandDescription
bun run src/cli.ts initInitialize workspace and config
bun run src/cli.ts ingest --source <src>Scan corpus (cc, codex, gemini, memory, articles, all)
bun run src/cli.ts import <path>Import external files (Mentor Mode)
bun run src/cli.ts refineClean, dedup, sanitize
bun run src/cli.ts qualityGenerate quality report
bun run src/cli.ts statsShow corpus statistics
bun run src/cli.ts verify-templateGenerate test case template
bun run src/cli.ts deploy-guide --platform <p>Generate deployment guide
bun run src/cli.ts refreshRe-scan sources and merge new content into the refined corpus

Set CLONE_WORKSPACE to pin the workspace to a fixed path shared between CLI and Skill sessions.

refresh can optionally pull recent memories from a RecallNest install (the author's memory system; set RECALLNEST_CLI or place it at ~/recallnest/lm). Without it, use --skip-recallnest.

ToolDescription
clone_ingestScan and collect corpus
clone_refineClean and deduplicate
clone_qualityAssess corpus quality
clone_statsShow statistics
clone_read_corpusRead refined corpus slices (defaults to user-side text)

MCP Setup (Claude Code):

{
  "mcpServers": {
    "digital-clone": {
      "command": "bun",
      "args": ["run", "/path/to/digital-clone-skill/src/mcp-server.ts"],
      "cwd": "/path/to/digital-clone-skill"
    }
  }
}
FileRole
SKILL.mdClaude Code Skill — the full 6-stage pipeline (the product)
src/cli.tsOptional CLI entry (Bun)
src/mcp-server.tsOptional MCP tools (Bun)
src/parsers.tsMulti-source transcript parsing
src/ingest.tsCorpus collection pipeline
src/refine.tsDedup + PII sanitize + normalize
src/quality.tsQuality assessment + report
src/templates.tsVerify + deploy template generation
src/config.tsConfiguration management

Credit

SourceContribution
Claude CodeFoundation, CLI, MCP server, parsers
RecallNestParser architecture for CC/Codex/Gemini transcripts
@MinLiBuildsNaval clone tutorial — original inspiration
alchaincyf/nuwa-skill6-angle research + three-pass verification
LvPengfei1/PersonaVaultEvidence grading + capability boundaries

Author

Built by 小试AI (@AliceLJY) for the WeChat public account 我的AI小木屋.

Ecosystem

Part of the 小试AI open-source AI workflow:

ProjectDescription
recallnestMCP memory workbench (LanceDB + Jina v5)
content-publisherImage generation + layout + WeChat publishing
openclaw-tunnelDocker ↔ host CLI bridge (/cc /codex /gemini)
telegram-ai-bridgeTelegram bots for Claude, Codex, and Gemini
claude-code-studioMulti-session collaboration platform for Claude Code
cc-empireComplete Claude Code workflow scaffold (rules + hooks + agents)
etwin-botE-Twin Telegram bot — this skill's 1:1 instantiation as a runnable bot
trio-handoffBidirectional handoff bundles for AI coding agents

License

MIT

Ver o original no GitHub

Bom para

Relacionados