First-Love Skill Creator

Name: First-Love Skill Creator
Rating: 74 (1 reviews)
Author: z969081067-commits

Trust Score 74/100

Creates a personal 'first love' skill by importing chat logs, photos and social posts, then generating structured memory and persona files for private, evolving

triggers:first lovecreate-first-loveintakememorypersonaimport chatsphoto analysis

GitHub SKILL.md

What it does

Builds a private, structured representation of a personal romantic memory: ingests chat exports, photos, and social media content; extracts key moments and persona traits; and generates memory.md, persona.md, meta.json and a response_profile for an evolving personal skill. The workflow includes intake questions, import/parsing tools, versioning, and guardrails to keep the content local and non-harmful.

When to use it

Use when a user wants to preserve and revisit personal memories in a structured way, create a prototype conversational persona based on real material, or maintain an evolving private archive for reflection. Not for contacting real people or publishing private data.

What's included

Scripts: the SKILL references parser and writer tools (wechat_parser, qq_parser, social_parser, photo_analyzer, skill_writer, version_manager) though they may be provided in the CLAUDE_SKILL_DIR rather than this repo.
References: stepwise intake prompts, merger and analysis prompts, and safety boundary guidance.
Instructions: detailed workflow for intake, import, analysis, preview and versioned writes.

Compatible agents

Designed for Claude Code environments and agents with file Read/Write/Bash capabilities; will work with coding-capable assistants that can execute parsing scripts locally.

Audit Summary

A bilingual (Chinese/English) skill for creating personalized 'first love' AI personas from chat logs, photos, and memories. The SKILL.md is thorough with detailed multi-step intake flows, but all functional scripts (wechat_parser, qq_parser, social_parser, photo_analyzer, etc.) are referenced but not bundled — the skill cannot work without fetching them from the GitHub repo. No scripts were available to test. Shell injection risk exists from unquoted variable interpolation in bash command templates.

Watch Out

All tool scripts (7+ Python files) are referenced via ${CLAUDE_SKILL_DIR}/tools/ but not bundled — skill requires external download to function
Shell injection risk: some command templates use unquoted variable interpolation (e.g., --file {path})
Processes highly personal data (chat logs, photos) — privacy-sensitive use case
Bilingual skill requires language detection on first message

Notes

The skill is essentially a detailed prompt/guide rather than a functional skill since all implementation scripts are missing. The SKILL.md itself is well-written and thoughtful (includes safety boundaries about not idealizing, not contacting real people), but the dependency on external scripts that aren't included means it can't be used out-of-the-box. The GitHub repo (z969081067-commits/first-love-skill) would need to be cloned for the tools to work.

Information

Repository: first-love-skill
Stars: 10

Trust Score

Overall74

Security88

Code Quality58

Architecture65

Usefulness42

Related Skills

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Retriever (Membrane CLI)

Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.

Cost Tracker

Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.

Bash Pro

Defensive, production-grade Bash scripting patterns and CI/CD best practices: strict mode, safe argument parsing, testing with Bats, and tooling (ShellCheck/shf

Audit Agents/Skills/Commands

Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.

NotebookLM Research Agent

End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c

Cashu Wallet

Privacy-focused Bitcoin wallet skill enabling sending/receiving via Lightning and Cashu ecash tokens, with multi-mint support and basic wallet management comman

CLS-Certify — Skill Security Auditor

Enterprise-grade multi-dimensional security scanner for Agent Skills that produces S+/S/A/B/C/D ratings and structured HTML/PDF reports.

Back to Skills