Create-Yourself Skill

Trust Score 77/100

Generates a personal ‘self’ skill by analyzing a user's chat logs, photos, and notes to produce a runnable persona and memory skill in English and Chinese.

triggers:create-yourself/create-yourselfself skilldistill yourselfgenerate persona

GitHub SKILL.md

What it does

This skill guides an agent through building a personalized runnable skill that captures a user's persona and self-memory. It ingests source materials (chat exports, social posts, photos), extracts speaking style and life events, and generates files (.md and meta.json) and a combined SKILL.md that makes the agent "think and speak" like the user. The skill supports both English and Chinese.

When to use it

Use when a user wants to distill their own writing, chat history, or photos into a persistent persona for testing, roleplay, or personal archiving. Helpful for creating personal assistants, simulated selves, or continuity profiles for long-running agents.

What's included

Scripts: tooling hooks described (parsers and writers) though not bundled as executable scripts in the discovered repo.
References: guidance, prompts, and structured flows for intake, analysis, persona building, merging, and version management.
Instructions: step-by-step flow for intake questions, source import options (WeChat, QQ, social, photos, paste), analysis lines (Self Memory and Persona), preview and confirmation, file generation, evolution (append/rollback), and management commands.

Compatible agents

Designed for higher-level authoring agents with file and shell access (Claude Code, Codex, or similar), since it expects Read/Write/Edit/Bash tools to import and generate files.

Audit Summary

A bilingual (Chinese/English) persona-generator skill that walks users through creating a digital self from chat logs, photos, and notes. No scripts were bundled — it references external tools via ${CLAUDE_SKILL_DIR}/tools/ (wechat_parser, qq_parser, photo_analyzer, skill_writer, version_manager) which weren't available for testing. The SKILL.md is well-structured with clear step-by-step flows, but relies heavily on these unbundled scripts being present. Contains a scoped rm -rf in the delete command with confirmation, which is the main security concern.

Watch Out

Requires unbundled tools in ${CLAUDE_SKILL_DIR}/tools/ (wechat_parser.py, qq_parser.py, photo_analyzer.py, skill_writer.py, version_manager.py) — skill won't work without them
Delete command uses rm -rf on .claude/skills/{slug} — confirmation step exists but command is still destructive
Primarily designed for Chinese messaging platforms (WeChat, QQ) — limited appeal outside that ecosystem

Notes

Creative concept but heavily dependent on external tool scripts not bundled with the skill. The skill body is essentially a detailed prompt/workflow guide. Architecture doesn't follow skill spec conventions (no scripts/ or references/ dirs, tools referenced by env var path). Bilingual support is a nice touch.

Information

Repository: yourself-skill
Stars: 2,254
Installs: 0

Trust Score

Overall77

Security87

Code Quality72

Architecture58

Usefulness55

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.

Caveman Compress

Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.

Go Data Structures

Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container

Memory Search

Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.

Create & Configure Agents

Helpers and templates to scaffold agent directories, generate agent.yaml, and author SOUL.md and RULES files for new agents.

悟道真英雄

Create a personalized A-share trading persona that grows with your trade history: analyze screenshots, ingest chat posts, track watchlists and regrets, and enfo

hmem — Setup

Interactive installer and setup guide for hmem (persistent memory MCP server); automates .mcp.json config, memory dir, and adds agent hooks for Claude Code, Gem

OpenViking Memory Plugin

Provides automatic long-term memory capture and recall for OpenClaw agents: auto-capture, auto-recall, and memory management tools for more context-aware conver

Back to Skills