minicoohei/hrfish

최근 기록된 소스 활동: 2026년 3월 15일 22:33

SkillsMP 카탈로그 업데이트: 2026년 11월 9일 14:22

수집된 skills: 1

GitHub 스타: 0
GitHub 포크: 0

AI 어시스턴트로 설치

이 프롬프트를 복사해 사용 중인 AI 어시스턴트에 입력하세요.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/minicoohei/hrfish.

저장소 README

README 원본 파일: README.md

README 원본 보기

README 전체 펼치기

# MiroFish AI Career Simulator powered by Claude Code SubAgents. Simulate 10-year career trajectories with multi-path analysis, social sentiment simulation, and detailed HTML reports. <div align="center"> <img src="docs/images/cli_demo.gif" alt="MiroFish CLI Pipeline Demo" width="80%"/> Full pipeline: profile init, path design, 5-way expansion, scoring, 30-agent swarm, HTML report </div> ## What It Does Input a resume and career context. MiroFish generates a comprehensive career simulation report covering: - **5 parallel career paths** with best/likely/base/worst scenarios per path - **10-year income projections** with interactive charts - **30 AI agents** discussing your career choices from different perspectives - **Fact-checked claims** against real market data - **Reskilling recommendations** prioritized by cross-path impact ### Report Output <div align="center"> <img src="docs/images/report_demo.gif" alt="MiroFish Report Sections" width="80%"/> Self-contained HTML report with 10 interactive sections </div> ### Report Sections <table> <tr> <td width="50%"><img src="docs/images/report_01_profile.png" alt="Profile"/> 01 Profile - Candidate overview with career history, skills, and financials</td> <td width="50%"><img src="docs/images/report_02_core_skills.png" alt="Core Skills"/> 02 Core Skills - Fundamental strengths identified by 30 swarm agents</td> </tr> <tr> <td><img src="docs/images/report_03_overview_radar.png" alt="Scenario Analysis"/> 03 God's Eye View - 5 paths x 3 scenarios with probability-weighted scoring</td> <td><img src="docs/images/report_04_income_chart.png" alt="Income Chart"/> 04 Income Projections - 10-year salary trajectories across all paths</td> </tr> <tr> <td><img src="docs/images/report_05_career_paths.png" alt="Career Paths"/> 05 Career Paths - Period-by-period breakdown with events, blockers, and agent commentary</td> <td><img src="docs/images/report_06_reskill.png" alt="Reskilling"/> 06 Reskilling - Skills prioritized by cross-path relevance</td> </tr> <tr> <td><img src="docs/images/report_07_mirror.png" alt="Parallel Self"/> 07 Parallel Self - How your parallel-world selves would view each other</td> <td><img src="docs/images/report_08_swarm_voices.png" alt="Agent Voices"/> 08 External Voices - 30 AI agents discuss each career path</td> </tr> <tr> <td><img src="docs/images/report_09_macro_trends.png" alt="Macro Trends"/> 09 Macro Trends - Industry trends and labor market risks</td> <td><img src="docs/images/report_10_knowledge_graph.png" alt="Knowledge Graph"/> 10 Knowledge Graph - Interactive visualization of career entity relationships</td> </tr> </table> ## Origin This project is a Claude Code-native fork of [666ghj/MiroFish](https://github.com/666ghj/MiroFish), the multi-agent social simulation platform. **What we kept from the original:** - Domain models: `BaseIdentity`, `CareerState`, life event definitions - Core engines: `LifeEventEngine`, `BlockerEngine` (6-category career blockers) - Zep knowledge graph integration for candidate memory - OASIS-inspired social simulation concepts **What changed:** - Replaced OpenAI + Flask backend with Claude Code SubAgent orchestration - Removed frontend (Vue.js) and Docker -- output is a self-contained HTML report - Added multi-path expansion (5 paths x 4 scenarios = 20 trajectories) - Added SNS Agent Swarm (30-50 AI characters discussing career decisions) - Added Pydantic v2 data contracts with normalizer layer for LLM output variance - Added fact-checking pipeline (Tavily) and macro trend analysis - Packaged as standalone Python CLI (`cc_layer`) ## Requirements - Python 3.11+ - [Claude Code](https://docs.anthropic.com/en/docs/claude-code) (for SubAgent orchestration) ## Installation ```bash pip install -e . # Optional dependencies pip install -e ".[zep]" # Zep knowledge graph pip install -e ".[search]" # Tavily web search pip install -e ".[otel]" # OpenTelemetry tracing pip install -e ".[all]" # Everything ``` ## Quick Start ### Demo Mode (no API keys needed) Generate a report from bundled sample data: ```bash python -m cc_layer.cli.pipeline_run \ --session-dir cc_layer/fixtures/samples/session_01 \ --phase report ``` ### Full Pipeline Check pipeline status and follow guided steps: ```bash python -m cc_layer.cli.pipeline_run \ --session-dir cc_layer/state/my_session \ --phase status ``` The orchestrator guide at `cc_layer/prompts/orchestrator.md` provides step-by-step instructions for running the complete pipeline with Claude Code. ## Architecture ``` cc_layer/ app/ models/ # Domain models (CareerState, BaseIdentity, etc.) services/ # Business logic (event engine, blocker engine, etc.) utils/ # Shared utilities (logging, retry, validation) cli/ # CLI tools (sim_init, sim_tick, path_score, report_html, etc.) schemas/ # Data contracts (canonical models, normalizer, validator) prompts/ # SubAgent prompt templates fixtures/ # Sample session data for testing tests/ # Test suite ``` ### Pipeline Phases | Phase | Tool | Description | |-------|------|-------------| | 0 | `sim_init` | Initialize candidate profile and career state | | 1a | SubAgent | Design 5 career paths (PathDesignerAgent) | | 1b | SubAgent x5 | Expand each path into 10-year scenarios (PathExpanderAgent) | | 2 | `path_score` | Score and rank paths | | 3 | `generate_swarm_agents` | Create SNS agent profiles | | 4 | SubAgent | Run 40-round swarm discussion | | 5-6 | `fact_check` | Extract and verify claims | | 7 | SubAgent | Analyze macro trends | | 8 | `pipeline_run --phase report` | Generate HTML report | ## CLI Reference All CLIs are self-documenting: ```bash python -m cc_layer.cli.sim_init --help python -m cc_layer.cli.path_score --help python -m cc_layer.cli.report_html --help python -m cc_layer.cli.pipeline_run --help ``` ## Testing ```bash python -m pytest cc_layer/tests/ -v ``` ## License MIT

저장소 README를 불러오는 중…

이 저장소의 skills

소프트웨어 개발자

직업 카테고리 1개 · 100% 분류됨

skill

직업 분류

설명

업데이트

mirofish-orchestrator

소프트웨어 개발자

MiroFish CC-Native シミュレーション全体フロー・CLI呼出手順・SubAgent起動手順

원문 언어: 일본어

2026-03-15

수집된 skill 1개 중 1개를 표시합니다.