singularity-claude
installs/mo · npmstarsforks
How to install singularity-claude?
shmayro/singularity-claude
$git clone https://github.com/Shmayro/singularity-claude---
README.md
| 1 | <p align="center"> |
| 2 | <h1 align="center">singularity-claude</h1> |
| 3 | <p align="center"> |
| 4 | <strong>Skills that evolve themselves.</strong> |
| 5 | <br /> |
| 6 | A self-evolving skill engine for Claude Code — create, score, repair, and crystallize skills through autonomous recursive improvement loops. |
| 7 | </p> |
| 8 | <p align="center"> |
| 9 | <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a> |
| 10 | <a href="#installation"><img src="https://img.shields.io/badge/Claude%20Code-Plugin-blue?logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMjQiIGhlaWdodD0iMjQiIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj48Y2lyY2xlIGN4PSIxMiIgY3k9IjEyIiByPSIxMCIgZmlsbD0id2hpdGUiLz48L3N2Zz4=" alt="Claude Code Plugin"></a> |
| 11 | <img src="https://img.shields.io/badge/Version-0.1.0-green" alt="Version"> |
| 12 | <img src="https://img.shields.io/badge/Status-Experimental-orange" alt="Status"> |
| 13 | </p> |
| 14 | </p> |
| 15 | |
| 16 | --- |
| 17 | |
| 18 | ## The Problem |
| 19 | |
| 20 | Claude Code skills are **static**. You write them once, and they stay exactly as they are — even when they fail, produce subpar output, or encounter new edge cases. There's no feedback loop, no way to know which skills are working well, and no mechanism to improve them over time. |
| 21 | |
| 22 | You end up with a growing pile of skills where some work great, some are mediocre, and some are silently broken. The only way to fix them is manual review. |
| 23 | |
| 24 | ## The Solution |
| 25 | |
| 26 | **singularity-claude** adds a recursive evolution loop to your skills: |
| 27 | |
| 28 | ```mermaid |
| 29 | graph TD |
| 30 | Goal["🎯 Goal:<br/>Set up API proxy endpoints"] |
| 31 | Goal --> HasSkill{Skill exists?} |
| 32 | |
| 33 | HasSkill -->|No| Gap["🔍 Gap detected:<br/>recurring pattern"] |
| 34 | Gap --> Create["⚙️ /singularity-create\nGather requirements\nGenerate SKILL.md\nRegister + init scoring"] |
| 35 | Create --> Execute |
| 36 | |
| 37 | HasSkill -->|Yes| Execute["⚡ Execute skill"] |
| 38 | Execute --> Score["📊 /singularity-score\nDispatch assessor agent\nRate 5 dimensions · 0-100"] |
| 39 | Score --> Maturity["🔄 Auto-update maturity\ndraft → tested → hardened"] |
| 40 | |
| 41 | Maturity --> Low{Avg < 50\n2+ runs?} |
| 42 | Low -->|Yes| Repair["🔧 /singularity-repair\nAnalyze telemetry\nRewrite weak dimensions\nBump version · re-test"] |
| 43 | Repair --> Execute |
| 44 | |
| 45 | Low -->|No| High{Avg ≥ 90 · 5+ runs\nhardened · edge cases?} |
| 46 | High -->|Yes| Crystal["💎 /singularity-crystallize\nGit tag + lock version"] |
| 47 | Crystal --> Done["✅ Production-grade skill\nImmutable · rollback-safe"] |
| 48 | |
| 49 | High -->|No| Loop["🔁 Keep using + scoring"] |
| 50 | Loop --> Execute |
| 51 | |
| 52 | style Goal fill:#1d3557,color:#fff,stroke:#0d1b2a |
| 53 | style Gap fill:#e9ecef,color:#000,stroke:#adb5bd |
| 54 | style Create fill:#457b9d,color:#fff,stroke:#1d3557 |
| 55 | style Execute fill:#2a9d8f,color:#fff,stroke:#1a7a6e |
| 56 | style Score fill:#e76f51,color:#fff,stroke:#c1440e |
| 57 | style Maturity fill:#264653,color:#fff,stroke:#1d3540 |
| 58 | style Low fill:#fff3cd,color:#000,stroke:#ffc107 |
| 59 | style High fill:#d4edda,color:#000,stroke:#28a745 |
| 60 | style Repair fill:#f4a261,color:#000,stroke:#e76f51 |
| 61 | style Crystal fill:#2d6a4f,color:#fff,stroke:#1b4332 |
| 62 | style Done fill:#1b4332,color:#fff,stroke:#0d2818 |
| 63 | style Loop fill:#a8dadc,color:#000,stroke:#457b9d |
| 64 | ``` |
| 65 | |
| 66 | > **Tip:** Click the expand button (↔) on the diagram to see the full interactive flow. |
| 67 | |
| 68 | Skills are scored after every execution. Low scores trigger automatic repair. High scores lead to crystallization — a locked, battle-tested version you can trust. Every step is logged for full auditability. |
| 69 | |
| 70 | **No external dependencies.** No SmythOS, no OpenTelemetry collector, no Docker. Pure Claude Code. |
| 71 | |
| 72 | ## What's Inside |
| 73 | |
| 74 | ### Skills (7) |
| 75 | |
| 76 | | Skill | Command | Purpose | |
| 77 | |-------|---------|---------| |
| 78 | | **using-singularity** | *(auto-loaded)* | Bootstrap context + capability gap detection | |
| 79 | | **creating-skills** | `/singularity-create` | Build new skills through a structured workflow | |
| 80 | | **scoring** | `/singularity-score` | Rate execution on a 5-dimension rubric (0-100) | |
| 81 | | **repairing** | |
People who liked this also viewed
6 picksType
- Raycast-PromptLabA Raycast extension for creating powerful, contextually-aware AI commands using placeholders, action scripts, selected files, and more.PromptsJan 2024
- ai-shortVideo-pipelineEnd-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.PromptsJun 2026
- Instructgpt-promptsInstruction-based prompts for generating and classifying text.PromptsNov 2025
- AI_Gen_Novel基于大语言模型(LLM)和多智能体(Multi-Agent)，探究AI写小说能力的边界PromptsSep 2024
- ANWS🚀 A spec-driven workflow framework for AI-assisted development. Empowers prompt engineers to build production-ready software through structured PRD → Architecture → Task decomposition. Designed for Antigravity to enforce design-first principles and prevent architectural drift in vibe coding.🗺️Antigravity-Workflow-SystemPromptsMay 2026
- AI_Find_Customer面向外贸与 B2B 场景的 AI 客户挖掘系统，基于 FastAPI、LangGraph 和 React，实现公司理解、关键词生成、网页搜索、线 索提取与联系方式发现AI-powered B2B lead hunting system built with FastAPI, LangGraph, and React for automated company research, keyword generation, web search, lead extraction, and contact discovery.PromptsJul 2026
