# #phase — MDRSS hashtag feed

> Public MDRSS cards tagged #phase.
> Canonical feed: https://mdrss.com/feeds/phase

## Cards (30)

### [TDD Cycle Orchestrator](https://mdrss.com/software-craft/testing-and-documentation/901453/901453.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: software-craft/testing-and-documentation · Feed: software-craft · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Security Hardening Orchestrator](https://mdrss.com/security/application-security-and-threat-modeling/901422/901422.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/application-security-and-threat-modeling · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Reverse engineer](https://mdrss.com/security/forensics-and-reverse-engineering/901415/901415.md)

You are an elite reverse engineer with deep expertise in software analysis, binary reverse engineering, and security research. You operate strictly within authorized contexts: security research, CTF competitions, authorized penetration testing, malware defense, and educational pu. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/forensics-and-reverse-engineering · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Malware analyst](https://mdrss.com/security/forensics-and-reverse-engineering/901414/901414.md)

You are an elite malware analyst focused on defensive security research. Your purpose is to help security professionals understand malicious software to protect systems and respond to incidents. You operate strictly within defensive and educational contexts. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/forensics-and-reverse-engineering · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Firmware analyst](https://mdrss.com/security/forensics-and-reverse-engineering/901413/901413.md)

You are an elite firmware analyst with deep expertise in embedded systems security, IoT device analysis, and hardware reverse engineering. You operate within authorized contexts: security research, penetration testing with authorization, CTF competitions, and educational purposes. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/forensics-and-reverse-engineering · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Multi-Platform Feature Development Orchestrator](https://mdrss.com/web-mobile/accessibility-and-mobile-ux/901387/901387.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: web-mobile/accessibility-and-mobile-ux · Feed: web-mobile · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Machine Learning Pipeline - Multi-Agent MLOps Orchestration](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901383/901383.md)

This workflow orchestrates multiple specialized agents to build a production-ready ML pipeline following modern MLOps best practices. The approach emphasizes:. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/mlops-and-ml-systems · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Eval Harness First](https://mdrss.com/llm-engineering/training-and-fine-tuning/901363/901363.md)

The Phase 0 gate for the whole plugin: finetuning-method-selection and every downstream skill assume this harness exists before a training config gets written. The harness is not a run-end side artifact — it is the data-curation engine. The same labeled traces that build the go. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Fine-tune for: $ARGUMENTS](https://mdrss.com/llm-engineering/training-and-fine-tuning/901357/901357.md)

This command orchestrates the eval-gated fine-tuning lifecycle across seven phases, each owned by a specialist agent and gated by the artifact the prior phase produced:. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning training engineer](https://mdrss.com/llm-engineering/training-and-fine-tuning/901356/901356.md)

You are the fine-tuning training engineer: the workhorse who takes a training-brief.md someone else already justified and turns it into a dataset, a running job, and an exported artifact. You don't re- litigate method or model choice, and you don't decide whether a checkpoint s. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning eval engineer](https://mdrss.com/llm-engineering/training-and-fine-tuning/901355/901355.md)

You are the fine-tuning eval engineer: the independent gatekeeper who builds the measuring stick before anyone trains against it, and reads that same measuring stick to decide whether a trained checkpoint ships. You own the two phases that bound the lifecycle — Phase 0 before a t. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Intelligent Issue Resolution Orchestrator](https://mdrss.com/security/forensics-and-reverse-engineering/901321/901321.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/forensics-and-reverse-engineering · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Incident Response Orchestrator](https://mdrss.com/security/forensics-and-reverse-engineering/901320/901320.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/forensics-and-reverse-engineering · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Git Workflow Orchestrator](https://mdrss.com/ai-agents/agent-design-and-orchestration/901315/901315.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: ai-agents/agent-design-and-orchestration · Feed: ai-agents · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Full-Stack Feature Orchestrator](https://mdrss.com/software-craft/api-backend-and-databases/901312/901312.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: software-craft/api-backend-and-databases · Feed: software-craft · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Dependency Upgrade](https://mdrss.com/web-mobile/web-design-systems/901301/901301.md)

Master major dependency version upgrades, compatibility analysis, staged upgrade strategies, and comprehensive testing approaches. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: web-mobile/web-design-systems · Feed: web-mobile · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Legacy Code Modernization Workflow](https://mdrss.com/ai-agents/agent-design-and-orchestration/901299/901299.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: ai-agents/agent-design-and-orchestration · Feed: ai-agents · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Debugging Strategies](https://mdrss.com/software-craft/testing-and-documentation/901274/901274.md)

Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: software-craft/testing-and-documentation · Feed: software-craft · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Code Review Excellence](https://mdrss.com/software-craft/testing-and-documentation/901273/901273.md)

Transform code reviews from gatekeeping to knowledge sharing through constructive feedback, systematic analysis, and collaborative improvement. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: software-craft/testing-and-documentation · Feed: software-craft · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Data-Driven Feature Development Orchestrator](https://mdrss.com/data-research/research-and-evaluation/901259/901259.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: data-research/research-and-evaluation · Feed: data-research · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Comprehensive Code Review Orchestrator](https://mdrss.com/software-craft/testing-and-documentation/901239/901239.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: software-craft/testing-and-documentation · Feed: software-craft · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [C4 Architecture Documentation Workflow](https://mdrss.com/software-craft/architecture-and-distributed-systems/901223/901223.md)

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: software-craft/architecture-and-distributed-systems · Feed: software-craft · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Brand Discovery Interview Framework](https://mdrss.com/growth/marketing-seo-and-growth/901217/901217.md)

1. "What's your project called?" - Extract exact spelling, capitalization, and any tagline they mention. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: growth/marketing-seo-and-growth · Feed: growth · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Brand Landing Page Designer](https://mdrss.com/growth/marketing-seo-and-growth/901216/901216.md)

You are a design consultant embedded in a developer's workflow. Your user has built a product, side project, or service and needs a landing page -- but hasn't thought much about brand identity, visual direction, or how to communicate their product to non-technical visitors. You g. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: growth/marketing-seo-and-growth · Feed: growth · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Feature Development Orchestrator](https://mdrss.com/software-craft/api-backend-and-databases/901198/901198.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: software-craft/api-backend-and-databases · Feed: software-craft · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Performance Optimization Orchestrator](https://mdrss.com/platforms/observability-and-sre/901195/901195.md)

You MUST follow these rules exactly. Violating any of them is a failure. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: platforms/observability-and-sre · Feed: platforms · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Agent Performance Optimization Workflow](https://mdrss.com/ai-agents/agent-design-and-orchestration/901185/901185.md)

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: ai-agents/agent-design-and-orchestration · Feed: ai-agents · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [MCP Server Development Guide](https://mdrss.com/ai-agents/mcp-tooling-and-context/901158/901158.md)

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks. Use it to make implementation decisions and avoid common dead ends.

Classification: ai-agents/mcp-tooling-and-context · Feed: ai-agents · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [180-Day Free Roadmap to Become a Job-Ready Data Analyst](https://mdrss.com/learning/courses-roadmaps-and-reference/901117/901117.md)

This roadmap is designed for aspirants with zero experience , focusing on free learning paths , projects , interview prep , and tools that are widely accepted in the industry. Use it as a repeatable review, validation or hardening pass.

Classification: learning/courses-roadmaps-and-reference · Feed: learning · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Preface](https://mdrss.com/crypto/smart-contract-and-protocol-security/901053/901053.md)

Software for the SPDZ, MASCOT, and Overdrive secure multi-party computation protocols. See Programs/Source/ for some example MPC programs, and tutorial.md for a basic tutorial. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: crypto/smart-contract-and-protocol-security · Feed: crypto · Updated: 2026-08-04T13:54:51.641Z · Version: 1