# #skill — MDRSS hashtag feed

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

## Cards (7)

### [mattpocock/skills / skills/engineering/ask-matt/SKILL.md — The router skill: maps every user-reachable skill and how they relate, so an agen](https://mdrss.com/software-craft/developer-tooling/901529/901529.md)

The router skill: maps every user-reachable skill and how they relate, so an agent can pick the right one instead of guessing. Kept in sync whenever a skill is added, renamed or removed, on the principle that a router which lies is worse than none.

Classification: software-craft/developer-tooling · Feed: software-craft · Updated: 2026-08-07T09:26:33.000Z · Version: 1

### [reverse-skill / skills/SKILL.md — Master controller and entry point for the skills tree](https://mdrss.com/security/forensics-and-reverse-engineering/901514/901514.md)

Master controller and entry point for the skills tree. YAML frontmatter declares the routing scope; the body defines the routing execution contract, RFC-2119 instruction levels, the unified entry, the next-step menu pattern, the precedent library and auto-evolution.

Classification: security/forensics-and-reverse-engineering · Feed: security · Updated: 2026-08-05T14:43:21.008Z · Version: 1

### [Recsys Pipeline Architect](https://mdrss.com/llm-engineering/mlops-and-ml-systems/901385/901385.md)

A spec-and-scaffold skill for building composable recommendation, ranking, and feed pipelines. Encodes the six-stage pattern popularized by xAI's open-sourced For You algorithm (Apache 2.0) and applies it to any "top K for (user, context)" problem. 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

### [Trace To Training Data](https://mdrss.com/llm-engineering/training-and-fine-tuning/901376/901376.md)

This skill assumes eval-harness-first already graded the traces being converted here — goldens, graders, and runs//results.json all exist before conversion starts. This is the flywheel edge that skill names in its own flow: "the same labeled traces become the training set." C. 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-Tuning Method Selection](https://mdrss.com/llm-engineering/training-and-fine-tuning/901366/901366.md)

This is the router skill for the fine-tuning lifecycle: it decides whether fine-tuning is the right tool at all, and if so, which method and which base-model size class. Every other skill in this plugin assumes this routing already happened — start here before opening lora-qlora. 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

### [HADS Claude](https://mdrss.com/growth/marketing-seo-and-growth/901291/901291.md)

This skill teaches Claude how to read, generate, and validate HADS documents. Read all  SPEC  blocks before responding to any HADS-related request. Read  NOTE  blocks if you need context on intent or edge cases. 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

### [Skill Creator](https://mdrss.com/data-research/research-and-evaluation/901167/901167.md)

A skill for creating new skills and iteratively improving them. Use it to make implementation decisions and avoid common dead ends.

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