---
title: "erKam (@erkamyaman) skills · skilld"
canonical_url: "https://skilld.dev/gh/erkamyaman"
meta:
  description: "9 agent skills written by erKam on skilld."
  "og:description": "9 agent skills written by erKam."
  "og:title": "erKam on skilld"
---

`

![Avatar for erKam](https://skilld.dev/_img/avatar?url=https%3A%2F%2Fgithub.com%2Ferkamyaman.png)

# **erKam**

[@erkamyaman](https://github.com/erkamyaman)person

kæm · Döner kebab in developer form 🌯

9 skills 1 Istanbul 🇹🇷

[GitHub](https://github.com/erkamyaman) [Website](https://erkamyaman.dev)

## Skills

### [erkamyaman/dhh-p-bloom-agent-skills](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills)

DHH's Rails World 2026 opening keynote, turned into agent skills for working with AI coding agents

9 skills 1

`npx skilld add erkamyaman/dhh-p-bloom-agent-skills`

- [

  **/agent-evals**1

  Use when measuring how well an AI agent handles a recurring kind of task. Builds a small eval set, runs it, and raises the difficulty once the agent passes. /agent-evals by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/agent-evals)
- [

  **/agent-security-basics**1

  Use when letting AI agents run code, install packages or touch real systems. Covers sandboxing, least privilege and quarantine basics. /agent-security-basics by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/agent-security-basics)
- [

  **/architecture-for-agents**1

  Use when structuring a codebase that AI agents will edit heavily. Weighs duplication against abstraction now that repeating code and keeping copies in sync is cheap. /architecture-for-agents by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/architecture-for-agents)
- [

  **/async-delegation**1

  Use when you have several independent jobs for AI agents. Splits work into parallel tasks, hands them off like to coworkers, and reviews results in batches. /async-delegation by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/async-delegation)
- [

  **/black-box-review**1

  Use when reviewing code an AI agent wrote, especially in a language or area you don't know well. Judges the result through tests and behaviour instead of reading every line. /black-box-review by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/black-box-review)
- [

  **/cli-for-your-app**1

  Use when making an app or library usable by a person's own AI agent. Designs a command-line interface so agents can drive the app without a built-in chatbot. /cli-for-your-app by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/cli-for-your-app)
- [

  **/native-vs-web**1

  Use when deciding whether an app should be native, web, or hybrid (Ionic/Capacitor) now that agents make native code cheaper to produce. /native-vs-web by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/native-vs-web)
- [

  **/outcome-prompting**1

  Use when giving an AI coding agent a job. Turns a task into a problem-and-outcome brief with acceptance checks, instead of step-by-step instructions. /outcome-prompting by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/outcome-prompting)
- [

  **/overnight-optimization**1

  Use when you want an AI agent to improve performance, size or startup time of a project over a long unattended run, with tests as a safety gate. /overnight-optimization by erkamyaman](https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/overnight-optimization)

Curated skills from @erkamyaman. Checked GitHub just now