damson

Hard Won Skills — Development skill for Claude Code

Development community

Hard-won habits for Claude Code — themed plugins of battle-earned skills, each extracted from a real session where not having it cost something.

How to install Hard Won Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open damson/hard-won-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Hard Won Skills does

Hard-won habits for Claude Code — themed plugins of battle-earned skills, each extracted from a real session where not having it cost something.

Alternatives in Development

Codexbar — Show usage stats for OpenAI Codex and Claude Code, without having to login 8.8k ★
Prompt Sensei — Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analy 107 ★
Fire Cost — Track context usage, estimate session costs, and trigger strategic compaction 77 ★

README

hard-won-skills

![Terminal-styled banner: a claude session announcing the hard-won-skills marketplace, over the tagline "Hard-won habits for Claude Code"](docs/assets/social-preview.png)

*Hard-won habits for [Claude Code](https://claude.com/claude-code), packaged so you don't have to win them the hard way too.*

[![CI](https://github.com/damson/hard-won-skills/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/damson/hard-won-skills/actions/workflows/ci.yml) [![Release](https://img.shields.io/github/v/release/damson/hard-won-skills?label=release&color=blue)](https://github.com/damson/hard-won-skills/releases/latest) [![License: MIT](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE) [![Coverage](https://codecov.io/gh/damson/hard-won-skills/graph/badge.svg)](https://codecov.io/gh/damson/hard-won-skills) [![Made for Claude Code](https://img.shields.io/badge/made%20for-Claude%20Code-d97757.svg)](https://claude.com/claude-code)

👋 **Welcome!** This is a marketplace of **31 skills in 5 themed plugins**: small, careful procedures your agent picks up automatically when a task calls for them: rebasing a stack of PRs without losing one, proving a screenshot test actually compared pixels, probing a migration without leaving a trace.

What holds them together is where they came from. **Every skill here was extracted from a real session where not having it cost something**: a check that could never fail, a release that could not tag itself, forty-seven stale branches nobody could see. The measured facts stayed in the text, and so did the scars: each skill knows not just what to do, but when to stop and ask.

**Jump to:** [Quick start](#-quick-start) · [Pick your themes](#-pick-your-themes) ([git-workflow](#git-workflow) · [agent-config](#agent-config) · [verification](#verification) · [data-safety](#data-safety) · [mobile-ui](#mobile-ui)) · [What a skill looks like](#-what-a-skill-here-looks-like) · [Contributing](#-contributing) · [Releases](#-