PeterHdd Agent Skills
Nine engineering skills with decision rules and runnable scripts.
About
A collection of 9 engineering skills for Claude Code and Codex covering frontend, backend architecture, system design, DevOps, mobile, ML, rapid prototyping, and security. Each skill pairs a SKILL.md of when-X-do-Y decision rules with reference material and runnable Python/Bash scripts.
Honest limitations: a small single-maintainer repo with 11 stars, so the patterns reflect one person's production experience rather than broad consensus. The scripts need Python 3.8+ and Bash, and the depth is shallower than the mega-collections.
What it can do
- Frontend/backend/mobile engineering patterns
- System design with capacity formulas
- DevOps and security review rules
- Runnable reference scripts
Setup
- Run npx skills add PeterHdd/agent-skills --all (or --skill <name> for one).
- Restart Claude Code or Codex so the skills load.
- Ask for the work; Claude applies the skill's decision rules automatically.
Prerequisites
Claude Code or Codex CLI, the skills CLI (npx skills), Python 3.8+ and Bash for the scripts.
Use cases
Works with
Trust score — 6/10
Scored 6/10 (metrics tier, metrics-v1). Evidence: 11 stars, 11 commits; single-maintainer repo; 9 engineering skills with decision rules, reference material, and runnable scripts; Requirements (Claude Code or Codex CLI) verified in README. License: MIT.
★ 11 GitHub stars
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 4.0/10
- Maintenance · recency, releases, issue load
- 4.0/10
- Openness · license + docs
- 9.0/10
- Manual review · sanity read + red-flag check
- 6.0/10
- · 11 stars, 11 commits; single-maintainer repo
- · 9 engineering skills with decision rules, reference material, and runnable scripts
- · Requirements (Claude Code or Codex CLI) verified in README
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.