#292292nd of 324 in Skills, plugins and prompts
skills
Library of agent skills for spec-driven, verifiable autonomous coding loops
- Stars
- 1.4k
- License
- MIT
- Last commit
- Nov 2026
- Language
- HTML
117 on 3 Jul 20261,393 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A collection of SKILL.md folders for coding agents, covering exploring unknowns, writing specs, implementing them in slices, reviewing, and visual checks. Install with `npx skills add dzhng/skills` or copy a skill folder into `.claude/skills/`. It targets Claude Code, Codex, opencode, Cursor and other harnesses that support skills.
Who it is for: Developers running Claude Code or Codex on long, spec-driven builds
Strengths
- Skills are standalone; each can be installed or copied alone via `--list` or `--only`
- Covers the whole loop: explore-unknowns, write-spec, implement-spec, review, close-spec
- Visual review skills compare screenshots against a baseline, with a diff script included
- Works with any harness that reads skills; MIT licensed
Weaknesses
- Author's personal library; workflow assumes his spec and choices.md conventions
- Full loop relies on a harness `/goal` mode, as in Claude Code or Codex
- Long unattended runs of days; the only evidence is one 3d 18m run
- Some skills are niche, such as WebGPU renderer rules and Xiaohei illustrations
What it needs
- no GPU
- Needs Node.js/npx, A skills-capable agent harness (Claude Code, Codex, opencode, Cursor)
Quick answers
Is skills open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |