Commonly Used High-Value Skills
293 skills in 16 categories for Codex, Claude Code and Cursor with an npx installer, provenance and license checks
- 74 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The set includes skills with scripts, and some of them run code and use the network
- Skills also come from external sources, so their content should be reviewed before installation
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/commonly-used-high-value-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The set includes skills with scripts, and some of them run code and use the network
- Skills also come from external sources, so their content should be reviewed before installation
This is third-party code. Review the repository files before installing.
What it does
The repository gathers skills around real work scenarios: engineering, DevOps, product and design, operations, office automation, AI platforms and security. It currently holds 293 skills in 16 categories. Each skill is a `SKILL.md` and often `scripts/`, `references/` and `assets/`, so it can be used at once. One source set fits Codex, Claude Code, Cursor, Hermes Agent and OpenClaw. The installer runs from GitHub with `npx github:seaworld008/Commonly-used-high-value-skills install`. By default it writes to `.agents/skills` of the current project, and flags choose the target (`--target codex,claude`), categories (`--category developer-engineering`), individual skills (`--skill docx,xlsx,pdf,pptx`) and a custom directory with `--dir`. `--dry-run` shows what would be written without changing anything. Every skill has a provenance record, and skills from external repositories pass a license audit. CI and Code Scanning checks run before release, and a `dead-links` job checks links monthly. The set includes security audit skills such as `skill-security-auditor` and `input-guard` that help assess external skills before installing them.
Who it is for. People who build a skill library for Codex or Claude Code and want ready skills by category in place of searching dozens of repositories.
Good fit when
- A team needs a set of engineering and DevOps skills installed with one command into `.agents/skills`
- You need only document skills such as `docx`, `xlsx`, `pdf` and `pptx`
- Before installing you want to see which directories and skills would be written with no changes on disk
- The set must be pinned to a release so the team reproduces one state
Not a fit when
- You need one narrow skill: the whole collection holds over two hundred skills and extras take up context
- You work without Node.js: the installer runs through `npx`
- OpenClaw reads only a flat directory: use `openclaw-skills/` for it, as the repository root does not work
Example request
Show which skills from the developer-engineering and security-and-reliability categories would be written, with no changes on diskLimitations
The collection is wide, and installing all 293 skills would bloat the description list in the agent context, so the author advises choosing categories or individual skills. Skills are assembled and partly taken from external sources: their licenses and sources are recorded in the repository and audited, but the decision to use them stays with you. OpenClaw needs the flat `openclaw-skills/` directory, not the root or `skills/`. The installer needs Node.js, and the README is in Chinese with an English version in `README.en.md`.
How to disable. Delete the installed skill folders from `.agents/skills/`, `~/.codex/skills` or `~/.claude/skills`. The installer installs only skill files and has no background process.
FAQ
How do I install only what I need?
With installer flags: `--category` picks categories and `--skill docx,xlsx,pdf,pptx` picks individual skills, and they can be combined. Check the plan with `--dry-run` before writing.
Where do skills go?
By default into `.agents/skills` of the current project. With `--target codex,claude` they go to the user directories `~/.codex/skills` and `~/.claude/skills`, and `--target custom --dir` sets your own.
Which agents are supported?
Codex, Claude Code, Cursor, Antigravity, Hermes Agent and OpenClaw. For OpenClaw use the flat `openclaw-skills/` directory.
Where do the skills come from?
Each has a provenance record, external skills pass a license audit and a source policy with allow and block lists lives in the repository.
How do I pin a version?
The installer accepts pinning to a release so the team gets the same state of the set. Versions are listed on the repository releases page.
Discussion
No questions or reviews yet.
Related
Skillscafe3310's personal skill collection: spec-driven project work, reviews, reports, browser, 3D and video in one repository
A desktop app and skm CLI: one copy of each skill in a central hub, symlinked into every AI tool
Seven skills for research, HTML explainers and source citation, installable all at once or one at a time through npx.
Claude Skills (Alireza Rezvani)
Claude Code Skills & Plugins
A large library of skills, agents and commands by domain: engineering, marketing, product, compliance, C-level advisors and research
A set of 13 SKILL.md skills: research, a product doc, decks, articles and audits for any compatible agent
A collection of 26 agent skills: idea scoring, GEO audits, design systems, AI-text cleanup and plugin evaluation
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Commonly Used High-Value Skills (this card) | no | 74 | |
| Claude Code Skills Collection | no | 248 | 145 plugin skills for Claude Code and Codex on Cloudflare, React and other topics |
| Awesome Agent Skills (libukai) | no | 5,218 | a skills guide with a selection |
README in short
The README presents the repository as a skill set organized around real work scenarios, describes 16 categories and 293 skills and explains which directory suits each agent. Installation through npx with flag examples, manual installation and contribution rules follow.