skills-x
CLAUDE.md18 starsChanged 7 months agoMITView on GitHub
Skills-X is a Go-based CLI tool for downloading and managing AI agent skills. It supports multiple AI IDEs (Claude Code, Cursor, Windsurf, CodeBuddy) and distributes skills via npm and Go install. This project uses a plan-first workflow (see .cursor/rules/development-workflow.mdc):
- Installs packages
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brainstormingSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- find-skillsSkill
- finishing-a-development-branchSkill
- golang-cli-cobra-viperSkill
- golang-testingSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- skill-creatorSkill
- skills-xSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-superpowersSkill
- verification-before-completionSkill
- writing-plansSkill
- writing-skillsSkill
- baidu-speech-to-textSkill
- feishu-notifySkill
- go-embedded-spaSkill
- go-i18nSkill
- go-pocketbase-integrationSkill
- minimal-ui-designSkill
- shadowrocket-claude-routingSkill
- skills-xSkill
- tui-designSkill
The file
We split this CLAUDE.md into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 47
Discussion Phase: When users提出需求, discuss the approach first
- Distinctive: line 48
Plan Confirmation: Wait for user to confirm the plan
- Distinctive: line 49
Execution Phase: Only start coding after explicit instructions like "开始开发" or "start development"
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Skills-X is a Go-based CLI tool for downloading and managing AI agent skills. It supports multiple AI IDEs (Claude Code, Cursor, Windsurf, CodeBuddy) and distributes skills via npm and Go install.
Common Commands
# Build the binary
make build
# Run tests
make test
# Run a single test
go test -v ./cmd/skills-x/command/initcmd/...
# Install to ~/.local/bin
make install-local
# Build cross-platform binaries for npm release
make build-npm
# Build all platforms to bin/
make build-allArchitecture
- CLI Framework: Uses Cobra (
github.com/spf13/cobra) - Commands:
list,init,tui(seecmd/skills-x/command/) - Core Packages:
pkg/registry/- Skill registry (registry.yaml)pkg/discover/- Skill discoverypkg/gitutil/- Git utilities for cloning skillspkg/versioncheck/- Version checking against GitHub releases
- Skills: Embedded in binary at
cmd/skills-x/skills/skills/viago:embed. Runmake sync-skillsbefore building to update embedded skills. - i18n: Translations in
cmd/skills-x/i18n/locales/(en.yaml, zh.yaml)
Development Workflow
This project uses a plan-first workflow (see .cursor/rules/development-workflow.mdc):
- Discussion Phase: When users提出需求, discuss the approach first
- Plan Confirmation: Wait for user to confirm the plan
- Execution Phase: Only start coding after explicit instructions like "开始开发" or "start development"
- Documentation: Save implementation plans to
docs/before coding
Key Files
cmd/skills-x/main.go- Entry point, registers commandscmd/skills-x/command/initcmd/init.go- Download/install skillscmd/skills-x/command/list/list.go- List available skillscmd/skills-x/tui/- Interactive TUI for skill managementpkg/registry/registry.yaml- Skill registry definition
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

