skl
AGENTS.md11 starsChanged 5 months agoMITView on GitHub
skl supports 40+ agent environments. It evaluates the local filesystem and environment variables to detect installed agents, routing and linking skills dynamically. We enforce strict feature parity (commands, flags, platforms) with the original TypeScript skills npm package. Antigravity maps to ~/.gemini/config (original IDE) and ~/.gemini/antigravity (2.0). IMPORTANT: ONLY WHEN EDITING README.md or human docs (eg --help) run /humanizer skill. skl detects agents via project folders (e.g., .cursor, .cline, .zed) or environment variables (XDGCONFIGHOME, APPDATA, etc.): Skills are mapped using relative…
Files
🤖 Agent Configurations & Discovery
skl supports 40+ agent environments. It evaluates the local filesystem and environment variables to detect installed agents, routing and linking skills dynamically.
We enforce strict feature parity (commands, flags, platforms) with the original TypeScript skills npm package. Antigravity maps to ~/.gemini/config (original IDE) and ~/.gemini/antigravity (2.0).
IMPORTANT: ONLY WHEN EDITING README.md or human docs (eg --help) run /humanizer skill.
⚡ Discovery Mechanics
skl detects agents via project folders (e.g., .cursor, .cline, .zed) or environment variables (XDG_CONFIG_HOME, APPDATA, etc.):
func detectInstalledAgents(home, configHome, cwd string) []AgentType {
var installed []AgentType
for agentType, config := range Agents {
if config.DetectInstalled != nil && config.DetectInstalled(home, configHome, cwd) {
installed = append(installed, agentType)
}
}
return installed
}🔗 Symlink Routing
Skills are mapped using relative symlinks to prevent duplication:
graph TD
A[Add Skill command] --> B{Installation Scope?}
B -->|Global: -g / --global| C1[Canonical Base: ~/.gemini/antigravity/skills]
B -->|Local: Project Default| C2[Canonical Base: .agents/skills]
C1 --> D1[Copy files to Canonical Global Dir]
C2 --> D2[Copy files to Canonical Project Dir]
D1 --> E1{Universal Agent?}
D2 --> E2{Universal Agent?}
E1 -->|Yes: antigravity| F1[No symlink needed]
E1 -->|No: claude-code| F2[Create relative symlink in home dir]
F2 --> G1[~/.claude/skills/my-skill -> ../.gemini/antigravity/skills/my-skill]
E2 -->|Yes: antigravity| H1[No symlink needed]
E2 -->|No: claude-code| H2[Create relative symlink in project dir]
H2 --> I1[.claude/skills/my-skill -> ../../.agents/skills/my-skill]🛠️ Multi-Platform Compilation & Path Mappings
To ensure that skl can be deployed across Linux, Windows, and macOS architectures, the CLI tool resolves home directories and environments dynamically at runtime:
- Linux: Crawls
$XDG_CONFIG_HOMEor falls back to standard UNIX directories (e.g.,~/.config/). - Windows: Dynamic resolution maps to
%APPDATA%or%USERPROFILE%targets depending on user credentials. - macOS: Resolves configuration folders directly using standard
~/.gemini/configand~/.gemini/antigravitystructures.
Multi-Platform CI Builds
Our GitHub Actions pipeline (ci.yml) is configured to compile and run tests natively on all three major platforms using a build matrix:
strategy:
matrix:
os: [ubuntu-latest, macos-latest, windows-latest]This guarantees that the codebase builds and passes all tests across Linux, macOS, and Windows.
The Local Compile Hack (macOS Gatekeeper & Code Signing)
While Go can easily cross-compile to macOS from a Linux runner, the resulting binary is unsigned. When distributed, macOS Gatekeeper stamps it with com.apple.quarantine and blocks execution, throwing a security warning. To bypass this restriction:
- Local Compilation: We compile the official production macOS releases locally on the developer's macOS machine (
go build -o skl-darwin-arm64andgo build -o skl-darwin-amd64). - Local Signing: Since the developer's local environment has access to the developer keychain and native signing tools (
codesign), the binary is signed natively on macOS. - Distribution: The signed binaries are then uploaded directly to release assets, bypassing standard runner constraints.
Windows Compilation and SmartScreen
For Windows platforms, compiling natively in CI or cross-compiling on macOS/Linux using GOOS=windows GOARCH=amd64 go build produces a functional skl-windows-amd64.exe binary. However, because this binary is unsigned, Windows SmartScreen will flag the executable.
- Distribution Guidelines: Standard users running the pre-compiled binary must unblock the file. Refer to README.md for step-by-step instructions on running unsigned Windows and macOS executables.
In this repository46 other files it gives its agents.
- .agents/skills/humanizer/AGENTS.mdAGENTS.md
- cli-to-go-migrationSkill
- golang-benchmarkSkill
- golang-cliSkill
- golang-code-styleSkill
- golang-concurrencySkill
- golang-contextSkill
- golang-continuous-integrationSkill
- golang-databaseSkill
- golang-data-structuresSkill
- golang-dependency-injectionSkill
- golang-dependency-managementSkill
- golang-design-patternsSkill
- golang-documentationSkill
- golang-error-handlingSkill
- golang-google-wireSkill
- golang-graphqlSkill
- golang-grpcSkill
- golang-how-toSkill
- golang-lintSkill
- golang-modernizeSkill
- golang-namingSkill
- golang-observabilitySkill
- golang-performanceSkill
- golang-popular-librariesSkill
- golang-project-layoutSkill
- golang-safetySkill
- golang-samber-doSkill
- golang-samber-hotSkill
- golang-samber-loSkill
- golang-samber-moSkill
- golang-samber-oopsSkill
- golang-samber-roSkill
- golang-samber-slogSkill
- golang-securitySkill
- golang-spf13-cobraSkill
- golang-spf13-viperSkill
- golang-stay-updatedSkill
- golang-stretchr-testifySkill
- golang-structs-interfacesSkill
- golang-swaggerSkill
- golang-testingSkill
- golang-troubleshootingSkill
- golang-uber-digSkill
- golang-uber-fxSkill
- humanizerSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

