Minimal example skill: greets the user and explains how Agent Skills are structured.
The smallest useful Agent Skill. It greets the user and can explain how a skill is structured. It needs no tools, no files and no network access.
skills install @spboucher/hello-skill --client claude-code
Then ask your agent: "Is the hello skill loaded?"
SKILL.md: frontmatter (name, description, license) and instructions.agent-registry.json: the registry manifest (identity, version, compatibility).Destination: ~/.claude/skills/hello-skill · project scope: .claude/skills/hello-skill
1Install with the Skills CLI (verifies the checksum, previews the destination, never runs scripts)
skills install @spboucher/hello-skill@1.0.0 --client claude-codeAdd --project to install into .claude/skills/hello-skill instead of ~/.claude/skills/hello-skill.
2Or manually: download the release archive
curl -fsSLo hello-skill-1.0.0.tar.gz https://skills.spboucher.ai/api/v1/artifacts/spboucher/hello-skill/versions/1.0.0/download3Verify the SHA-256 checksum
echo "8191b4125a53b1cc224bf6e4be6080707541b2a902e61c2a65fdf28dfc8de022 hello-skill-1.0.0.tar.gz" | shasum -a 256 -c -4Inspect the contents before extracting
tar -tzf hello-skill-1.0.0.tar.gz5Extract into ~/.claude/skills/hello-skill
mkdir -p ~/.claude/skills/hello-skill && tar -xzf hello-skill-1.0.0.tar.gz -C ~/.claude/skills/hello-skillInstalling only copies or configures. Nothing is executed for you. The Skills CLI verifies the checksum before writing files.
Select a file to preview it. Files are shown as plain text and never executed.
The publisher declared no permissions. This is a claim, not a guarantee.
No advisory findings from static-1.0.0 on Nov 10, 2026. 1 informational note.
Static checks are advisory. They never certify that a package is safe. Compatibility entries are publisher claims unless marked verified.
| Version | Published | Size | SHA-256 | State |
|---|---|---|---|---|
| 1.0.0latest | Nov 10, 2026 | 1.7 kB | 8191b4125a53… | published |
Drive Safari on macOS with AppleScript: reliable page waits, reading, forms, uploads, downloads with the page's session, screenshots. Works in a dedicated window with domain policy and sensitive-field guards.
Write, review, debug and migrate OpenAI API code with model tables and a request linter built from live probes of 29 models. Covers Responses, Chat Completions, tools, costs and tested scaffolds.
Write, review, debug and migrate Claude API code with model tables and a request linter built from live API probes of 15 models. Includes cost estimates and tested agent scaffolds.