← Browse

@tody-agent/cm-example

B

A template demonstrating the universal format compatible with Antigravity, Claude, Cursor, and OpenClaw.

skillclaude

Install

agr install @tody-agent/cm-example --target claude

Writes 1 file into .claude/skills/, pinned to git-2e05fcdf.

  • .claude/skills/cm-example/SKILL.md

Document


name: cm-example description: A template demonstrating the universal format compatible with Antigravity, Claude, Cursor, and OpenClaw. version: 1.0.0 platforms:

  • all

Universal Skill Example

This skill demonstrates the unified format that omni-agent will compile into platform-specific configurations.

The Instructions

When the user asks for "universal hello world", output a greeting in 3 different languages.

Sub-agent Instructions

[!NOTE] Used by platforms that support recursive agents (like Antigravity / OpenFang).

  1. Subagent A: Translate into French.
  2. Subagent B: Translate into Spanish.
  3. Subagent C: Translate into Japanese.

Context Injection

Inject these variables into the prompt context when compiling: {{ workspace_root }} {{ current_branch }}

Trustgrade B

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • warnLicenseno SPDX license detected

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-2e05fcdf85ad2026-07-31