@afx-team/your-skill-name
AA clear description of what this skill does and when to use it. Include specific keywords that users would naturally say. Use when [specific scenarios].
Install
agr install @afx-team/your-skill-name --target claudeWrites 5 files into .claude/skills/, pinned to git-58d61605.
- .claude/skills/your-skill-name/.gitignore
- .claude/skills/your-skill-name/LICENSE
- .claude/skills/your-skill-name/README.md
- .claude/skills/your-skill-name/SKILL.md
- .claude/skills/your-skill-name/package.json
Document
name: your-skill-name description: A clear description of what this skill does and when to use it. Include specific keywords that users would naturally say. Use when [specific scenarios]. allowed-tools: Read, Bash
Your Skill Name
A brief description of what this skill does and how it helps users.
Instructions
When the user [describes the scenario when this skill should be used]:
-
First Step: [What Claude should do first]
- [Additional details or substeps]
- [Use bash, read files, etc.]
-
Second Step: [What Claude should do next]
- [How to process or analyze information]
- [What to look for]
-
Final Step: [How to complete the task]
- [What output to provide]
- [How to format the response]
Examples
Example 1: [Scenario Name]
User asks: "[Example user question]"
What the skill does:
- [First action]
- [Second action]
- [Result]
Expected output:
[Show example output]
Example 2: [Another Scenario]
User asks: "[Another example question]"
What the skill does:
- [Actions...]
- [More actions...]
Best Practices
- [Best practice 1]
- [Best practice 2]
- [Best practice 3]
Common Patterns
Pattern 1: [Pattern Name]
[Describe when to use this pattern]
[Example code or template]
Limitations
- [Limitation 1]
- [Limitation 2]
- [What to do instead]
Configuration
You can customize this skill by editing scripts/config.json after installation.
Available options:
option1: [Description]option2: [Description]
Additional Resources
For more detailed information:
- See reference.md for complete API documentation
- See examples.md for more usage examples
Trustgrade A
- 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.
- passLicense
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-58d6160583ba2026-07-31