Sample Skill Advanced
Demonstrate progressive disclosure with references, scripts, and assets for creating a new skill. Use when you need a structured example of how to split instructions and supporting files.
Install
$ agentstack add skill-lc-rezende-ai-custom-skills-sample-skill-advanced ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
When to use this skill
Use this skill to see a complete example of a skill that keeps core instructions in SKILL.md and loads additional context only when needed.
Core workflow
- Read this file to understand the minimal, always-loaded guidance.
- If you need detailed rules or a checklist, read
references/REFERENCE.md. - If you need a template for output formatting, open
assets/skill-template.md. - If you need to validate a skill folder, run
scripts/validate-skill.sh.
Output expectations
- The skill uses progressive disclosure correctly.
- Optional folders are used only when their content is needed.
- References are relative to the skill root and one level deep.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: lc-rezende
- Source: lc-rezende/AI-Custom-Skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.