Install
$ agentstack add skill-podcast72-agent-skill-starter-kit-basic-skill ✓ 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Basic Local Skill
What this skill does
Use this skill when you want the smallest reusable local skill with clear instructions, clear limits, and a short final report.
Activation
Activate this skill for small local tasks that do not need helper scripts.
Scope
- Local work only.
- Small and clear tasks.
- No network access by default.
- No global configuration changes.
Rules
- Read the request carefully before changing files.
- Keep changes small and explain what changed.
- Do not use destructive commands by default.
- Do not use
sudoor global installs. - Report limits and missing verification clearly.
Stop rules
- Stop if the request requires network access, secrets, or global changes.
- Stop if the task scope is unclear.
- Stop if the requested action becomes destructive.
Final Report Format
MODE:
TASK:
FILES CHANGED:
VALIDATION:
LIMITS:
STATUS:
No scripts are required for this example.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Podcast72
- Source: Podcast72/agent-skill-starter-kit
- License: MIT
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.