Full Skill Agents
Open-standard skill at the vendor-agnostic `.agents/skills/<name>/SKILL.md` path. Discovered by the `agent-skills` Provider, which any vendor (Anthropic, OpenAI, Google) can adopt without skill-map needing a vendor-specific copy.
Install
$ agentstack add skill-crystian-skill-map-full-skill-agents ✓ 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
Full open-standard skill
Demonstrator skill for the neutral .agents/skills/ convention. The schema mirrors Anthropic's, only name + description are required; everything else flows through via additionalProperties: true. Pairs with #full-skill-claude for cross-vendor comparison.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: crystian
- Source: crystian/skill-map
- License: MIT
- Homepage: http://skill-map.dev/
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.