Skip to content
Back to skills

Agentskills

ASecurity

Agent Skills portable format router. Use when creating cross-client skills, validating portable frontmatter, packaging skills for upload or API use, or implementing skill discovery and activation.

  • 67 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 12, 2026
documentationapisecurity

Works with

  • claude code
  • cli
  • api

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 29, 2026

npx -y skills add Jamie-BitFlight/claude_skills --skill agentskills --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agentskills?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agentskills
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jamie-bitflight-agentskills/badge)](https://www.skillsdirectory.com/skills/jamie-bitflight-agentskills)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agentskills
description: Agent Skills portable format router. Use when creating cross-client skills, validating portable frontmatter, packaging skills for upload or API use, or implementing skill discovery and activation.
user-invocable: true
---

# Agent Skills Portable Format

Use this skill for the portable Agent Skills boundary. Use
`plugin-creator:claude-skills-overview-2026` instead for Claude Code runtime extensions such as
hooks, context forks, model selection, and invocation controls.

Load the reference that matches the current branch:

- **Schema or validation**: Read [specification.md](./references/specification.md) for the portable
  directory shape, frontmatter fields, name rules, resources, and `skills-ref` behavior.
- **Authoring**: Read [best-practices.md](./references/best-practices.md) for description design,
  workflow structure, scripts, references, assets, and evaluation guidance.
- **Client implementation**: Read [integration.md](./references/integration.md) for discovery,
  metadata loading, activation, security boundaries, and reference-library usage.

Portable upload and package boundaries accept `name`, `description`, `license`, `compatibility`,
`metadata`, and experimental `allowed-tools`. Host extensions are outside this schema and may be
rejected rather than ignored.

Primary sources: [Agent Skills specification](https://agentskills.io/specification) and
[live client showcase](https://agentskills.io) (accessed 2026-09-24).

Files in this skill

  • SKILL.md11.3 KB
  • references/best-practices.md16.6 KB
  • references/integration.md8.5 KB
  • references/specification.md9 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…