Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Skill Creator

ASecurity

Guide for creating and validating agent skills. Use when authoring or updating a SKILL.md, writing frontmatter, structuring scripts/references/assets, or checking a skill before deployment. Triggers on create skill, write skill, skill frontmatter, validate skill, fix skill YAML. For installing a finished skill, use skill-deployer instead.

10 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentspythonrustgobash

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add fritzprix/libr-agent --skill skill-creator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Creator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Skill Creator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fritzprix-skill-creator/badge)](https://www.skillsdirectory.com/skills/fritzprix-skill-creator)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: skill-creator
description: Guide for creating and validating agent skills. Use when authoring or updating a SKILL.md, writing frontmatter, structuring scripts/references/assets, or checking a skill before deployment. Triggers on create skill, write skill, skill frontmatter, validate skill, fix skill YAML. For installing a finished skill, use skill-deployer instead.
---

# Skill Creator

Guidance for building lean, effective agent skills and validating them before deployment.

> **Deployment** (scope, target paths, verification in `<available_skills>`) is handled by **skill-deployer**. Finish creation and validation here first.

## Quick Process

1. **Understand** — gather concrete usage examples (see [creation-process.md](references/creation-process.md) Step 1)
2. **Plan** — identify scripts, references, and assets to bundle
3. **Implement** — write SKILL.md and bundled resources
4. **Validate** — `python scripts/validate_skill.py <skill-folder>` (see [validation.md](references/validation.md))
5. **Deploy** — hand off to **skill-deployer** when the skill should become available to agents
6. **Iterate** — refine after real usage, re-validate after edits

## Validation (required before deploy)

```bash
python scripts/validate_skill.py <path/to/skill-folder>
python scripts/validate_skill.py <path/to/skill-folder> --strict   # before deployment
```

Checks frontmatter (same rules as the Rust scanner) and warns about common path mistakes. Full checklist: [validation.md](references/validation.md).

## Core Rules

- **Concise body**: SKILL.md under ~150 lines; move detail to `references/`
- **Triggers in frontmatter**: all "when to use" guidance goes in `description`, not the body
- **Name matches folder**: `name:` in frontmatter must equal the directory name
- **Safe YAML**: use double quotes in `description` when text contains apostrophes (`"Telegram's"`, not `'Telegram\'s'`)
- **No duplicate reads**: information lives in SKILL.md *or* references, not both
- **Imperative voice** in body instructions
- **No auxiliary docs**: no README, CHANGELOG, or INSTALLATION_GUIDE in the skill folder

## Structure

See [anatomy.md](references/anatomy.md) for directory layout (`SKILL.md`, `scripts/`, `references/`, `assets/`).

## Design Guidance

- [design-principles.md](references/design-principles.md) — concision, degrees of freedom, progressive disclosure
- [creation-process.md](references/creation-process.md) — full walkthrough
- [validation.md](references/validation.md) — validate_skill.py usage and rules
- [workflows.md](references/workflows.md) — sequential and conditional workflow patterns
- [output-patterns.md](references/output-patterns.md) — template and example patterns

## Frontmatter Checklist

```yaml
---
name: skill-name
description: "What it does + specific triggers/contexts for when to use it."
---
```

Only `name` and `description` are required. The description is the primary trigger mechanism.

Attribution

fritzprixfritzprix
View sourceMore from fritzprix →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →