# Evaluating Skills

> Evaluates and creates agent skills following best practices. Use when reviewing, writing, or refactoring skills, or asking about skill structure, format, or specification.

- **Type:** Skill
- **Install:** `agentstack add skill-altertable-ai-skills-evaluating-skills`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [altertable-ai](https://agentstack.voostack.com/s/altertable-ai)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [altertable-ai](https://github.com/altertable-ai)
- **Source:** https://github.com/altertable-ai/skills/tree/main/skills/evaluating-skills
- **Website:**  https://altertable.ai

## Install

```sh
agentstack add skill-altertable-ai-skills-evaluating-skills
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Evaluating & Creating Skills

## Quick Start

1. **Validating**: Run `skills validate ` for structural checks
2. **Scoring**: Run `python scripts/score-skills.py ` for spec-grounded LLM evaluation

## When to Use This Skill

- User wants to create a new skill
- User asks to review or evaluate an existing skill
- User needs help with skill format or structure
- User asks about skill best practices
- User wants to refactor or improve a skill
- Keywords: "skill", "SKILL.md", "create skill", "evaluate skill", "skill quality"

## Authoritative References

The scorer grounds evaluation against these live documents (with vendored snapshot fallback):
- [Specification](https://agentskills.io/specification.md) - Field constraints, structure rules
- [Best Practices](https://agentskills.io/skill-creation/best-practices.md) - Quality criteria
- [Evaluating Skills](https://agentskills.io/skill-creation/evaluating-skills.md) - Evaluation methodology

## Skill Anatomy

```
skill-name/                    # Gerund form (verb-ing)
├── SKILL.md                   # Main documentation ( --validate_only
```

### Full Scoring (with spec grounding)
```bash
uv run python scripts/score-skills.py 
```

### Batch All Skills
```bash
uv run python scripts/score-skills.py . --scan_all
```

## Common Pitfalls

1. **First-person descriptions** - Use "Analyzes..." not "I analyze..."
2. **Missing trigger keywords** - Agents can't find the skill
3. **Too long SKILL.md** - Move details to references/ and add trigger context (e.g. "Read when working with X")
4. **Nested reference folders** - Only one level allowed
5. **Abstract examples** - Use concrete, real scenarios
6. **Noun-form names** - Use "analyzing-data" not "data-analyzer"
7. **No Quick Start** - Users abandon without immediate value
8. **Inconsistent terminology** - Pick terms and stick with them
9. **Missing pitfalls section** - Helps users avoid mistakes
10. **Time-sensitive content** - Skills should be evergreen

## References

- [skill-checklist.md](references/skill-checklist.md) - Read when scoring or reviewing a skill to get the full rubric breakdown, anti-patterns, and evaluation template
- [examples.md](references/examples.md) - Read when creating a new skill or refactoring an existing one to see concrete patterns from well-designed skills

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [altertable-ai](https://github.com/altertable-ai)
- **Source:** [altertable-ai/skills](https://github.com/altertable-ai/skills)
- **License:** MIT
- **Homepage:**  https://altertable.ai

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-altertable-ai-skills-evaluating-skills
- Seller: https://agentstack.voostack.com/s/altertable-ai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.