prompt-evaluation

Specialized evaluation of prompt quality, clarity, and effectiveness

IndexedMIT

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/ankh-studio-prompt-evaluation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Specialized evaluation of prompt quality, clarity, and effectiveness

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/prompt-evaluation

What's inside

Skill name: prompt-evaluation
Description: Specialized evaluation of prompt quality, clarity, and effectiveness
License: MIT
Instructions: 34 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Prompt Evaluation

Specialized prompt quality assessment with Chain-of-Verification methodology.

## Evaluation Criteria

- **Clarity** (25%): Unambiguous, specific, easily understood
- **Specificity** (25%): Clear expectations and constraints
- **Context** (20%): Relevant background and environment
- **Constraints** (15%): Clear boundaries and limitations
- **Examples** (15%): Illustrative examples and use cases

## Process

1. **Analyze**: Apply prompt-specific rubric criteria
2. **Verify**: Self-critique with 3 potential issues and evidence
3. **Revise**: Incorporate verified corrections
4. **Score**: Calculate weighted scores (0-4 scale)

## Usage

```bash
node scripts/apply-pack.js prompt --path <prompt-file>
```

## Example

```bash
node scripts/apply-pack.js prompt --path .github/prompts/api-design.prompt.md
```

Provides actionable feedback for prompt improvement with evidence-based analysis.

From Ankh-Studio/copilot-enterprise-eval-plugin, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Mar 13, 2026 (7 months ago)
Last release: Mar 14, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/Ankh-Studio/copilot-enterprise-eval-plugin
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Ankh-Studio

Cite this page

prompt-evaluation skill. Agent Mart. https://agentmart.dev/skills/ankh-studio-prompt-evaluation (last updated 2026-10-24)