grade-rule — for Claude Code grade-rule, boilerplate-vite-supabase-mui-cursor, community, for Claude Code, ide skills, EXECUTE, ATTACHED, CONTEXT, INSTEAD, rubric

v1.0.0
GitHub

Acerca de este Skill

Escenario recomendado: Ideal for AI agents that need do not execute the other attached rule context. instead, grade it:. Resumen localizado: Boilerplate for the stack boilerplate-vite-supabase-mui-cursor with no opinionated app hosting.

Características

DO NOT EXECUTE THE OTHER ATTACHED RULE CONTEXT. INSTEAD, GRADE IT:
Cursor Command Quality Rubric
Here's a rubric for grading Cursor commands on a 1-5 scale across key dimensions:
Clarity of Instructions (Weight: 25%)
------- -------------

# Core Topics

for Claude Code EXECUTE ATTACHED CONTEXT INSTEAD rubric
TMI-apps TMI-apps
[2]
[0]
Updated: 4/19/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
10/11
Quality Score
70
Canonical Locale
en
Detected Body Locale
en

Escenario recomendado: Ideal for AI agents that need do not execute the other attached rule context. instead, grade it:. Resumen localizado: Boilerplate for the stack boilerplate-vite-supabase-mui-cursor with no opinionated app hosting.

¿Por qué usar esta habilidad?

Recomendacion: grade-rule helps agents do not execute the other attached rule context. instead, grade it:. Boilerplate for the stack boilerplate-vite-supabase-mui-cursor with no opinionated app hosting.

Mejor para

Escenario recomendado: Ideal for AI agents that need do not execute the other attached rule context. instead, grade it:.

↓ Casos de uso accionables for grade-rule

Caso de uso: Applying DO NOT EXECUTE THE OTHER ATTACHED RULE CONTEXT. INSTEAD, GRADE IT:
Caso de uso: Applying Cursor Command Quality Rubric
Caso de uso: Applying Here's a rubric for grading Cursor commands on a 1-5 scale across key dimensions:

! Seguridad y limitaciones

  • Limitacion: DO NOT EXECUTE THE OTHER ATTACHED RULE CONTEXT. INSTEAD, GRADE IT:
  • Limitacion: 3 Mostly clear but some vague sections require the assistant to make assumptions.
  • Limitacion: 2 Frequently unclear. Assistant must guess intent in multiple places.

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Install Path

Start With Installation And Validation

If this skill is worth continuing with, the next step is to confirm the install command, CLI write path, and environment validation.
Trusted Recheck

Cross-Check Against Trusted Picks

If you are still comparing multiple skills or vendors, go back to the trusted collection before amplifying repository noise.
Workflow

Move To Workflow Collections For Team Rollout

When the goal shifts from a single skill to team handoff, approvals, and repeatable execution, move into workflow collections.
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is grade-rule?

Escenario recomendado: Ideal for AI agents that need do not execute the other attached rule context. instead, grade it:. Resumen localizado: Boilerplate for the stack boilerplate-vite-supabase-mui-cursor with no opinionated app hosting.

How do I install grade-rule?

Run the command: npx killer-skills add TMI-apps/boilerplate-vite-supabase-mui-cursor/grade-rule. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for grade-rule?

Key use cases include: Caso de uso: Applying DO NOT EXECUTE THE OTHER ATTACHED RULE CONTEXT. INSTEAD, GRADE IT:, Caso de uso: Applying Cursor Command Quality Rubric, Caso de uso: Applying Here's a rubric for grading Cursor commands on a 1-5 scale across key dimensions:.

Which IDEs are compatible with grade-rule?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for grade-rule?

Limitacion: DO NOT EXECUTE THE OTHER ATTACHED RULE CONTEXT. INSTEAD, GRADE IT:. Limitacion: 3 Mostly clear but some vague sections require the assistant to make assumptions.. Limitacion: 2 Frequently unclear. Assistant must guess intent in multiple places..

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add TMI-apps/boilerplate-vite-supabase-mui-cursor/grade-rule. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use grade-rule immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

grade-rule

Install grade-rule, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

grade-rule

DO NOT EXECUTE THE OTHER ATTACHED RULE CONTEXT. INSTEAD, GRADE IT:

Use the rubric below to evaluate the attached rule/command file. Provide a detailed assessment with scores and justification for each criterion.

Cursor Command Quality Rubric

Here's a rubric for grading Cursor commands on a 1-5 scale across key dimensions:

1. Clarity of Instructions (Weight: 25%)

ScoreDescription
5Crystal clear, unambiguous instructions. Each step is explicit with no room for misinterpretation. Uses precise language and concrete examples.
4Clear instructions with minor ambiguities. Assistant can reliably follow with minimal interpretation.
3Mostly clear but some vague sections require the assistant to make assumptions.
2Frequently unclear. Assistant must guess intent in multiple places.
1Confusing or contradictory instructions. High likelihood of misinterpretation.

Key questions:

  • Can the assistant execute this without asking clarifying questions?
  • Are technical terms defined or used consistently?
  • Are conditionals (if/then) explicitly stated?

2. Handling Ambiguous User Input (Weight: 25%)

ScoreDescription
5Explicitly defines how to handle vague/incomplete user requests. Includes fallback behaviors, clarification prompts, and decision trees for common ambiguities.
4Addresses most ambiguity scenarios with clear guidance. Minor edge cases may be unhandled.
3Some guidance for ambiguity, but relies on assistant judgment for many scenarios.
2Limited guidance. Assistant is left to improvise when user input is unclear.
1No consideration for ambiguous input. Command assumes perfect user requests.

Key questions:

  • Does it tell the assistant what to do when the user's request is incomplete?
  • Are there explicit "ask the user" triggers defined?
  • Does it prevent the assistant from making dangerous assumptions?

3. Structure & Organization (Weight: 15%)

ScoreDescription
5Logical flow with clear sections, headers, and hierarchy. Easy to scan and reference. Uses formatting (lists, code blocks) effectively.
4Well-organized with minor structural improvements possible.
3Adequate structure but could be clearer. Some sections feel out of place.
2Poorly organized. Important information buried or scattered.
1No discernible structure. Stream of consciousness.

4. Completeness (Weight: 15%)

ScoreDescription
5Covers all necessary scenarios including success paths, error handling, edge cases, and exit conditions. Nothing left implicit.
4Covers main scenarios well. Minor gaps in edge case handling.
3Handles happy path but misses several important scenarios.
2Significant gaps. Many scenarios require assistant to improvise.
1Incomplete. Missing critical steps or scenarios.

5. Actionability (Weight: 10%)

ScoreDescription
5Every instruction is directly actionable. Verbs are specific (e.g., "search for X in Y" vs "look around"). Outputs are clearly defined.
4Mostly actionable with occasional vague directives.
3Mix of actionable and abstract instructions.
2Many instructions are too abstract to execute directly.
1Instructions are philosophical rather than actionable.

6. Guardrails & Safety (Weight: 10%)

ScoreDescription
5Explicit boundaries on what the assistant should NOT do. Includes validation steps, confirmation prompts for destructive actions, and scope limits.
4Good guardrails for major risks. Minor oversights.
3Some guardrails but gaps in protection against common mistakes.
2Few guardrails. Assistant could easily go off-track.
1No guardrails. High risk of unintended consequences.

Scoring Template

Use this template to calculate the final grade:

Command: ____________________

| Criterion                    | Score (1-5) | Weight | Weighted |
|------------------------------|-------------|--------|----------|
| Clarity of Instructions      |             | 0.25   |          |
| Handling Ambiguous Input     |             | 0.25   |          |
| Structure & Organization     |             | 0.15   |          |
| Completeness                 |             | 0.15   |          |
| Actionability                |             | 0.10   |          |
| Guardrails & Safety          |             | 0.10   |          |
|------------------------------|-------------|--------|----------|
| TOTAL                        |             | 1.00   |    /5    |

Grade Scale:

  • A (4.5-5.0): Excellent - Ready to use with minimal improvements
  • B (3.5-4.4): Good - Solid foundation with some areas for enhancement
  • C (2.5-3.4): Adequate - Works but needs significant improvements
  • D (1.5-2.4): Poor - Major issues that need addressing
  • F (<1.5): Failing - Needs complete revision

Output Format

For each criterion:

  1. Score: Provide the score (1-5)
  2. Justification: Explain why this score was given, citing specific examples from the rule/command
  3. Suggestions: If score < 5, provide concrete suggestions for improvement

After scoring all criteria:

  1. Calculate the weighted total
  2. Assign the letter grade
  3. Provide an overall summary with prioritized recommendations

Habilidades relacionadas

Looking for an alternative to grade-rule or another community skill for your workflow? Explore these related open-source skills.

Ver todo

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
Inteligencia Artificial

widget-generator

Logo of f
f

Generar complementos de widgets personalizables para el sistema de feeds de prompts.chat

★ 149.6k
⑂ 0
Inteligencia Artificial

flags

Logo of vercel
vercel

El Marco de React

★ 138.4k
⑂ 0
Navegador

pr-review

Logo of pytorch
pytorch

Tensores y redes neuronales dinámicas en Python con fuerte aceleración de GPU

★ 98.6k
⑂ 0
Desarrollador