multiAI Summary Pending

descriptive-action

Use when the user asks to describe, summarize, analyze, compare, explain, or report on something (text, data, events, systems) without asking for recommendations or next steps.

231 stars

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/descriptive-action/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/bellabe/descriptive-action/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/descriptive-action/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How descriptive-action Compares

Feature / Agentdescriptive-actionStandard Approach
Platform SupportmultiLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when the user asks to describe, summarize, analyze, compare, explain, or report on something (text, data, events, systems) without asking for recommendations or next steps.

Which AI agents support this skill?

This skill is compatible with multi.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Descriptive Action Skill

## Purpose
Produce accurate, neutral descriptions and analyses. Do not prescribe actions unless explicitly requested.

## When to use
Use this skill when the user request is primarily:
- Describe / explain / summarize / define
- Analyze / interpret / compare
- Extract facts from provided material
- Report status, metrics, or observations

Do NOT use if the user asks “what should I do”, “recommend”, “best way”, “steps”, “plan”, or “strategy”.

## Operating rules
1. Stay observational: focus on what is true in the input and what can be inferred safely.
2. Separate facts from interpretation:
   - Facts: directly supported by the provided input.
   - Inferences: clearly labeled.
3. If key information is missing, state what’s missing and proceed with bounded analysis.
4. Avoid normative language.
5. Prefer structure over prose.

## Inputs
- Text, data, artifacts, or systems to describe
- Any stated constraints (scope, timeframe, audience)

## Outputs
Structured descriptive analysis using the format below.

### Summary
- 3–6 bullets capturing the main points.

### Details
- Organized sections (background, findings, trends, constraints).

### Evidence
- Brief references to supporting input.

### Open questions
- Unknowns limiting confidence.