multiAI Summary Pending

prescriptive-actions

Use when the user asks for recommendations, next steps, best approaches, or “what should I do” guidance to achieve a goal or fix a problem.

231 stars

Installation

Claude Code / Cursor / Codex

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

Manual Installation

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

How prescriptive-actions Compares

Feature / Agentprescriptive-actionsStandard Approach
Platform SupportmultiLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use when the user asks for recommendations, next steps, best approaches, or “what should I do” guidance to achieve a goal or fix a problem.

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

# Prescriptive Actions Skill

## Purpose
Provide actionable guidance: recommended approaches, prioritized steps, options, and tradeoffs.

## When to use
Use this skill when the user request is primarily:
- Recommend / advise / propose
- “What should I do?”
- Suggest next steps or an approach
- Diagnose + prescribe direction (but not a full plan)

Do NOT use if the user explicitly asks for:
- a roadmap or timeline (use planning-action)
- a runbook or checklist (use procedural-action)
- success criteria or tests (use validation-action)

## Operating rules
1. Restate the goal in one line.
2. Recommend a primary approach.
3. Provide alternatives when meaningful (A/B).
4. Make tradeoffs explicit (cost, time, risk, complexity).
5. Keep steps high-level and directional, not exhaustive.
6. List assumptions clearly.
7. Follow safety and legality constraints.

## Outputs
Use this structure unless the user specifies otherwise:

### Goal
- One sentence.

### Recommended approach
- 3–6 high-level steps or principles (directional, not detailed).

### Alternatives
- Option A: when to use it
- Option B: when to use it

### Tradeoffs
- Cost / speed / risk / complexity notes

### Key risks
- Major risks to watch (no mitigation plans unless asked)

### Immediate next actions
- 2–5 concrete starting actions (not a full checklist)