Prompt to Executable Tasks Transformer

VerifiedSafe

Converts any free-form prompt into a structured executable prompt with tasks (TaskCreate/TaskUpdate/TaskList), phases, and validation criteria. Helps break down vague requests into concrete, AI-executable steps.

Sby Skills Guide Bot
ProductivityIntermediate
6/2/2026
Claude Code
#prompt-engineering#task-management#orchestration#structured-prompts#automation

Recommended for

Automated summary

Transforms any free-form prompt into a structured executable prompt using Claude Code's Task Management System.

Strengths

  • Converts vague instructions into concrete, verifiable steps
  • Ensures appropriate granularity (5-30 minutes per task)
  • Produces a timestamped, reusable file

Limitations

  • Requires TaskCreate/TaskUpdate/TaskList tools, specific to Claude Code
  • May over-engineer very simple requests
  • Does not handle cyclic dependencies
When to use it

When you have a complex or ambiguous prompt that needs to be broken down into a step-by-step plan.

When not to use it

For a trivial one-step request that can be executed directly.

Security analysis

Safe
Quality score90/100

The skill only uses safe Bash (mkdir -p) and file writes. No destructive commands, no exfiltration, no execution of arbitrary code. The transformation process itself is risk-free.

No concerns found

How this analysis is made

Examples

Build a web scraper
Create a Python script that scrapes news headlines from a given URL and saves them to a CSV file.
Set up a CI pipeline
Set up a GitHub Actions CI pipeline for a Node.js project with linting, testing, and deployment to Vercel.
Organize a project refactor
Refactor the authentication module to use JWT tokens instead of session cookies, with proper error handling and tests.

name: orchestrator:transform description: Transforme un prompt quelconque (texte libre ou fichier) en prompt exécutable structuré avec TaskCreate/TaskUpdate/TaskList. Génère un fichier .claude/prompts/executable-{name}-{timestamp}.md argument-hint: <prompt-file-or-text> [--name=<output-name>] model: sonnet allowed-tools: [Read, Write, Bash, AskUserQuestion, Glob, TaskCreate, TaskUpdate, TaskList] version: 1.0.0 license: MIT

orchestrator:transform

Transformation d'un prompt en prompt exécutable compatible avec le Task Management System.

Instructions à Exécuter

1. Récupérer le prompt source

  • Si argument est un fichier : Read le contenu
  • Si argument est du texte : utiliser directement
  • Si aucun argument : AskUserQuestion pour demander le prompt

2. Analyser le prompt

Identifier :

  • L'objectif principal
  • Les sous-tâches implicites ou explicites
  • Les dépendances entre tâches
  • Les livrables attendus
  • Les critères de validation

3. Structurer en tâches exécutables

Pour chaque tâche :

  • #N : Numéro (commence à 0)
  • content : Description impérative (ex: "Créer le fichier X")
  • activeForm : Forme continue (ex: "Création du fichier X")
  • Critères de validation
  • Dépendances si applicable

4. Générer le format exécutable

Le prompt transformé doit inclure :

# [Titre]

## Objectif
[Description]

## Initialisation des Tâches

TaskCreate #0: [Nom]
  content: "[Description impérative]"
  activeForm: "[Forme continue]"

TaskCreate #1: [Nom]
  ...

## Instructions d'Exécution

### Phase 1 : [Nom]

**Tâche #0 : [Nom]**
1. TaskUpdate #0 → in_progress
2. [Instructions]
3. [Critères de validation]
4. TaskUpdate #0 → completed

## Critères de Validation Globaux

- [ ] Critère 1
- [ ] Toutes les tâches completed (TaskList)

5. Créer le répertoire de sortie

mkdir -p .claude/prompts

6. Écrire le prompt transformé

Nom : .claude/prompts/executable-{name}-{timestamp}.md

{name} depuis :

  1. --name=XXX si fourni
  2. Titre/objectif du prompt (kebab-case)
  3. Sinon "prompt"

{timestamp} : format YYYYMMDD-HHMMSS

7. Afficher le résultat

.claude/prompts/executable-{name}-{timestamp}.md

Tâches extraites : X
Phases : Y

Règles de transformation

  • Granularité : chaque tâche réalisable en 5-30 minutes
  • Atomicité : une tâche = une action claire
  • Vérifiabilité : critère de validation par tâche
  • Numérotation commence à #0
  • Minimum 3 tâches, au moins 2 phases

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/prompt-to-executable-tasks-transformer-mmk3nifg/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/prompt-to-executable-tasks-transformer-mmk3nifg' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/prompt-to-executable-tasks-transformer-mmk3nifg/download' --output '.skill-downloads/prompt-to-executable-tasks-transformer-mmk3nifg/SKILL.md.part' && mv '.skill-downloads/prompt-to-executable-tasks-transformer-mmk3nifg/SKILL.md.part' '.skill-downloads/prompt-to-executable-tasks-transformer-mmk3nifg/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/prompt-to-executable-tasks-transformer-mmk3nifg/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills