Automatic implementation plan generation

VerifiedSafe

This skill automatically generates a detailed implementation plan based on previous workflow phases (feature description, clarifications, and chosen architecture). It creates a structured markdown file with summary, context, components, steps and tests, then updates the workflow state. Useful for automating phase 5 of a development process without human intervention.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#auto-plan#implementation-plan#workflow-automation#feature-planning

Recommended for

Automated summary

Automatically generates a detailed implementation plan based on previous phases of a structured workflow, with no user interaction.

Strengths

  • Automates creation of reproducible implementation plans
  • Integrates with a multi-phase workflow with persistent state
  • Produces structured documentation (components, tasks, tests)

Limitations

  • Depends on previous phases (architecture, clarification) which must be completed
  • Rigid output format (Markdown with predefined sections)
  • Requires prior setup of the workflow state
When to use it

When working in an automated sequential workflow and need to generate an implementation plan without manual intervention.

When not to use it

For ad-hoc projects without a defined workflow structure, or when you need iterative planning with human validation at each step.

Security analysis

Safe
Quality score85/100

The skill only uses Read, Write, and Glob tools to read a state file, generate a markdown plan, and update a JSON state file. No destructive commands, network access, or secret exfiltration are involved.

No concerns found

How this analysis is made

Examples

Generate plan from issue
Run Phase 5 of the dev workflow for issue #42: auto-generate the implementation plan from the workflow state.
Auto plan after architecture
Using the architecture chosen in the previous phase, automatically create the implementation plan in docs/specs/feature-auth.md.

name: dev:auto:plan description: Générer plan d'implémentation automatiquement - Mode AUTO (Phase 5) model: sonnet allowed-tools:

  • Write
  • Read
  • Glob version: 1.0.0 license: MIT

Objectif

Instructions à Exécuter

IMPORTANT : Exécute ce workflow étape par étape :

Phase 5 du workflow automatisé : générer un plan d'implémentation détaillé basé sur l'architecture choisie SANS interaction.

Instructions

1. Lire le contexte

Déterminer le chemin du workflow state :

workflow_state_file=".claude/data/workflows/issue-${issue_number}-dev-workflow-state.json"
  • Lire le workflow state pour récupérer :
    • La feature description
    • Les décisions de clarification (Phase 3)
    • L'architecture choisie (Phase 4)
  • Si phases précédentes non complétées, exit avec erreur code 1

2. Générer le plan

Créer le fichier docs/specs/feature-{nom-kebab-case}.md avec le contenu suivant :

# Plan d'implémentation : {Feature Name}

## Résumé

**Feature :** {description}
**Approche :** {nom de l'approche choisie}
**Date :** {date du jour}

## Contexte

### Problème résolu
{description du problème}

### Décisions prises
- {décision 1}
- {décision 2}

## Architecture

### Composants
| Composant | Responsabilité | Fichier |
|-----------|---------------|---------|
| {nom} | {description} | `{chemin}` |

### Diagramme de flux

{représentation ASCII du flux}


## Plan d'implémentation

### Étape 1 : {titre}
- [ ] {tâche 1}
- [ ] {tâche 2}

**Fichiers :**
- `{chemin}` : {description}

### Étape 2 : {titre}
- [ ] {tâche 1}
- [ ] {tâche 2}

**Fichiers :**
- `{chemin}` : {description}

...

## Tests

### Tests unitaires
- [ ] {test 1}
- [ ] {test 2}

### Tests d'intégration
- [ ] {test 1}

3. Sauvegarder le chemin du plan

Mettre à jour le workflow state :

{
  "currentPhase": 5,
  "phases": {
    "5": {
      "status": "completed",
      "completedAt": "{ISO timestamp}",
      "durationMs": {durée},
      "planPath": "docs/specs/feature-{nom-kebab-case}.md",
      "components": ["{liste des composants}"],
      "implementationSteps": {nombre}
    }
  }
}

Règles

  • ✅ Mode automatique : aucune interaction
  • ✅ Générer le plan basé sur les phases précédentes
  • ✅ Créer le fichier docs/specs/ avec chemin correct
  • ✅ Documenter chaque étape d'implémentation
  • ❌ Jamais demander confirmation
  • ✅ Exit 1 si phases précédentes manquantes

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/automatic-implementation-plan-generation-mma3js25/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/automatic-implementation-plan-generation-mma3js25' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/automatic-implementation-plan-generation-mma3js25/download' --output '.skill-downloads/automatic-implementation-plan-generation-mma3js25/SKILL.md.part' && mv '.skill-downloads/automatic-implementation-plan-generation-mma3js25/SKILL.md.part' '.skill-downloads/automatic-implementation-plan-generation-mma3js25/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/automatic-implementation-plan-generation-mma3js25/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