Development Summary

VerifiedSafe

Produces a structured summary of development progress at the end of a feature (Phase 7). Helps document key decisions, modified files, and suggests next steps like commits or new features.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#development#workflow-summary#project-review#next-steps

Recommended for

Automated summary

This skill generates a structured summary of what was built during a development workflow by reading the workflow state, listing modified files, and suggesting next steps.

Strengths

  • Automates documentation of key decisions and development outcomes.
  • Formats durations in a readable and customizable way.
  • Proactive in suggesting follow-up actions like committing or creating a PR.
  • Cleans up workflow state to prevent conflicts.

Limitations

  • Relies on a predefined workflow state file (.dev-workflow-state.json) that must be created by previous phases.
  • Only works within the context of a structured phased development workflow.
  • The ultra-concise output may omit certain important details depending on needs.
When to use it

Use this skill at the end of a development phase (Phase 7) to generate a summary report and propose next steps.

When not to use it

Do not use it to document ad hoc changes or outside a structured workflow, as it expects a well-defined workflow state.

Security analysis

Safe
Quality score85/100

This skill only reads files via Read and Glob; it does not execute any shell commands, network operations, or destructive actions. It reads a local state file and outputs a summary, posing no security risk.

No concerns found

How this analysis is made

Examples

Invoke dev:summary
/dev:summary
Generate development summary via command
Generate a development summary using /dev:summary

name: dev:summary description: Résumé de ce qui a été construit (Phase 7) model: haiku allowed-tools: [Read, Glob] version: 1.0.0 license: MIT

Configuration de sortie

Instructions à Exécuter

IMPORTANT : Exécute ce workflow étape par étape :

IMPORTANT : Cette skill génère un résumé concis et nécessite un format de sortie spécifique.

Lis le frontmatter de cette skill. Si un champ output-style est présent, exécute immédiatement :

/output-style <valeur-du-champ>

Note : Une fois que le champ output-style sera supporté nativement par Claude Code, cette instruction pourra être supprimée.

Output-style requis : ultra-concise

Objectif

Phase 7 du workflow de développement : documenter ce qui a été accompli et suggérer les prochaines étapes.

Instructions

1. Lire le contexte

  • Lire .claude/data/.dev-workflow-state.json pour récupérer toutes les informations du workflow
  • Lister tous les fichiers créés/modifiés

2. Générer le résumé

Présenter un résumé structuré avec :

  • Description de la feature
  • Composants créés
  • Fichiers modifiés
  • Décisions clés
  • Résultats qualité
  • Temps de développement par phase
  • Prochaines étapes suggérées

Format de durée

Formater les durées de manière lisible :

  • < 60s → {X}s (ex: 45s)
  • < 60min → {X}m {Y}s (ex: 2m 30s)
  • >= 60min → {X}h {Y}m (ex: 1h 15m)

3. Nettoyer le workflow state

Marquer le workflow comme terminé

4. Proposer les actions suivantes

📋 Et maintenant ?

- /git:commit - Commiter les changements
- /git:pr - Créer une Pull Request
- /dev:feature <nouvelle-feature> - Démarrer une nouvelle feature

Merci d'avoir utilisé le workflow de développement !

Règles

  • Être concis mais complet
  • Mettre en avant les décisions importantes
  • Toujours suggérer des prochaines étapes
  • Ne pas oublier de marquer les todos comme complétés

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/development-summary-mm5t8bmx/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/development-summary-mm5t8bmx' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/development-summary-mm5t8bmx/download' --output '.skill-downloads/development-summary-mm5t8bmx/SKILL.md.part' && mv '.skill-downloads/development-summary-mm5t8bmx/SKILL.md.part' '.skill-downloads/development-summary-mm5t8bmx/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/development-summary-mm5t8bmx/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