Skills Guide

Factory Spec - MODEL Phase Orchestrator

VerifiedCaution

Orchestrates the MODEL phase of a factory: sequentially delegates the generation of functional specs (pm), technical specs (architect), and memory rules (rules-memory), with gate checks between steps. Useful for automatically producing specifications, ADRs, and project rules from an initial brief and scope.

Download and use
Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#spec-generation#architecture-decision-records#workflow-orchestration#model-phase

Recommended for

Backend developerClaude CodeCode reviewFrontend developerFullstack developerRefactoring

Automated summary

Orchestrates the MODEL phase by delegating generation of functional and technical specs, ADRs, and memory rules to sub-agents with gate checks.

Strengths

  • Automates a complex document generation pipeline
  • Ensures synchronization and validation of intermediate deliverables
  • Integrates quality gates for early error detection

Limitations

  • Depends on sub-agents availability and completeness
  • Does not cover modeling beyond specs and ADRs
  • Requires a pre-existing project structure (e.g., docs/brief.md, tools/)
When to use it

Use at the start of a project to formalize specifications and architecture decisions before development.

When not to use it

Avoid if the project is already in advanced development or if specifications are not needed.

Security analysis

Caution
Quality score85/100

The skill uses Bash to execute node scripts (gate-check.js, factory-log.js) which are assumed to be part of the repository. These are legitimate development tools, but Bash execution inherently carries risk if scripts are compromised. No destructive or exfiltrating actions are instructed.

No concerns found

How this analysis is made

Examples

Run full MODEL phase
Execute the factory-spec skill to run the MODEL phase: generate specs, ADRs, and rules from docs/brief.md and docs/scope.md.
Regenerate specs only
Re-run the MODEL phase for the current project, skipping gate checks if already passed.

name: factory-spec description: "Phase MODEL - Génère specs + ADR + rules" context: fork allowed-tools: Read, Glob, Grep, Task, Bash

Factory Spec - Phase MODEL

Tu es l'orchestrateur de la phase MODEL.

Workflow

⚠️ SYNCHRONISATION OBLIGATOIRE : Chaque étape DOIT être terminée avant de passer à la suivante. Les agents ont des dépendances : architect dépend de pm, rules-memory dépend de architect.

  1. Vérifier Gate 1 : node tools/gate-check.js 1

    • Si exit code ≠ 0 → STOP immédiat

  2. Déléguer à l'agent pm via Task tool :

    Task(
  subagent_type: "pm",
  prompt: "Produis docs/specs/system.md et docs/specs/domain.md depuis docs/brief.md et docs/scope.md",
  description: "PM - Specs fonctionnelles"
)

    ⏳ ATTENDRE que le Task soit terminé avant de continuer. ✅ Vérifier : docs/specs/system.md ET docs/specs/domain.md existent.

  3. Déléguer à l'agent architect via Task tool :

    Task(
  subagent_type: "architect",
  prompt: "Produis docs/specs/api.md et docs/adr/ADR-0001-stack.md depuis docs/specs/system.md et docs/specs/domain.md",
  description: "Architect - Specs techniques"
)

    ⏳ ATTENDRE que le Task soit terminé avant de continuer. ✅ Vérifier : docs/specs/api.md ET docs/adr/ADR-0001-*.md existent.

  4. Déléguer à l'agent rules-memory via Task tool :

    Task(
  subagent_type: "rules-memory",
  prompt: "Génère les rules dans .claude/rules/ et enrichis CLAUDE.md depuis docs/specs/* et docs/adr/*",
  description: "Rules-Memory - Rules et mémoire"
)

    ⏳ ATTENDRE que le Task soit terminé avant de continuer.

  5. Vérifier les outputs :

    • docs/specs/system.md existe
    • docs/specs/domain.md existe
    • docs/specs/api.md existe
    • docs/adr/ADR-0001-*.md existe

  6. Exécuter Gate 2 : node tools/gate-check.js 2

    • Si exit code ≠ 0 → STOP immédiat avec rapport des erreurs

  7. Logger via :

    node tools/factory-log.js "MODEL" "completed" "Phase MODEL terminée"

  8. Retourner un résumé avec liste des specs générées

En cas d'échec

Si Gate 2 échoue → STOP et rapport des fichiers manquants.

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/factory-spec-model-phase-orchestrator-mma3jrin/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/factory-spec-model-phase-orchestrator-mma3jrin' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/factory-spec-model-phase-orchestrator-mma3jrin/download' --output '.skill-downloads/factory-spec-model-phase-orchestrator-mma3jrin/SKILL.md.part' && mv '.skill-downloads/factory-spec-model-phase-orchestrator-mma3jrin/SKILL.md.part' '.skill-downloads/factory-spec-model-phase-orchestrator-mma3jrin/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.

Tools declared by the author (check availability in your agent): Read, Glob, Grep, Task, Bash

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

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/factory-spec-model-phase-orchestrator-mma3jrin/SKILL.md' && test -s '.skill-downloads/factory-spec-model-phase-orchestrator-mma3jrin/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/factory-spec' && cp -R '.skill-downloads/factory-spec-model-phase-orchestrator-mma3jrin' '.claude/skills/factory-spec'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/factory-spec-model-phase-orchestrator-mma3jrin'

openskills read 'factory-spec-model-phase-orchestrator-mma3jrin'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

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/factory-spec-model-phase-orchestrator-mma3jrin/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

React Hook Form Best Practices

Development

Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.

Claude CodeCursorWindsurf+2intermediateSafe 108,623
Skills Guide Bot

Emotion to Mantine Migration

Development

Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.

Claude CodeCursorWindsurf+1intermediateSafe 48,981
Skills Guide Bot

Scope Creep Detector

Development

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.

Claude CodeCursorCodexintermediateSafe 135,015
Skills Guide Bot