spec-driven

Convert compound SEO requests into spec, plan, and result-check artifacts.

49|7|Updated May 4, 2026
One-click install
npx skills add https://github.com/agencia-conversion/agentic-seo-skills --skill spec-driven-agencia-conversion
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spec-driven
Source: https://github.com/agencia-conversion/agentic-seo-skills/tree/main/skills/spec-driven
Command: npx skills add https://github.com/agencia-conversion/agentic-seo-skills --skill spec-driven-agencia-conversion

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents agent workflows from skipping planning by converting a multi-outcome user request into clear control artifacts (spec, plan, and result checks) that downstream skills can execute safely and coherently.

Core Features & Use Cases

  • Compound request detection: Ensures the skill only runs when multiple deliverables, pillars, dependencies, or gates are involved.
  • Durable workbench artifacts: Creates spec.md, plan.md, and result-check.md under project/workbench/specs/<slug>/ for stable downstream execution.
  • Gate-and-blocker visibility: Keeps upstream evidence and decision requirements explicit, marking dependent deliverables as blocked when prerequisites are missing.
  • Separation of concerns: Enforces that raw sources stay in project/sources/, synthesis stays in project/workbench/, and completed outputs go to project/artifacts/, without writing into project/brain/ unless a type: decision is properly logged.

Quick Start

Ask for something like an SEO technical audit plus a content plan plus publication readiness review, and instruct the agent to create a durable spec and plan for the SEO deliverables while marking website generation as out of scope.

Frequently Asked Questions about spec-driven

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a compound SEO and content workflow request into a structured plan?

A compound SEO and content workflow request is converted into durable specification, planning, and result-check artifacts stored under project/workbench/specs/, ensuring downstream execution remains safe and coherent.

When do I need specification artifacts for content governance and workflow planning?

Specification artifacts are needed when a content governance or workflow planning request involves multiple deliverables, cross-pillar work, dependent gates, or downstream skill prerequisites rather than a single-step task.

How do I manage blocked deliverables and evidence gating in a multi-stage SEO strategy?

Evidence gating and blocked deliverables are managed by keeping upstream decision requirements explicit, marking dependent tasks as blocked when prerequisites are missing, and exposing evidence checks across the SEO strategy workflow.

Can I write draft content directly into the project brain during spec-driven workflow planning?

Drafts and unevidenced strategy cannot be written into project/brain/ during spec-driven workflow planning; raw sources stay in project/sources/, synthesis in project/workbench/, and completed outputs in project/artifacts/.

What is the best way to separate raw sources from synthesis in a technical SEO audit workflow?

The best way to separate raw sources from synthesis in a technical SEO audit is enforcing strict directory boundaries where raw inputs stay in project/sources/, synthesis occurs in project/workbench/, and finalized deliverables go to project/artifacts/.

Does spec-driven workflow planning work for single-step content tasks?

Spec-driven workflow planning does not suit single-step content tasks; it requires compound requests with multiple deliverables, cross-pillar dependencies, and downstream execution gates to generate durable workbench control files.