Skip to content
SkillModel-led3,557 tokens in use

spec-driven-development

Write a structured spec before any code, with human approval gates between specify, plan, tasks and implement.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/spec-driven-development
npx skills add addyosmani/agent-skills --skill spec-driven-development
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing spec-driven-development costs

117tokens idle
3,557tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Spec-Driven Development has an agent write a specification first and treat it as the shared source of truth with the human engineer. A gated workflow moves through specify, plan, tasks and implement, and the agent stops after saving the spec so the human can approve it in a later turn.

The spec template covers objective, commands, project structure, code style, testing strategy and boundaries. An optional scope check builds a capability map for requests that bundle several independent capabilities, and later changes get a delta spec.

What You Get

  • A gated four-phase workflow with an optional scope check
  • A spec template with six core areas
  • A capability map template and a delta spec template
  • Rules for keeping the spec current, red flags and a verification checklist

Common Use Cases

  • Starting a new project or feature
  • Clarifying vague requirements into success criteria
  • Decomposing a large request into modules
  • Scoping V1 and deferring ideas to V2

What Makes It Unique

The skill ends the agent’s turn once the spec is saved so planning cannot start without approval. It handles scope growth through an Out of Scope list, a capability map for bundled requests and delta specs for shipped features.

Under The Hood

The skill is a single SKILL.md of instructions. It runs no scripts. The agent writes spec files in the repository, such as spec/capability-map.md and module specs, and hands off to the planning, incremental implementation, test-driven and context engineering skills in later phases.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers