mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-11 19:47:12 +03:00
Each README is written for a human audience, explaining: - What the skill does (not what format it follows) - What benefit the user gets from installing it - Quick setup and usage patterns - When to load/trigger the skill - What scripts, references, and templates it ships data-scientist already had a README — left unchanged. 48 READMEs added across all skill and bundle directories.
1.5 KiB
1.5 KiB
Spec-Driven Development for AI Software Factories
A methodology where structured specifications are the executable input to an AI code generation pipeline. Quality gates enforce correctness at each phase.
Why Install This Skill
When your agent loads this skill, it becomes a software factory designer who can:
- Design an SDD pipeline — 5-phase pipeline from SPECIFY to DELIVER with 4 phase gates
- Write great specs — 7 spec quality gates that separate precise specs from vague ones
- Choose spec methodologies — BDD, OpenAPI, AsyncAPI, DbC, TLA+, ADRs, C4 — matched to your context
- Encode NFRs — performance, security, observability requirements in machine-readable format
- Translate between formats — PRD → SPEC.md → Gherkin → OpenAPI
- Handle gate recovery — revision workflows when specs fail review
What You Get
| Directory | Purpose |
|---|---|
SKILL.md |
Pipeline overview, loading guide, methodology quick-pick |
references/ |
9 reference files: overview, pipeline, quality gates, phase gates, methodology matrix, NFR encoding, format translation, critiques, example spec |
templates/ |
4 spec templates |
scripts/ |
2 validation scripts |
Triggers
Load this when designing a spec-driven pipeline, writing an AI-ready specification, or setting up quality gates for AI code generation.
Requirements
Tool-agnostic — works with Claude Code, Cursor, Hermes Agent, Devin, OpenHands, droid, or any AI coding agent.