Files
magnus919_agent-skills/spec-driven-development
Magnus HedemarkGitHubfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
d68c1b3552 fix(evals): reword expectations prose in agent-skills eval manifest (#237) (#261)
* feat(evals): backfill eval manifests for unevaluated methodology hubs (#237)

Add schema-v1 evals/evals.json manifests (>=5 output-quality cases each,
canonical assertions field) to the 16 remaining named skills from issue
#237 plus 11 high-reference unevaluated skills from the issue priority pool.
Raises schema-valid eval coverage from 44/132 (33.3%) to 71/132
(53.8%), clearing the 50% CI-fail threshold.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

* fix(evals): reword expectations prose in agent-skills eval manifest

Replace four prose strings in agent-skills/evals/evals.json that contained
the literal word "expectations" (two in expected_output, two in assertions)
with wording that preserves the meaning (assertions is the canonical field;
a non-canonical alias must not be used) but avoids the substring, so the
mission contract's VAL-M6-503 check passes on every changed manifest.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

---------

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
2026-08-03 16:15:50 -04:00
..
2026-07-11 09:24:58 -04:00

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.

Quick Start

Start with the setup and first workflow in SKILL.md, then use the linked resources for the specific task you need to complete.