Agent Skillswinstonkoh87/Athena-Public › Spec-Driven Development

Spec-Driven Development

GitHub

通过强制在编码前进行需求问询、编写设计规格书并获用户批准,防止盲目开发。适用于复杂功能或耗时任务,确保明确目标与边界。

examples/skills/coding/spec-driven-dev/SKILL.md winstonkoh87/Athena-Public

Trigger Scenarios

需要修改多个文件的功能开发 预计耗时超过30分钟的任务 缺乏清晰需求说明的开发场景

Install

npx skills add winstonkoh87/Athena-Public --skill Spec-Driven Development -g -y
More Options

Non-standard path

npx skills add https://github.com/winstonkoh87/Athena-Public/tree/main/examples/skills/coding/spec-driven-dev -g -y

Use without installing

npx skills use winstonkoh87/Athena-Public@Spec-Driven Development

指定 Agent (Claude Code)

npx skills add winstonkoh87/Athena-Public --skill Spec-Driven Development -a claude-code -g -y

安装 repo 全部 skill

npx skills add winstonkoh87/Athena-Public --all -g -y

预览 repo 内 skill

npx skills add winstonkoh87/Athena-Public --list

SKILL.md

Frontmatter
{
    "name": "Spec-Driven Development",
    "model": "default",
    "created": 1772150400,
    "auto-invoke": false,
    "description": "Interrogates the user to build a complete design specification before writing any code. Prevents \"vibe coding\" failures.",
    "context_trigger": "build app, create feature, new project, spec out, design doc, requirements, let's build, software project"
}

📋 Spec-Driven Development

Philosophy: 55 minutes defining the problem, 5 minutes solving it.

1. The Problem

Most AI coding failures happen because the agent starts coding before understanding:

  • What the user actually wants (vs. what they said)
  • Edge cases and constraints
  • Integration points and dependencies
  • Success criteria

2. Execution Workflow

PHASE 1: INTERROGATION (No Code Allowed)
  ├─ "What is the ONE thing this must do?"
  ├─ "What does success look like? Be specific."
  ├─ "What are 3 things this must NOT do?"
  ├─ "Who/what does this interact with?"
  └─ "What's the simplest version that would be useful?"

PHASE 2: SPEC DOCUMENT
  └─ Write a design.md with:
     ├─ Goal (1 sentence)
     ├─ Requirements (numbered list)
     ├─ Non-Requirements (explicit exclusions)
     ├─ Architecture (how components connect)
     ├─ Edge Cases (what could go wrong)
     └─ Acceptance Criteria (how to verify)

PHASE 3: USER APPROVAL
  └─ Present spec for review
  └─ DO NOT proceed to code until approved

PHASE 4: IMPLEMENTATION
  └─ Code against the approved spec
  └─ Reference spec line items in commits

3. The Spec Template

# Design Spec: [Feature Name]

## Goal
[One sentence describing what this does]

## Requirements
1. [Must do X]
2. [Must handle Y]
3. [Must integrate with Z]

## Non-Requirements (Out of Scope)
- [Will NOT do A]
- [Will NOT support B]

## Architecture
[How the components connect — diagram or description]

## Edge Cases
- [What if input is empty?]
- [What if API is down?]
- [What if user does X instead of Y?]

## Acceptance Criteria
- [ ] [Testable condition 1]
- [ ] [Testable condition 2]

4. When to Use

  • Any feature that touches >3 files
  • Any task that takes >30 minutes
  • Any time you catch yourself thinking "I'll figure it out as I go"

skill #engineering #planning #spec

Version History

  • e624e2d Current 2026-07-19 08:47

Same Skill Collection

examples/protocols/diagnostics/DIA-SKILL.md
examples/skills/business/brand-foundations/SKILL.md
examples/skills/business/client-pricing/SKILL.md
examples/skills/business/distribution-physics/SKILL.md
examples/skills/business/marketing-swarm/SKILL.md
examples/skills/business/seo-auditor/SKILL.md
examples/skills/business/sovereign-economics-engine/SKILL.md
examples/skills/coding/agentic-code-orchestrator/SKILL.md
examples/skills/coding/atomic-execution/SKILL.md
examples/skills/coding/dashboard-builder/SKILL.md
examples/skills/coding/diagnostic-refactor/SKILL.md
examples/skills/coding/git-worktree-swarm/SKILL.md
examples/skills/coding/micro-commit/SKILL.md
examples/skills/coding/visual-verify-ui/SKILL.md
examples/skills/decision/bionic-decision-engine/SKILL.md
examples/skills/decision/decision-journal/SKILL.md
examples/skills/decision/mcda-solver/SKILL.md
examples/skills/decision/trading-risk-gate/SKILL.md
examples/skills/decision/zenith-execution/SKILL.md
examples/skills/quality/bionic-safety-net/SKILL.md
examples/skills/quality/circuit-breaker/SKILL.md
examples/skills/quality/consiglieri-protocol/SKILL.md
examples/skills/quality/power-inversion/SKILL.md
examples/skills/quality/red-team-review/SKILL.md
examples/skills/quality/web-launch-gate/SKILL.md
examples/skills/research/data-analysis/SKILL.md
examples/skills/research/deep-research-loop/SKILL.md
examples/skills/research/semantic-search/SKILL.md
examples/skills/research/statistical-analysis/SKILL.md
examples/skills/research/synthetic-parallel-reasoning/SKILL.md
examples/skills/social-physics-filter/SKILL.md
examples/skills/structural-trading-gate/SKILL.md
examples/skills/therapeutic-ifs/SKILL.md
examples/skills/workflow/academic-delivery/SKILL.md
examples/skills/workflow/context-compactor/SKILL.md
examples/skills/workflow/daemon-loop/SKILL.md
examples/skills/workflow/skill-compiler/SKILL.md
examples/skills/workflow/trade-journal-analyzer/SKILL.md

Metadata

Files
0
Version
e624e2d
Hash
d6188251
Indexed
2026-07-19 08:47

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-22 06:07
浙ICP备14020137号-1 $Carte des visiteurs$