Menu

Not in the top 1,000 by GitHub stars

FredAntB/Spec-Driven-Development

A Claude skill that keeps your AI coding tools from contradicting each other. Generates requirements.md, design.md, and tasks.md before any code is written — then creates matching config files for Claude Code, Cursor, Copilot, Windsurf, and Aider.

Claude CodeEngineeringDesign

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 7296108716de

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 7296108716dea8447938a81fa82bbf7369a0fce2

git clone --filter=blob:none --no-checkout https://github.com/FredAntB/Spec-Driven-Development.git .hotskills/fredantb-spec-driven-development && git -C .hotskills/fredantb-spec-driven-development checkout --detach 7296108716dea8447938a81fa82bbf7369a0fce2 # Copy each selected skill directory from .hotskills/fredantb-spec-driven-development into .claude/skills/<skill-name>/
158GitHub stars
3stars in 7 days
1skill in this repository
0commits in 30 days

Heat

2.8
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 3, 2026158

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

spec-driven-development

When your agent uses it

Use this skill to scaffold Spec Driven Development: requirements.md, design.md, tasks.md, and cross-compatible AI config files (CLAUDE.md, .cursorrules, .windsurfrules, .github/copilot-instructions.md). Triggers: 'requirements', 'spec', 'design doc', 'tasks', 'CLAUDE.md', 'cursorrules', 'SDD', 'spec driven', 'AI configuration', 'cross-AI', 'multi-agent', 'agent setup'. Also trigger for: 'set up my AI tools', 'keep agents consistent', 'stop AI going off-script', 'plan before coding', 'structure project for AI'. Retrofit triggers: 'document my system', 'document my codebase', 'describe my architecture', 'write up what we built', 'add specs to existing project', 'no specs yet', 'help me document', 'I already have a codebase'. Use whenever a user wants to start a project, configure coding agents, create spec docs, or prevent AI agents from drifting, hallucinating scope, or producing inconsistent implementations.

What it loads into context

Frontmatter

241 tokens

Always available to the agent

SKILL.md

5,018 tokens

When the skill is activated

Reference documents

36,648 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. When to Read Reference Files
  2. Workflow: First Run (New Project)
  3. Workflow: Existing Project (Retrofit)
  4. Workflow: Updating Specs (Change Request)
  5. Session Management — CONTEXT.md
  6. Output Quality Checklist
  7. Metrics: Evaluating SDD Health
  8. Teaching Mode
  9. Common Mistakes to Prevent

Scripts executed separately

  • phase2a/run_assertions.py
  • phase2c/check_outputs.py

Files

  • .github/workflows/ci.ymlasset6,941 bytes
  • CLAUDE.mddoc1,965 bytes
  • LICENSEasset1,093 bytes
  • README.mddoc14,231 bytes
  • SKILL.mdcore21,698 bytes
  • beta/BETA_PLAN.mddoc7,891 bytes
  • beta/ISSUE_TEMPLATES.mddoc1,987 bytes
  • beta/TESTER_BRIEF.mddoc2,330 bytes
  • phase2a/KICKOFF.mddoc728 bytes
  • phase2a/assertions.mddoc8,806 bytes
  • phase2a/run_assertions.pyruns15,107 bytes
  • phase2b/KICKOFF.mddoc857 bytes
  • phase2b/eval_report.mddoc7,126 bytes
  • phase2b/eval_session.mddoc17,915 bytes
  • phase2c/KICKOFF.mddoc1,547 bytes
  • phase2c/check_outputs.pyruns11,795 bytes
  • phase2c/eval_flows.mddoc10,840 bytes
  • phase2c/eval_report_2c.mddoc4,248 bytes
  • phase2c/flow_a/.cursorrulesasset1,988 bytes
  • phase2c/flow_a/CLAUDE.mddoc1,974 bytes
  • phase2c/flow_a/design.mddoc8,851 bytes
  • phase2c/flow_a/requirements.mddoc4,268 bytes
  • phase2c/flow_a/tasks.mddoc6,945 bytes
  • phase2c/flow_b/design.mddoc7,550 bytes
  • phase2c/flow_b/requirements.mddoc5,805 bytes
  • phase2c/flow_b/tasks.mddoc6,786 bytes
  • phase2c/flow_c/.cursorrulesasset1,988 bytes
  • phase2c/flow_c/.github/copilot-instructions.mddoc2,060 bytes
  • phase2c/flow_c/.windsurfrulesasset1,969 bytes
  • phase2c/flow_c/CLAUDE.mddoc2,007 bytes
  • references/capabilities-and-cross-ai.mddoc8,753 bytes
  • references/sdd-curriculum.mddoc11,012 bytes
  • references/templates.mddoc6,195 bytes
Read SKILL.md

# Spec Driven Development Skill

This skill guides the user through creating a complete Spec Driven Development environment:
- `requirements.md` — what the system must do
- `design.md` — how it will be built
- `tasks.md` — atomic, ordered implementation steps
- AI agent configuration files for Claude Code, Cursor, Windsurf, GitHub Copilot, and Aider

**Reference files** (read when needed):
- `references/sdd-curriculum.md` — full teaching curriculum, newbie to hero
- `references/capabilities-and-cross-ai.md` — Claude Code capabilities, limitations, cross-AI strategy
- `references/templates.md` — all spec file and AI config templates

---
View the complete source on GitHub

Skills included

  • spec-driven-development

Repository facts

License
MIT
Created
May 18, 2026
Last pushed
May 23, 2026
Forks
18
Open issues
8
Project activity
Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Show all 16 signals by file

README.md

  • Network accessline 9
    [![Version](https://img.shields.io/badge/version-1.0--beta-blue)](https://github.com/FredAntB/spec-driven-development/releases/tag/v1.0-beta)
  • Network accessline 10
    [![CI](https://github.com/FredAntB/spec-driven-development/actions/workflows/ci.yml/badge.svg)](https://github.com/FredAntB/spec-driven-development/actions/workflows/ci.yml)
  • Network accessline 11
    [![Phase 2A](https://img.shields.io/badge/static%20assertions-67%2F67-brightgreen)](phase2a/assertions.md)
  • Network accessline 12
    [![Phase 2B](https://img.shields.io/badge/behavioral%20tests-15%2F15-brightgreen)](phase2b/eval_session.md)
  • Network accessline 13
    [![Phase 2C](https://img.shields.io/badge/generation%20quality-53%2F53-brightgreen)](phase2c/eval_flows.md)
  • Network accessline 14
    [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
  • Network accessline 88
    git clone https://github.com/FredAntB/spec-driven-development
  • Network accessline 94
    **Windows note:** Git must be installed for the Code tab to work with local folders. Download from [git-scm.com](https://git-scm.com).
  • Network accessline 95
    with local folders. Download from [git-scm.com](https://git-scm.com).

phase2a/run_assertions.py

  • Executable scriptline 1
    #!/usr/bin/env python3

phase2c/check_outputs.py

  • Executable scriptline 1
    #!/usr/bin/env python3

phase2c/flow_a/design.md

  • Access to secretsline 16
    [Credential-related source omitted]

phase2c/flow_a/tasks.md

  • Network accessline 21
    - _Output_: `package.json`, `package-lock.json`, `src/server.js`     listening on `process.env.PORT`.   - _Verify_: `npm install && node src/server.js` boots; curl to `/health`
  • Network accessline 22
    listening on `process.env.PORT`.   - _Verify_: `npm install && node src/server.js` boots; curl to `/health`     returns `200 {"ok":true}`.
  • Network accessline 23
    - _Verify_: `npm install && node src/server.js` boots; curl to `/health`
  • Access to secretsline 36
    [Credential-related source omitted]

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 16 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativePath CLAUDE.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

yvgude/lean-ctx

LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls, connect local knowledge and inspect recorded evidence. Open-source Engine: C…

3.9kGitHub stars

PhAlves23/prompt-engineering-skill

Prompt Engineering skill for Claude Code — rewrites and optimizes prompts using proven techniques (Anthropic, OpenAI, Gemini, The Prompt Report).

13GitHub stars

Gentleman-Programming/gentle-ai

Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills…

8.5kGitHub stars

samber/cc-skills-golang

🧑<U+200D>🎨 A collection of Golang agentic skills that works

3.8kGitHub stars

NeoLabHQ/context-engineering-kit

Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source …

1.8kGitHub stars

sharpdeveye/maestro

Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and 6…

592GitHub stars