I Made a Claude Skill for Spec-Driven Development (SDD)
Details
- External ID
- 48221805
- Source
- HN
- Company
- —
- Product
- I Made a Claude Skill for Spec-Driven Development (SDD)
- Website domain
- github.com
- Launched
- May 21, 2026
- Cohort
- —
- Upvotes
- 40
- Upvotes percentile
- 0.821486268174475
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
At my work they provided a single Claude subscription for everyone on the team. To be honest I like kiro better as it provides a way better SDD management. But the company can't provide it and I can't afford it yet. Turns out I had the skill creator skill in my claude instance so I made use of it to create this Skill. I made it fully by using Claude but I wanted to make it open source, so I asked it to help me make tests and preparations for it, even a CI to run python tests.Well, we got this results with it:- Phase 2A: 67 static assertions (Python script, runs in CI)- Phase 2B: 15 behavioral tests (live Claude Code session)- Phase 2C: 53 generation quality checks across 3 end-to-end flowsAll of these passed and the CI also passed (after a few tries).I made it to suit my way of prompting and coding and based it off kiro's SDD management, but I want it to be publicly available and used by many people. According to claude some of the testers need to fit the following criteria:1. Developer starting a real new project from scratch2. Solo dev with an active side project (greenfield or partial codebase)3. Team lead whose team uses multiple AI tools4. Developer with an existing codebase and no written specs5. Developer who actively uses 3+ AI coding toolsIt's actually a blind test, no guiding, just try it if you can, I'd really appreciate your help.The repo is here: https://github.com/FredAntB/Spec-Driven-Development
Enrichment
- Theme
- ai coding agents and tooling
- Vertical
- —
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- claude skill for spec-driven development
- Manually corrected
- False
Could you build this?
Yes It is a prompt/configuration skill definition for Claude to facilitate Spec-Driven Development, which can be authored in minutes using conversational AI.
Discussion
17 comments analyzed.
Competitors mentioned: Get-Shit-Done (GSD), Superpowers, Compound Engineering, Spec Kit, Allium
Concerns raised: Context rot on large specs causes hallucinations and drift, One-shot generation of all documents prevents review between phases, Shallow initial prompting doesn't ask enough questions, Limited to 4-question interview minimum, No versioning/changelog visibility for generated documents
Feature requests: Follow-up interview questions based on project type (API vs frontend vs data pipeline), Sequential document generation with review gates between phases, Multi-agent review of generated plans before execution, Proper context rotation for larger specs, More prominent versioning/changelog in templates
Competitors
Other products that read as similar to this one — 188 launches clear the similarity bar, closest 8 shown.
Attention rank: #38 of 189 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 191 days after the earliest competitor.
- MakeSkill · hn · 2025-11-27 · 9 upvotes · similarity 0.55
- Spec-Driven Development Workflow for Claude Code · hn · 2026-05-22 · 20 upvotes · similarity 0.55
- Agent-evals · hn · 2026-05-04 · 9 upvotes · similarity 0.54
- Agent37 · hn · 2025-12-29 · 5 upvotes · similarity 0.52
- Generate Claude Code Workflows using Spec Driven Development approach · hn · 2026-05-28 · 5 upvotes · similarity 0.51
- claude-sdlc-skills · github · 2026-09-12 · 8 upvotes · similarity 0.49
- A registry for curated, high quality Claude skills and skillsets · hn · 2026-01-22 · 9 upvotes · similarity 0.49
- I built a way to find and install Claude skills · hn · 2026-06-02 · 7 upvotes · similarity 0.48