Run Skill Generator — Development skill for Claude Code
Capture a non-trivial build/launch tooling discovery (a setup step, a.
How to install Run Skill Generator
Installs to ~/.claude/skills/siddaharthsuman-spec-driven-dev-run-skill-generator/SKILL.md
mkdir -p ~/.claude/skills/siddaharthsuman-spec-driven-dev-run-skill-generator && curl -fsSL https://raw.githubusercontent.com/SiddaharthSuman/spec-driven-dev/HEAD/commands/run-skill-generator.md -o ~/.claude/skills/siddaharthsuman-spec-driven-dev-run-skill-generator/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Run Skill Generator does
description: Capture a non-trivial build/launch tooling discovery (a setup step, a workaround, a version-pin quirk) as a new project-local skill under .claude/skills/, per the tooling-capture rule in 04-ai-workflow-rules.md. Scope is build/launch recipes specifically. Anything broader gets hand-authored instead.
Take $ARGUMENTS as a description of what was discovered: what you were trying to build or launch, what didn't work as expected, what actually fixed it or made it work,
Alternatives in Development
- 14 Tool Use Summary — Tool Use Summary Generator 2.3k ★
- Part 2 — Product Requirements Document (prd) Generator — I'll help you create a Product Requirements Document (PRD) for your MVP 2.1k ★
- Meta Prompt Generator — You are a prompt engineering specialist who builds production-grade system 1.4k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Arch Decision
Architecture Decision Record (ADR) generator backed by the Claude Power Pack vault. Before committing to a non
Pre Ship Adversary
Before committing a non-trivial change, spend 2-3 minutes attacking the change yourself — scope creep, failure
After Change Monitor
After making any non-trivial change, define a verification window and check back. Don't fire-and-forget.
Connection Finder
Use when looking for non-obvious conceptual relationships between notes that are not linked yet. Read-only dis
Adversarial Dev
GAN-inspired three-agent harness that pits a generator against an adversarial evaluator to build applications
Editscore Ladder Run
Run an EditScore-7B pairwise ladder for an image-edit generator (SDEdit / diffusion / LoRA / distilled step-co
Related Agents
Worktree Setup.Agent
Use when starting work on any non-trivial task that involves edits, multiple parallel tasks on the same repo,
AI Plan
Relentless interrogator and principal delivery architect. Entry point for non-trivial work: runs discovery, ex
Flutter Device Orchestrator
Use this agent when managing iOS simulators and Android emulators for Flutter development. Specializes in devi