By awolve
Spec-driven development — create, sync, and manage spec documents with the Awolve Spec Service
Upload a binary file as an attachment to a spec feature
Add a new idea or feature request to the project backlog (optionally as a child of an epic)
Document work after the fact — create design.md (and optionally plan.md) from what was built
Write requirements.md for a feature — what to build and why
Pull latest spec files from the spec service
Matches all tools
Hooks run on every tool call, not just specific ones
Runs pre-commands
Contains inline bash commands via ! syntax
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Claude Code plugin for spec-driven development with the Awolve Spec Service.
Run these as slash commands inside Claude Code:
/plugin marketplace add awolve/open-claude-plugins
/plugin install awolve-spec@awolve-open-claude-plugins
/reload-plugins
/plugin marketplace update awolve-open-claude-plugins
/awolve-spec:login in Claude Code (Azure CLI or API key).claude/specs.md (shared) or .claude/specs.local.md (personal override):---
service_url: https://specs.awolve.ai
projects:
- id: my-project
path: ./specs
---
Run /awolve-spec:help for the full list, or see below:
| Command | Description |
|---|---|
/awolve-spec:login | Authenticate (Azure CLI or API key) |
/awolve-spec:status | Show sync status and auth info |
/awolve-spec:pull | Pull latest spec files |
| Command | Description |
|---|---|
/awolve-spec:req | Write requirements.md — what to build and why |
/awolve-spec:design | Write design.md — how to build it |
/awolve-spec:plan | Write plan.md — implementation approach and task breakdown |
/awolve-spec:infra | Enrich design.md with infrastructure specifications |
/awolve-spec:retro | Document work after the fact from what was built |
| Command | Description |
|---|---|
/awolve-spec:list-features | List all features in a project |
/awolve-spec:create-feature | Create a new feature |
/awolve-spec:rename-feature | Rename a feature |
/awolve-spec:delete-feature | Delete a feature and all its documents |
/awolve-spec:create-doc | Add a document to an existing feature |
/awolve-spec:rename-doc | Rename a document |
/awolve-spec:delete-doc | Delete a document |
/awolve-spec:set-status | Change feature or document status |
| Command | Description |
|---|---|
/awolve-spec:backlog | List backlog items |
/awolve-spec:backlog-add | Add a new idea or feature request |
/awolve-spec:bugs | List open bugs |
/awolve-spec:bug | Report a new bug |
npx claudepluginhub awolve/open-claude-plugins --plugin awolve-specFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.