Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Summary

Spec-Driven Development toolkit - build high-quality software through executable specifications. Based on github/spec-kit.

Install to Claude Code

/plugin install spec-kit@awesome-plugins

Run in Claude Code. Add the marketplace first with /plugin marketplace add chenxizhang/agent-skills-and-plugins if you haven't already.

README.md

Claude Code Plugins Marketplace

A curated collection of plugins for Claude Code, Anthropic's official CLI for Claude.

Installation

Install the entire marketplace with a single command:

/plugin marketplace add chenxizhang/agent-skills-and-plugins

Or install individual plugins locally:

claude --plugin-dir ./plugins/<plugin-name>

Available Plugins

spec-kit

Spec-Driven Development (SDD) toolkit — build high-quality software through executable specifications.

Based on github/spec-kit. This plugin guides you through a structured methodology: define your constitution → specify features → plan implementations → implement with TDD.

Available Skills

| Skill | Command | Description | |-------|---------|-------------| | Initialize | /spec-kit:init | Set up a new SDD project scaffold | | Constitution | /spec-kit:constitution | Define project principles and governance | | Specify | /spec-kit:specify | Create feature specifications from natural language | | Clarify | /spec-kit:clarify | Resolve ambiguities in specifications (up to 5 targeted questions) | | Plan | /spec-kit:plan | Generate technical implementation plans with research | | Tasks | /spec-kit:tasks | Break plans into user-story-organized task lists | | Analyze | /spec-kit:analyze | Cross-artifact consistency and quality analysis | | Implement | /spec-kit:implement | Execute tasks phase-by-phase with TDD | | Checklist | /spec-kit:checklist | Create quality gates (security, performance, UX, testing) | | Tasks to Issues | /spec-kit:tasks-to-issues | Convert tasks to GitHub Issues | | Check Updates | /spec-kit:check-updates | Check for upstream template updates |

Typical Workflow

/spec-kit:init              → Initialize project
/spec-kit:constitution      → Define principles
/spec-kit:specify <feature> → Write feature spec
/spec-kit:clarify           → Resolve ambiguities (optional)
/spec-kit:plan              → Create technical plan
/spec-kit:tasks             → Generate task list
/spec-kit:analyze           → Quality check (optional)
/spec-kit:implement         → Execute implementation

Project Structure (created by the plugin)

.speckit/
├── constitution.md     — Project principles
├── spec-template.md    — Feature spec template
├── plan-template.md    — Implementation plan template
├── tasks-template.md   — Task breakdown template
└── upstream.json       — Upstream sync metadata
specs/
└── 001-feature-name/
    ├── spec.md         — Feature specification
    ├── plan.md         — Implementation plan
    ├── research.md     — Technical research
    ├── data-model.md   — Data model
    ├── contracts/      — Interface contracts
    ├── tasks.md        — Task list
    └── checklists/     — Quality gate checklists

Staying in Sync with Upstream

Run /spec-kit:check-updates to check whether the upstream spec-kit repository has released new template updates or methodology changes.

---

openspec

OpenSpec OPSX — a fluid, iterative SDD framework for AI-assisted development.

Based on Fission-AI/OpenSpec. Uses a lightweight "changes" model: create a change directory with planning artifacts, implement with /apply, archive when done. All commands use the /opsx: prefix.

Available Skills

Core Profile (default workflow)

| Skill | Command | Description | |-------|---------|-------------| | Propose | /openspec:propose | Create a change and generate all planning artifacts in one step | | Explore | /openspec:explore | Think through ideas and clarify requirements before building | | Apply | /openspec:apply | Implement tasks from the active change | | Archive | /openspec:archive | Archive a completed change, merging specs into main |

Expanded Workflow (granular control)

| Skill | Command | Description | |-------|---------|-------------| | New | /openspec:new | Scaffold a new change (no artifacts yet) | | Continue | /openspec:continue | Create the next artifact (one at a time) | | Fast-forward | /openspec:ff | Create all remaining artifacts at once | | Verify | /openspec:verify | Validate implementation against specs | | Sync | /openspec:sync | Merge specs into main without archiving |

Maintenance

| Skill | Command | Description | |-------|---------|-------------| | Check Updates | /openspec:check-updates | Check for upstream methodology updates |

Quick Start

# Simple path (one command to start):
/openspec:propose add-dark-mode

# Granular path (step by step):
/openspec:new add-dark-mode
/openspec:continue     # create proposal.md
/openspec:continue     # create specs/
/openspec:continue     # create design.md
/openspec:continue     # create tasks.md
/openspec:apply        # implement
/openspec:archive      # done

Project Structure (created by the plugin)

openspec/
├── config.yaml           — Project config (schema, context, rules)
├── specs/                — Canonical specifications (merged from changes)
│   └── <capability>/
│       └── spec.md
└── changes/
    ├── <active-change>/  — In-progress work
    │   ├── .openspec.yaml
    │   ├── proposal.md
    │   ├── specs/
    │   ├── design.md
    │   └── tasks.md
    └── archive/          — Completed changes
        └── <date>-<name>/

Staying in Sync with Upstream

Run /openspec:check-updates to check whether the upstream OpenSpec repository has released new methodology updates, schema changes, or workflow improvements.

---

Repository Structure

agent-skills-and-plugins/
├── .claude-plugin/
│   └── marketplace.json      — Marketplace definition
├── plugins/
│   ├── spec-kit/             — Spec-Kit plugin (github/spec-kit)
│   │   ├── .claude-plugin/
│   │   │   └── plugin.json
│   │   └── skills/
│   │       ├── init/
│   │       ├── constitution/
│   │       ├── specify/
│   │       ├── clarify/
│   │       ├── plan/
│   │       ├── tasks/
│   │       ├── analyze/
│   │       ├── implement/
│   │       ├── checklist/
│   │       ├── tasks-to-issues/
│   │       └── check-updates/
│   └── openspec/             — OpenSpec plugin (Fission-AI/OpenSpec)
│       ├── .claude-plugin/
│       │   └── plugin.json
│       └── skills/
│           ├── propose/
│           ├── explore/
│           ├── apply/
│           ├── archive/
│           ├── new/
│           ├── continue/
│           ├── ff/
│           ├── verify/
│           ├── sync/
│           └── check-updates/
├── CLAUDE.md                 — Development guidance
└── README.md                 — This file

Creating Your Own Plugin

This repository follows the Claude Code plugin architecture. Each plugin is self-contained under plugins/ with:

  • .claude-plugin/plugin.json — Plugin manifest (name, version, description)
  • commands/ — Slash commands (Markdown files)
  • agents/ — Custom agents (Markdown files)
  • skills/ — Interactive skills (subdirectories with SKILL.md)
  • hooks/ — Event hooks (JSON configuration)
  • .mcp.json — MCP server definitions (optional)

See CLAUDE.md for detailed development guidance.

Testing Locally

# Test a specific plugin
claude --plugin-dir ./plugins/spec-kit
claude --plugin-dir ./plugins/openspec

# Validate plugin structure
claude plugin validate ./plugins/spec-kit
claude plugin validate ./plugins/openspec

Upstream Sync Design

Both spec-kit and openspec plugins are based on external methodology repositories. Each plugin includes a check-updates skill that:

1. Stores metadata in the project directory (upstream.json for spec-kit, openspec/config.yaml for openspec) tracking the last known upstream commit SHA and check date 2. Fetches upstream status via GitHub API to compare the current HEAD with the stored SHA 3. Reports changes grouped by type (new commands, template updates, methodology changes, bug fixes) 4. Provides update instructions specific to what changed, whether to reinstall CLI tools or manually update skill files

This lightweight design means:

  • No automatic file modification — users stay in control
  • Works offline (reports status without making changes)
  • Clear audit trail of when checks were last run
  • Actionable update instructions rather than just "update available"

License

MIT

Related plugins

Browse all →