Agent Plugins Marketplace
All plugins

szsdlc

v0.1.3

Project-agnostic agentic SDLC framework: entities are the single source of truth, every index is generated, and the deterministic operations are script calls with fixed token cost.

Claude Code10 Skills

By Stephen ZhaoLicense: MIT0 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes
Claude Code
Parsed components
10 skill or MCP entries
Source updated
Aug 25, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology

Install plugin

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install szsdlc@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/stephen-zhao/szsdlc

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

szsdlc/
├── .claude-plugin/plugin.json
├── skills/capture/SKILL.md
├── skills/close/SKILL.md
├── skills/decide/SKILL.md
├── skills/design/SKILL.md
├── skills/execute/SKILL.md
├── skills/plan/SKILL.md
├── skills/refine/SKILL.md
├── skills/roadmap/SKILL.md
├── skills/spike/SKILL.md
└── skills/trace/SKILL.md

Included Skills10

captureskills/capture/SKILL.md

Record passing thoughts, complaints and half-formed "we should someday…" items as tracked ideas without derailing the current conversation. Use whenever someone says note that down, we should, remind me or worth doing later — and whenever they dump several loose thoughts at once, as a list or a rambling paragraph, rather than asking for one of them to be done now.

closeskills/close/SKILL.md

Verify that a piece of work is genuinely finished and move it to a terminal status. Invoke explicitly when work looks done and you want it closed out.

decideskills/decide/SKILL.md

Record an architectural or process decision with its context, options and consequences. Use when a choice is being made that the project will live with, when someone asks why is it built this way, or when a design settles something bigger than one work item.

designskills/design/SKILL.md

Write the design for a piece of work that is ready to start — the approach, the alternatives rejected, and the risks. Use before planning or implementing anything non-trivial, or when asked how should we build this.

executeskills/execute/SKILL.md

Work the current plan task by task, ticking boxes and logging as you go. Invoke explicitly when you want work carried out against a planned item.

planskills/plan/SKILL.md

Turn an agreed design into an ordered checklist of tasks that can be worked one at a time. Use after a design is written, or when asked to break down work that is about to start.

refineskills/refine/SKILL.md

Decide what a captured idea should become and spawn the typed entities for it. Use when working the inbox, when someone asks what to do with an idea, or before scheduling anything that is still just a thought.

roadmapskills/roadmap/SKILL.md

Decide what gets worked on next and in what order, and apply it to the roadmap. Use when asked what should we do next, when reprioritising, when new work needs a place, or when the roadmap has drifted from reality.

spikeskills/spike/SKILL.md

Run a timeboxed investigation to an answer and write it down. Use when a question is blocking a design or an estimate, when someone asks which of these should we use, or when a work item cannot proceed until something is measured or tried.

traceskills/trace/SKILL.md

Answer questions about how work connects — what satisfies a requirement, where a work item came from, what a change would break, or what is blocking something. Use when someone asks why does this exist, what covers this, or what depends on this.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "szsdlc",
  "description": "Project-agnostic agentic SDLC framework: entities are the single source of truth, every index is generated, and the deterministic operations are script calls with fixed token cost.",
  "version": "0.1.3",
  "author": {
    "name": "Stephen Zhao"
  },
  "homepage": "https://github.com/stephen-zhao/szsdlc",
  "license": "MIT",
  "keywords": [
    "sdlc",
    "backlog",
    "traceability",
    "requirements",
    "roadmap"
  ]
}

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[szsdlc on Agent Plugins Marketplace](https://pluginsmp.com/plugins/szsdlc)