Agent Plugins Marketplace
All plugins

spec-driven-engineering

v1.0.1

Spec/design-driven engineering workflow: spec -> plan -> implement -> review -> finish, with supporting standards, architecture, and debugging disciplines

Claude Code16 Skills

By GirijeshLicense: MIT1 GitHub starsUpdated 3 hours ago

Directory evidence

Runtimes
Claude Code
Parsed components
16 skill or MCP entries
Source updated
Sep 3, 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 spec-driven-engineering for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install spec-driven-engineering@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/girijesh-ai/spec-driven-engineering

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

spec-driven-engineering/
├── .claude-plugin/plugin.json
├── skills/codebase-architecture/SKILL.md
├── skills/debug-systematically/SKILL.md
├── skills/dev-workflow/SKILL.md
├── skills/domain-modeling/SKILL.md
├── skills/engineering-standards/SKILL.md
├── skills/finish-branch/SKILL.md
├── skills/grill-me/SKILL.md
├── skills/handoff/SKILL.md
├── skills/implement/SKILL.md
├── skills/plan-from-spec/SKILL.md
├── skills/resolve-merge-conflicts/SKILL.md
├── skills/review-code/SKILL.md
├── skills/spec-from-idea/SKILL.md
├── skills/test-driven-development/SKILL.md
├── skills/triage-issues/SKILL.md
└── skills/writing-for-agents/SKILL.md

Included Skills16

codebase-architectureskills/codebase-architecture/SKILL.md

Use when planning a non-trivial change's file/module structure, or reviewing whether a change's boundaries are sound — the structural lens on modules and boundaries, distinct from SOLID-level class design.

debug-systematicallyskills/debug-systematically/SKILL.md

Use when encountering any bug, test failure, or unexpected behavior, before proposing a fix — to find and fix the true root cause instead of guessing at the symptom the report happened to name.

dev-workflowskills/dev-workflow/SKILL.md

Use when starting any engineering task and it's unclear which skill in this repo to reach for first — routes to the right spine or supporting skill based on where the work actually is.

domain-modelingskills/domain-modeling/SKILL.md

Use when a spec's requirements use terms that are vague, overloaded, or inconsistently used across the conversation — builds and stress-tests the project's domain vocabulary so the spec is written in precise, shared language.

engineering-standardsskills/engineering-standards/SKILL.md

Use when writing or reviewing any non-trivial code — naming, function design, error handling, testing, security, logging, and SOLID/DRY checks that apply regardless of language. Referenced by implement and review-code rather than invoked on its own.

finish-branchskills/finish-branch/SKILL.md

Use when implementation is complete and review-code has returned READY — decides how the work gets integrated (merge, PR, rebase) and confirms nothing is left uncommitted or unverified before doing so.

grill-meskills/grill-me/SKILL.md

Use when a plan, spec, or design decision feels shaky and needs to be pressure-tested before committing to it — a relentless interview that keeps pushing until every branch of the decision is resolved, not just the happy path.

handoffskills/handoff/SKILL.md

Use when a conversation or session needs to end but the work isn't finished — compacts the current state into a handoff document another agent or session can pick up from without re-deriving everything.

implementskills/implement/SKILL.md

Use when writing the actual code for a plan step, feature, or bugfix — turns a plan (or an ad-hoc change) into committed, verified code.

plan-from-specskills/plan-from-spec/SKILL.md

Use when a spec or set of requirements exists and needs to become an ordered, executable implementation plan before any code is written — turns a spec's goals and success criteria into sequenced steps with named files and per-step verification.

resolve-merge-conflictsskills/resolve-merge-conflicts/SKILL.md

Use when a git merge or rebase produces conflicts — resolves each hunk by tracing what each side actually intended, not by mechanically picking one side or pasting both.

review-codeskills/review-code/SKILL.md

Use when about to commit, push, or open a PR for any non-trivial change — the last gate that checks the change against its spec and the engineering standards before it ships.

spec-from-ideaskills/spec-from-idea/SKILL.md

Use when starting any non-trivial feature, subsystem, or design change before writing code, or when requirements exist only in conversation with nothing written down — turns an idea into a spec with measurable success criteria that downstream implementation and review can be checked against.

test-driven-developmentskills/test-driven-development/SKILL.md

Use when implement or debug-systematically reaches a code seam that needs a test written before the implementation — the test-first sub-routine those skills drive, not a standalone entry point.

triage-issuesskills/triage-issues/SKILL.md

Use when grooming a backlog of issues, bugs, or requests and deciding what's next — moves items through a tracker-agnostic state machine instead of an ad-hoc priority argument.

writing-for-agentsskills/writing-for-agents/SKILL.md

Use when writing or editing a SKILL.md, CLAUDE.md, or any other document an agent will read and act on — governs how this repo's own skills, and any project's agent-facing docs, are written so they get followed correctly.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "spec-driven-engineering",
  "description": "Spec/design-driven engineering workflow: spec -> plan -> implement -> review -> finish, with supporting standards, architecture, and debugging disciplines",
  "version": "1.0.1",
  "author": {
    "name": "Girijesh",
    "email": "[email protected]",
    "url": "https://github.com/girijesh-ai"
  },
  "license": "MIT",
  "keywords": [
    "skills",
    "spec-driven-development",
    "design",
    "tdd",
    "code-review",
    "architecture",
    "workflows"
  ]
}

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

[spec-driven-engineering on Agent Plugins Marketplace](https://pluginsmp.com/plugins/spec-driven-engineering)