claude

sdd

Spec-Driven Development framework for Claude Code — canonical SDD flow (spec → clarify → plan → tasks → implement → review), TDD enforcement with contract-first UI, blocking hooks, and orchestration of your existing specialist sub-agents.

0 on GitHubby Szum Tech Teamv0.10.0MITupdated 2 days ago
/

Plugin sdd from marketplace spec-driven-development in JanSzewczyk/spec-driven-development. Commands read from the repo's manifest — 2 days ago.

What it installs

Skills (1)

  • doctor

    Preflight audit and setup of project readiness for the SDD framework. Runs 10 checks (specs/constitution.md, specs/template.md, plugin installed + enabled across user/project/local settings, capabilities.md, hooks, git, gh, tooling, specialist agents, projects — single app, monorepo or several repos

Slash commands (9)

  • /sdd:analyze

    Find conflicts between spec ↔ plan ↔ tasks ↔ code (SDD diagnostic tool)

  • /sdd:clarify

    AI asks gap questions about the current spec (SDD step 2)

  • /sdd:constitution

    Edit the project constitution at specs/constitution.md (full long-form rules with rationale)

  • /sdd:doctor

    Audit project SDD readiness (or init). Wrapper over the doctor skill.

  • /sdd:implement

    Implement a whole Story wave by wave — unblocked tasks run in parallel on their specialist agents, each with its own TDD loop (SDD step 5)

  • /sdd:plan

    Generate architectural plan from spec (SDD step 3) — run in Plan Mode!

  • /sdd:review

    Final audit before PR — runs spec-guard + drift-detector + ui-critic + reviewer (SDD step 6)

  • /sdd:spec

    Create a feature spec, branch, and skeleton files (SDD step 1)

  • /sdd:tasks

    Decompose plan into tagged, auto-routed tasks with dependencies and parallel waves (SDD step 4)

Subagents (4)

  • drift-detector

    Detects drift between the documentation (spec.md, plan.md, tasks.md) and the current code state. Invoked by /sdd:review and /analyze. Returns a list of concrete conflicts with file paths and line numbers.

  • reviewer

    Final quality audit before PR. Receives the test results and the spec-guard / drift-detector / ui-critic results from /sdd:review, runs the domain audit skills relevant to the diff, writes review.md and returns verdict READY/NOT READY + action list. Invoked by /sdd:review.

  • spec-guard

    Verifies whether a code diff satisfies ALL Acceptance criteria from spec.md and does NOT introduce out-of-scope changes. Invoked by /sdd:implement (once per Story, or per task in single-task mode) and /sdd:review (full feature). Returns JSON {satisfied, missing, out_of_scope}.

  • ui-critic

    Visual review of UI components — captures screenshots via browser MCP and evaluates visual quality, design-system adherence, layout regressions, and rendering issues. Invoked by /sdd:review when the diff contains UI files (.tsx components, .stories.tsx). Requires a browser MCP server (e.g. Claude_in

View source on GitHub

More from JanSzewczyk/spec-driven-development

All 2 plugins →

sdd-board

claude

Side panel for Claude Code Desktop that shows where each SDD feature stands: current spec with its pipeline phase, next command and tasks, plus an overview of all specs.

0

Similar plugins

mattpocock-skills

claude

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

agentic-qe-fleet

claude

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Maintain sdd?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins