By FlameMida
Guides developers through the entire development lifecycle: exploring ideas, writing specs, planning and executing tasks with TDD in isolated worktrees, visual review, multi-dimension acceptance testing, quick bug fixes, and real-time search.
Deep codebase analysis - trace execution paths, map architecture layers, understand design patterns and abstractions / 深度分析代码库,追踪执行路径,映射架构层次,理解设计模式和抽象
Code review - identify bugs, security vulnerabilities, code quality issues and convention violations / 代码审查,识别 bug、安全漏洞、代码质量问题和规范违反
External resource exploration - find best practices, standards, official docs and cases for requirement-analysis parallel and follow-up exploration; reports conclusions, evidence and sources / 外部资源探索 agent,负责查找外部最佳实践、标准、官方文档与案例,服务 requirement-analysis 的并行探索与回补探索,输出结论、证据和来源
All-round acceptance workflow - multi-dimension acceptance over the dimension x execution-nature matrix: unit/integration/API regression, E2E, visual regression, accessibility, performance (web CWV/Lighthouse, k6 load, client), plus AI autonomous acceptance and failure diagnosis. For acceptance-flavored requests (accept a feature/page/endpoint, E2E, load test, visual regression) or executing-plans wrap-up; also diagnoses page interaction, rendering, performance, Shadow DOM/iframe issues. Not for TDD red-green cycles, routine test runs, static code review, or doc review. / 全能验收工作流——按「验收维度 × 执行性质」矩阵对交付物做多维验收:单元/集成/API 回归、 E2E 端到端、视觉回归、可访问性、性能验收(前端 CWV/Lighthouse、后端 k6 压测、客户端), 外加 AI 自主验收与失败诊断。当用户要求"验收这个功能/页面/接口"、"E2E 测试"、 "acceptance test"、"性能测试/压测/能扛多少 QPS"、"视觉回归"、"界面/浏览器测试", 或 executing-plans 收尾按验收矩阵触发时使用;也用于诊断页面交互、渲染、性能、 Shadow DOM/iframe 问题。不适用于开发中的 TDD 红绿循环(用 test-driven-development)、 无验收语义的日常"跑一下测试/修测试"、代码静态审查、需求文档评审。
Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.
Execute implementation plans - when a written plan from writing-plans exists (plan/*-plan.md under the feature directory in .spec-dev/): the main thread executes task-by-task in an isolated worktree (TDD + per-task commits + spec self-check), then orchestrates multi-dimension adversarial code review and matrix-driven acceptance. Not for improvised changes without a written plan. / 执行实施计划——当已有 writing-plans 产出的实施计划(`.spec-dev/` 特性目录下 plan/ 子目录的 *-plan.md)、准备动手实现时使用。主线程在隔离 worktree 中逐任务执行(TDD + 每任务提交 + spec 自检),全部完成后编排多维对抗代码审查(code-reviewer 子代理不写码、仅分析与复跑验证),并按验收矩阵触发 acceptance-qa 验收,最终合并总结。不适用于没有书面计划的即兴改动。
Exploration mode (thinking partner) - for ideas not yet committed to delivery: read-only code walks, option comparison, diagram-driven reasoning; no code changes, no implementation artifacts, no forced conclusions; hands off to requirement-analysis once the idea crystallizes. Not for committed deliverables or single-fact lookups; for already-decided small fixes with no design space use quick-fix. / 探索模式(思考伙伴)——想法尚未定型、还没决定要不要做时使用。当用户表达"我在想要不要…""帮我想想/聊聊这个思路""A 和 B 哪个合适""为什么这里这么慢/乱""这个想法可行吗""先搞懂这块代码再说"等未承诺交付的请求时触发。只读代码、比较方案、画图梳理,不写代码、不建实施档案、不强制结论;想法结晶后交接 requirement-analysis。已明确要交付某功能时不适用(直接用 requirement-analysis);单点事实问答(如"这个函数在哪定义")也不适用;已决定要修的无设计空间小 bug/小调整用 quick-fix。
Lightweight bug-fix workflow - for fixes already decided on with no design space (small bugs, minor adjustments, post-plan tweaks): locate root cause with spec back-lookup, confirm one question at a time, fix under TDD, optional acceptance. Splits on contract impact to avoid spec drift; escalates to requirement-analysis on contract-crossing / cross-module / new-dependency signals. Not for new features or anything with design space (use requirement-analysis), nor for undecided ideas (use exploring). / 轻量 bug 修复工作流——已决定要修、无设计空间的小修复(小 bug、小调整、计划执行后的小问题)时使用:定位根因(含 spec 反查)、逐题校对、TDD 修复、可选验收。按契约影响分流以规避 spec 漂移;根因涉及跨 spec 契约/跨模块/新依赖时建议升级 requirement-analysis。不适用于新功能或任何有设计空间的需求(用 requirement-analysis),也不适用于尚未决定要不要做的想法(用 exploring)。
Requires secrets
Needs API keys or credentials to function
Uses power tools
Uses Bash, Write, or Edit tools
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 claimnpx claudepluginhub flamemida/spec-devBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
English | 简体中文
A design→plan→execute skill pipeline plugin: polish ideas into specs, break them into executable plans, and deliver with TDD discipline in isolated workspaces.
Design→Plan→Execute pipeline | Adversarial validation | Visual preview | All-round acceptance | MCP enhancements
exploring, a thinking partner: no-commitment exploration while an idea is unsettled — read-only, no code (HARD-GATE), opens side threads instead of interrogating, ASCII visualization, opt-in exploration notes under .spec-dev/explorations/; hands off to requirement-analysis once the idea crystallizes, and executing-plans can drop back into it when stuckrequirement-analysis, an 8-phase design workflow: triage (light / standard / deep tiers), parallel internal+external exploration (no subagent cap), one-question-at-a-time clarification, sequential-thinking adversarial validation + 2-3 option comparison, spec writing with double review (structured behavior requirements: Requirement + Scenario); a HARD-GATE guarantees zero implementation before the design is approvedvisual-preview, a browser companion: JIT-proposed during design conversations, renders mockups, wireframes and layout comparisons, and collects click-through choiceswriting-plans decomposes specs into bite-sized tasks executable with zero context: exact file paths, complete code, embedded 5-step TDD, consume/produce interface contracts, no placeholders allowedexecuting-plans: the main thread executes task-by-task (per-task commit + spec self-check), then wrap-up multi-dimension adversarial review (fan-out code-reviewer + contract validation + loop-until-dry + completeness critic), merge and summaryusing-git-worktrees (isolated workspaces, native tools first) and test-driven-development (no production code without a failing test) are standalone skills reusable from any workflowacceptance-qa runs acceptance over the dimension × execution-nature matrix: unit/integration/API, Playwright E2E, visual regression, accessibility, performance (web CWV / k6 for APIs / client), AI autonomous acceptance (mandatory evidence + serial recheck + verify-assertions-first) and failure diagnosisquick-fix, a fast path for already-decided fixes with no design space (small bugs, minor adjustments): root cause with spec back-lookup, one-question-at-a-time confirmation, TDD fix, optional acceptance; splits on contract impact to avoid spec drift and escalates to requirement-analysis on contract-crossing / cross-module / new-dependency signalsvalidate-output.mjs, with one retry on failureexploring (unsettled idea → optional .spec-dev/explorations/<topic>.md)
↓ crystallizes
requirement-analysis (design → .spec-dev/YYYY-MM-DD-<feature>/spec/<feature>-design.md)
↕ JIT
visual-preview
↓
writing-plans (plan → plan/<feature>-plan.md in the same feature dir)
↓
executing-plans (isolated execution + review + summary)
├── using-git-worktrees (isolated workspace)
├── test-driven-development (TDD discipline)
└── acceptance-qa (matrix-driven acceptance)
quick-fix (already-decided small fix, no design space) ── bypass fast path
root cause + spec back-lookup → one-question confirm → TDD fix → optional acceptance
↑ escalates to requirement-analysis on contract-crossing / cross-module / new-dependency signals
roadmap continuation (oversized goals) ── decomposition registered at .spec-dev/roadmaps/<project>.md ── outer loop
requirement-analysis registers sub-projects → each runs the full pipeline independently → executing-plans marks delivery and offers the next one
The three entry points split by commitment and design space: exploring (undecided — should we even do this?), quick-fix (decided, no design space — a small bug or adjustment), requirement-analysis (decided, has design space — a feature or change). quick-fix reuses test-driven-development and acceptance-qa, and hands control back to requirement-analysis the moment a fix turns out to need real design.
Specification-Driven Development with Process Discipline for Claude Code
Requirements-driven development workflow with quality gates for practical feature implementation
Spec-driven development pipeline for Claude Code: interview-to-spec, spec-approach, tdd, verify, diagnose, and a feature orchestrator.
Skills-first specification-driven development framework with 7 agent skills for planning, implementation, review, and shipping. Natural language activation with intelligent agent orchestration. Includes /plan, /implement, /research commands plus managing-specifications, implementing-features, and reviewing-and-shipping skills.
Spectacular skills/commands library for spec-anchored development and parallel task execution
Spec-Driven Development Workflow for Claude Code. A 6-step pipeline: Requirements → Code Analysis → Design → Implement → Verify → Self-Improve. Specifications are the source of truth, code is a verified artifact.