pm-execution
claude执行交付：PRD 撰写（8 段式）、用户故事/Job Stories/WWA、OKR 制定、成果导向路线图、Sprint 规划与回顾、事前验尸、红队挑战、干系人地图、测试场景、发布说明、会议纪要、模拟数据生成。
16 skills · 11 commands
0
claude
pm-ai-shipping
AI 交付审计：为 AI 构建（vibe-coded）的应用生成评审就绪的交付包——逆向文档化、安全审计（静态）、性能审计（静态）、测试覆盖地图、意图与实现差异检测。
/
Plugin pm-ai-shipping from marketplace skill-arsenal-ultra in Choi-Keith/skill-arsenal-ultra. Commands read from the repo's manifest — 1 month ago.
What it installs
Skills (2)
intended-vs-implemented用于发现“系统应该做什么”与“代码实际做了什么”之间差距的方法——这类 bug 是通用扫描器漏掉的,因为它们没有意图模型。定义什么算记录在案的意图、什么算实现证据、哪些不一致才真正要紧,以及如何避免空泛的发现。用于审计 AI 构建的代码、对照记录在案的权限评审访问控制,或检查代码库是否与自身文档一致时。
shipping-artifacts让 AI 构建(vibe-coded)的应用在发布前可以被评审的持久化文档集。每个应用都需要的核心文档——架构、用户/权限流程、权限、变量/密钥、测试覆盖地图——再加上仅在适用时添加的条件文档:邮件、定时任务、SEO、内嵌 agent/自动化。定义每份文档必须捕获的内容,以及评审者或审计者如何使用它。用于为代码库编写交接文档、梳理用户旅程与信任边界跨越、规划测试覆盖,或准备安全/性能审计时。
Slash commands (5)
/pm-ai-shipping:derive-tests把记录在案的意图变成测试覆盖地图——盘点当前已存在的测试、从系统文档推导用例、区分现有覆盖与提议的测试和未验证的缺口、为每条标注 单元 / 受控实时 / 人工,并推荐“绿了才能合并”的 CI 关卡
/pm-ai-shipping:document-app把 AI 构建的代码库逆向为评审者和审计者所需的系统文档——核心集(架构、流程、权限、变量)加上适用时的条件文档(邮件、cron、SEO、自动化)
/pm-ai-shipping:performance-audit-static对 AI 构建的代码做静态性能审计——发现 N+1 查询和请求瀑布、过度取数、缺失索引和缓存机会,按工作量和影响排序
/pm-ai-shipping:security-audit-static对 AI 构建的代码做静态安全审计——绘制信任边界、对照记录在案的意图、对每个发现自我反驳,只上报有证据支撑的风险
/pm-ai-shipping:ship-check把 vibe-coded 仓库变成评审者可直接签收的交付包——为应用补文档、接好 agent 上下文、运行安全与性能审计、绘制测试覆盖地图,并汇总结果
More from Choi-Keith/skill-arsenal-ultra
All 18 plugins →pm-product-discovery
claude产品发现：用户访谈脚本与纪要、完整发现流程、头脑风暴创意（PM/设计师/工程师三视角）、假设识别与优先级排序、功能请求分诊、OST 机会解决方案树、指标看板设计。
13 skills · 5 commands
0
pm-product-strategy
claude产品战略：愿景声明、9 段式战略画布、JTBD 价值主张、精益画布、商业模型画布、创业画布、SWOT、PESTLE、安索夫矩阵、波特五力、定价策略、变现策略。
12 skills · 5 commands
0
finance-research
claude投资研究：四大师综合分析框架（巴菲特/芒格/段永平/李录）、四角色并行投研团队、行业产业链全景研究、管理层纵深评估（买股票就是买人）、未上市公司 6 Agent 拼图式研究、收益型投资分析、段永平问答、财务数据交叉验证规范。
8 skills · 8 commands
0
pm-market-research
claude市场研究：用户画像、用户细分、市场细分、市场规模估算（TAM/SAM/SOM）、竞品分析、客户旅程地图、用户反馈情感分析。
7 skills · 3 commands
0
pm-go-to-market
claudeGTM 与发布：GTM 战略、滩头细分市场选择、ICP 理想客户画像、增长回路/飞轮设计、GTM 动作选择（集客/外呼/PLG 等 7 种）、竞争对战卡。
6 skills · 3 commands
0
Similar plugins
Pendo Analytics
claudeBring Pendo product analytics into Claude: account health, feature adoption, session replay lookup and triage, feedback analysis, and data-informed planning grounded in real usage data. Requires the Pendo connector and a Pendo subscription.
6 skills · 2 MCP servers
anthropics/knowledge-work-plugins 35,601
45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.
48 skills · hooks
alirezarezvani/claude-skills 29,725
pm-execution
claudeExecution and product management skills: PRDs, OKRs, roadmaps, sprints, pre-mortems, stakeholder maps, user stories, prioritization frameworks, live Q&A and polls, and more.
18 skills · 11 commands
phuryn/pm-skills 27,939
voltagent-biz
claudeProduct, legal, and business specialists - product strategy, licensing, project management, UX research
VoltAgent/awesome-claude-code-subagents 26,513
autoresearch
claudecodexAutonomous improvement engine. 14 commands with bounded defaults, chain handoff, and adaptive evals checkpoints. 95% token reduction via modular architecture.
1 skill · 14 commands · hooks
uditgoenka/autoresearch 6,833
backlogd
claudeTurn Claude Code into a problem-driven scrum team. You file problems as Linear issues; an agent team runs the empirical Scrum loop (scope, solve, review, adapt) and owns the solutions. An independent reviewer gates every increment against its acceptance criteria, the Definition of Done, and a standards corpus. Runs on your Claude subscription via the official Linear MCP over OAuth — no API keys.
8 skills · 7 commands · 4 agents · 1 MCP server · hooks
davepoon/buildwithclaude 3,741
Maintain pm-ai-shipping?
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 plugins18 plugins