Product & Planning

suraj787 Skill

Use when a pattern and interaction objective are fixed and you need to enumerate candidate effects from the approved offline registry that could realise that pattern.

ailearneryang Bundle

Generate, revise, 补全, 重写 or收口 architecture documents from PRD,需求文档,需求规格说明书,requirements/requirements_spec.md or feature specs. Use for 输出 design/architecture.md, and when requested also design/api_design.md and design/data_model.md, with API 边界, 模块划分, 数据流, 状态流, 技术选型, 安全设计 and 可观测性设计 for backend, platform, Android, IVI and cockpit projects.

ailearneryang Bundle

Generate, revise, 补全 or重写 car middleware, cockpit middleware, IVI middleware architecture from PRD,需求文档,requirements/requirements_spec.md or feature specs. Use for Linux/QNX/Android cross-OS 架构设计, 中间件分层, 服务拓扑, 通信矩阵, 资源预算, 诊断, 安全 and design/architecture.md.

beeltec Skill

Execute one user-declared small task — a tiny change or a deployment — directly, skipping the backlog/implement flow. User-invoked only; not for backlog work items or multi-file features — use `implement`.

beeltec Bundle

Plan one coordinated outcome end-to-end into a ready Epic under one standing approval. Use when asked to plan an Epic; not for standalone items — use to-backlog.

beeltec Skill

Publish the conversation's confirmed durable knowledge to the wiki under one standing approval, including ADRs for decisions already in force. Not for unimplemented proposals — use to-backlog.

beeltec Bundle

Manage approved desired work from intake through refinement, ranking, execution state, cancellation, and archival. Use when creating or changing Epics, Stories, Tasks, or Bugs in docs/backlog.

beeltec Bundle

Research a proposed backlog record before readiness, attaching version and standards evidence to it. Only on explicit request for identified proposed work; never for general questions or wiki guidance.

beeltec Skill

Intake the conversation's confirmed standalone work items and refine each to ready under one standing approval. Not for coordinated multi-item outcomes — use to-epic.

beeltec Bundle

Run the whole delivery flow unattended from a PRD or plan to accepted primary-branch state, answering every owner gate as owner-proxy. Not for interactive shaping (use $discuss) or planning one outcome (use $to-epic).

beeltec Bundle

Execute one ready backlog work item or Epic serially on its sole acceptance branch through claim, implementation, review, acceptance, and archival. Use with an explicit WORK-NNN, EPIC-NNN, backlog path, or unambiguous conversational selection.

beeltec Bundle

Review changes since a fixed point on Standards and Spec axes with risk-tiered agents. Use for backlog-backed branches, PRs, work in progress, or Epic closure.

beeltec Bundle

Initialize or safely upgrade a project's wiki, backlog, validation, and agent instructions; back-fill a foundation wiki on brownfield repositories. Use when creating or upgrading project governance.

carapace-sh Bundle

Use when working with the Epic Games Lore version control system — a centralized VCS designed for game development with binary-first content-addressed storage. Covers architecture, core concepts, server deployment, CLI and server configuration, workflows, and the full command reference. Triggers on: "lore", "Lore", "Epic Games Lore", "loreserver", "version control system", "VCS", "content-addressed", "immutable store", "mutable store", "BLAKE3", "Merkle tree", "FastCDC", "fragment", "partition", "content-defined chunking", "split-write", "shared store", "revision", "branch", "merge", "cherry-pick", "revert", "bisect", "layer", "link", "lock", "staging", "dirty", "obliterate", "packfile", "LoreError", "config.toml", "cli.toml", "lore://", "Lore server", "Lore CLI", "Lore configuration", "Lore FAQ", "Lore roadmap", "Lore system design".

carapace-sh Bundle

Use when working with the kubeadm CLI — bootstrapping Kubernetes clusters, init/join/reset/upgrade workflows, the phase system, certificate management, bootstrap tokens, kubeconfig generation, and the v1beta4 configuration API. Triggers on: "kubeadm", "kubeadm init", "kubeadm join", "kubeadm reset", "kubeadm upgrade", "kubeadm config", "kubeadm token", "kubeadm certs", "kubeadm kubeconfig", "kubeadm version", "kubeadm alpha", "bootstrap token", "InitConfiguration", "ClusterConfiguration", "JoinConfiguration", "ResetConfiguration", "NodeRegistrationOptions", "control-plane-endpoint", "discovery-token", "certificate-key", "feature-gates", "skip-phases", "static pod manifest", "TLS bootstrap", "kubeadm-config".

danielrosehill Bundle

Use when the user wants to browse, discover, or install third-party Claude Code agent skills focused on Israel (tax/accounting, government services, healthcare pharmacies, rail, cinema, post tracking, legal research, security compliance, communication, etc.) — skills authored by people other than Daniel, indexed here for easy installation alongside this plugin. Reads a curated list from `data/third-party-skills.yaml` (monorepo skill collections from github.com/skills-il plus standalone skill repos), shows each entry with its source repo / subpath / blurb, confirms the user's selection, and installs the chosen skill(s) into `~/.claude/skills/<name>/` via `git clone` or sparse-checkout. Does not install anything without explicit confirmation. Also surfaces the awesome-list reference (alexpolonsky/awesome-agent-skills-israel) for broader discovery. Trigger phrases - "what other israel skills are there", "install israeli agent skills", "find me a skill for [israel rail / clalit / maccabi pharmacy / cinema / israe

donald-ada Skill

Put the backlog's own rules to the backlog — seeds that should no longer be there, pairs that are one discovery, seeds that outgrew a line, and the order nobody has stated. Judged one at a time, landed only by the user's call.

donald-ada Skill

How the flow's records are written — every document under .genius/, snapshot to backlog line. Use when writing or rewriting any of them, or when another skill needs the prose discipline.

fattain-naime Bundle

Create a project delivery plan covering scope, milestones, timeline, work breakdown, resourcing, stakeholder roles (RACI), dependencies, budget, quality gates, and a project-level risk register. Use at the start of any project to define who is building what, in what order, by when - before any code is written.

fattain-naime Bundle

Create a phased implementation roadmap that sequences the technical build of an entire project - build order, module dependencies, environment/tooling setup, per-phase Definition of Ready/Done, and integration checkpoints. Use after the project plan and architecture exist, to turn "what we're building and when" into "in what technical order we actually build it."

fattain-naime Bundle

Write a technical specification (SRS/TSD) that captures stakeholder needs, system requirements, functional behavior, non-functional constraints, and acceptance criteria. Use when starting any significant engineering initiative.

goldenprofile Bundle

Проектный документ в файл, три режима: spec (проблема, цели, архитектура, ADR-решения, риски), plan (фазы, оценки, зависимости) и brief (записка для руководства без кода и терминов). Используй когда пользователь просит «составь план для реализации пунктов из ROADMAP», «разложи это в SPEC/PLAN», «напиши спеку», «tech spec», «design doc», «запроектируй фичу», «аналитическая записка». Только документ, ничего не исполняет: нарезать на агентские куски — agent-workflow (режим decompose); документация по существующему коду — docs-generator; пакет от виртуальной команды по сырому входу — sage.

hiboys Bundle

面向A股市场热点发现的综合能力。适用于用户提出“今日热点是什么”“当前热股有哪些”等泛化问题时，返回结构化的Markdown热点报告。覆盖热点资讯、热门股票等维度。触发核心条件：用户关注市场层面的热门方向或事件热度，而非单一标的的深度诊断或指标计算。

johnoconnor0 Bundle

Use to produce a practical product requirements document with functional and non-functional requirements, user stories, acceptance criteria, assumptions, dependencies, success metrics, and release criteria.

johnoconnor0 Bundle

Use to design the database schema after the PRD, technical design document, and architecture plan are agreed. Produces a durable schema file plus a generated JSON model, ERD, and migrations that later backend work reads back. Works on PostgreSQL, MySQL, SQLite, SQL Server and MongoDB. Use for entities, relationships, ownership, sensitive data, retention, indexes, access control, and migration risk.

johnoconnor0 Bundle

Use when the user asks to review everything outstanding, work through the backlog, pick up all open tickets, sweep the queue, see what needs doing, or parallelise the current workload. Pulls open items from the configured tracker, clusters them into workstreams, and fans out one read-only analysis agent per workstream.

johnoconnor0 Bundle

Use to turn a product idea, problem, or vague initiative into a clear discovery brief with users, goals, risks, assumptions, and MVP boundary.

joshukraine Bundle

Render a PRD Markdown file as a rich, self-contained HTML reading view (Dashboard style) and open it in the browser. The Markdown stays authoritative; the HTML is a derived, ephemeral presentation.

joshukraine Skill

Create a pull request with auto-generated description, issue linking, ROADMAP updates, and PR-metadata validation.

ratacat Bundle

Price-blind deep research for a Polymarket/prediction-market event or PMKNB situation — fresh or updated analysis, resolution mechanics, mechanism-only briefs, source discovery, 0-100 likelihood independent of market odds.

researai Bundle

Use when a quest needs problem framing, literature scouting, dataset or metric clarification, or baseline discovery before deeper work.

rome-os Skill

Route browser automation tasks to specialized Rome apps first, then use OpenCLI help discovery when no specialized Rome app is available.

makgunay Bundle

Guided app discovery, PRD generation, and architectural design for native macOS/iOS applications. Takes the user from a rough app idea through an interactive exploration of features, user experience, and design vision, then produces three deliverables: (1) a comprehensive PRD with functional requirements, user stories, and success metrics, (2) a technical architecture document with data models, system diagrams, and component design, (3) a feature list for non-technical stakeholders. Use when user says things like 'I have an app idea', 'help me plan an app', 'write a PRD', 'design the architecture for', 'what should my app do', 'help me think through features', or 'I want to build an app that...'. Also use when user has an existing PRD draft and wants to expand, validate, or restructure it. Guides through iterative discovery before producing documents — never jumps straight to writing.

makgunay Bundle

Validates and recommends technology stacks for native macOS/iOS app projects against PRD and architecture requirements. Reads the PRD and architecture documents (or gathers requirements interactively), then systematically checks every technology choice for: OS version availability, framework capability gaps, performance feasibility, distribution compatibility (sandbox vs direct), API deprecation risks, dependency conflicts, and timeline realism for the team size. Produces a structured validation report with go/no-go verdicts, risk flags, and alternative recommendations. Use when user says things like 'validate my tech stack', 'check if this architecture works', 'what should I build this with', 'is SwiftData the right choice', 'can I ship this on the App Store', 'review my architecture', or before starting implementation of any PRD. Also use when migrating between tech stacks or evaluating whether to adopt a new framework.

marco-souza Skill

Write and maintain project documentation including READMEs, API docs, ADRs, CHANGELOGs, and inline code comments. Use when: the user asks to write documentation, update a README, create an API reference, draft an ADR, add a CHANGELOG entry, or improve inline comments. Do NOT use when: the user wants to format markdown (use markdown-format), review code (use pr-review), or create a PRD (use create-prd).

marco-souza Skill

Capture and organize learnings from coding experiences, debugging sessions, and problem-solving. Use when: the user wants to save a learning, document a discovery, record a pattern, or create a reference for future work. Do NOT use when: creating project documentation (use docs), writing PRDs (use create-prd), or when the user wants to read existing learnings without creating new ones.