Product & Planning

andreaserradev-gbj Bundle

Generate a concise, scannable alignment report (tables + bullets) comparing a feature's PRD against the actual implementation. Spawns a fresh reporter subagent that explores the codebase and reports deviations, future-affecting constraints, and untested areas — then offers to apply the doc corrections it surfaces back to the PRD/checkpoint. Use when implementation is finished (or nearly), before final testing.

andreaserradev-gbj Bundle

Save progress and generate a continuation prompt. Updates PRD status markers, captures git state, and writes checkpoint.md for the next session. Use at the end of a session or before switching context.

anh-chu Bundle

Persistent PM knowledge base, competitive intel, customer notes, strategy, roadmap, AI market. Markdown wiki with entities, concepts, comparisons. Ingest sources, query, update with diffs, lint. Fires on "remember that / note that / don't forget / what do we know about X / what am I missing / blind spots".

anh-chu Bundle

Generate PRDs, user stories, and release notes grounded in wiki knowledge. Reads entities, concepts, decisions, and customer pages as source material.

ankit4479 Skill

Project discovery for the Outbound Builder Plugin. Analyzes an existing project or interviews the user to understand which technology domains are relevant, then maps available knowledge and suggests a build roadmap.

apache Bundle

Implements and reviews dubbo-admin resource storage and indexing changes. Use when the user asks about ResourceStore APIs, store routing, memory store behavior, index registration, IndexCondition, ListByIndexes, PageListByIndexes, ByMeshIndex, radix-tree prefix lookup, or pkg/core/store/, pkg/core/store/index/, and pkg/store/. Do not use for frontend, Console API, discovery, or engine tasks unless they require store or index changes.

apache Bundle

Routes dubbo-admin architecture questions to the right domain skill. Use for cross-module questions, end-to-end flows, subsystem boundaries, or deciding whether runtime, discovery, engine, events, store, Console API, or frontend guidance applies. Prefer a narrower dubbo-admin-* skill when the request clearly targets one subsystem.

apache Bundle

Implements and reviews dubbo-admin resource engine changes. Use when the user asks about runtime infrastructure discovery, engine factories, Kubernetes or mock engine ListWatchers, RuntimeInstance informers, RuntimeInstanceEventSubscriber, engine leader election, or merging RuntimeInstance data into Instance resources under pkg/core/engine/ and pkg/engine/. Do not use for registry discovery unless the task concerns engine-sourced RuntimeInstance resources.

apache Bundle

Implements and reviews dubbo-admin runtime component changes. Use when the user asks about component abstraction, component composition, runtime bootstrap, dependency ordering, registration, lifecycle, startup, shutdown, runtime builder behavior, or pkg/core/runtime/ and pkg/core/bootstrap/. Do not use for discovery, engine, store, Console API, or frontend tasks unless component lifecycle or dependencies are affected.

apache Bundle

Implements and reviews dubbo-admin registry discovery changes. Use when the user asks about Zookeeper or Nacos discovery, ListAndWatch, informers, discovery factories, discovery subscribers, ServiceProviderMetadata or ServiceConsumerMetadata processing, or Application, Service, RPCInstance, and Instance derivation under pkg/core/discovery/ and pkg/core/controller/. Do not use for engine-sourced RuntimeInstance behavior.

apache Bundle

Implements and reviews dubbo-admin Console API changes. Use when the user asks about HTTP endpoints, Gin routes, handlers, request or response models, console services, error handling, API pagination, or the handler to service to manager to store flow under pkg/console/. Do not use for frontend-only, discovery-only, or store-internals tasks unless they affect Console API behavior.

kubesense-ai Bundle

The KubeSense MCP tool layer — connection and auth, the full 29-tool inventory, tool selection, the discovery-first rule, the catalog-label field contract shared by every logs/traces query, WHERE syntax, multi-datasource formula queries, and how to read the TSV/columnar output formats. Read this when a tool returns a field-name or WHERE error.

kubesense-ai Bundle

Query Kubernetes, infrastructure and cloud-provider metrics from KubeSense with PromQL/MetricsQL — metric discovery, label inspection, the metric families KubeSense actually collects (kube-state-metrics, cAdvisor, node-exporter, OTel hostmetrics, DCGM GPU, JVM, and AWS/GCP/Azure/MongoDB Atlas/Confluent/Kong cloud resources), and the label conventions (clusterId, kubesense_cloud_resource_metric) needed to write a query that returns data.

l3wi Bundle

Entry point for feature planning workflow. Guides users through PRD creation, spec generation, and swarm design with automatic context management.

liangdabiao Bundle

Universal AI-powered web scraper for any platform. Scrape data from Instagram, Facebook, TikTok, YouTube, Google Maps, Google Search, Google Trends, Booking.com, and TripAdvisor. Use for lead generation, brand monitoring, competitor analysis, influencer discovery, trend research, content analytics, audience analysis, or any data extraction task.

lsnackerman Skill

Build topic reserves by searching your entire system, or run discovery mode to find what connects across territories. Use when consolidating scattered knowledge on a topic, before writing/sharing, or when curiosity has no specific target.

luxonis Bundle

Bootstrap this folder as a Luxonis agent workspace (AGENTS.md, oakctl, udev/host env, project venv/DepthAI v3, CLAUDE.md, docs/glossary.md). Use when AGENTS.md is missing, oakctl is not installed, host udev/env is unready, the project cannot import DepthAI v3, CLAUDE.md needs @AGENTS.md, or docs/glossary.md is missing. Do not use for camera discovery, proving a stream, building an app, product questions, or which camera to buy.

luxonis Bundle

Get Luxonis OAK hardware working for development and write setup notes. Use for first setup, USB/PoE, oakctl or DepthAI discovery, or a camera that is not found.

maquina-app Bundle

Manages workspaces and memories in the Recuerd0 platform via the recuerd0 CLI. Use PROACTIVELY after architectural decisions, debugging sessions that resolved an issue, when the user states a strong preference, when a non-obvious discovery is made, or at the natural end of a focused working session. Also handles explicit save, search, version, and organize requests.

matheusjesuspecege Skill

Cria as subtarefas da US que está no Azure DevOps para cada use case da feature. Use quando estiver com o plano de implantação pronto para desenvolver para manter backlog alinhado com o andamento da implementação.

matheusjesuspecege Skill

Conecta ao backlog do produto que está no Azure DevOps, permitindo que o desenvolvedor automatize processos, crie de tarefas, leia o prd das US, e obtenha informações do backlog do produto. Use quando estiver na etapa de research e está refinando o entendimento da US com o Product Owner ou durante o desenvolvimento para obter insights.

melodic-software Bundle

Validate a Codex plugin package or repo marketplace for manifest, catalog, skill, context-discovery, architecture, path, and portability defects. Use when reviewing, testing, publishing, migrating, or troubleshooting `.codex-plugin/plugin.json` or `.agents/plugins/marketplace.json` content.

mercedesperezcapilla-gif Bundle

Helps professionals identify practical AI automation Quick Wins through guided discovery, workflow analysis, role-based suggestions and industry-specific patterns. Designed for people who do not know where to start with AI automation. Returns prioritised opportunities, implementation guidance and governance signals.

rubenflamshepherd Skill

Find, inspect, recover, identify, or resume earlier coding-agent sessions across Claude Code, Codex, and Pi histories. Use whenever the user asks to locate previous work or continue an earlier agent conversation, regardless of the currently running harness.

saurabhships Skill

Extract structured, tagged insights from a customer call transcript — pain points, feature asks, objections, buying signals, and action items — ready to route to a backlog or share with a team. Use whenever a call transcript, meeting recording, or customer conversation needs to become a shareable summary rather than sit as raw notes, especially for sales calls, customer success check-ins, user research interviews, or support escalations.

saurabhships Skill

Draft a Product Requirements Document (PRD) that translates an established business need into a buildable spec — user stories, functional and non-functional requirements, scope, and testable acceptance criteria — for engineering, design, and QA. Use once a business case exists (via a BRD or other evidence) and it's time to define exactly what gets built.

saurabhships Skill

Draft a Business Requirements Document (BRD) that captures the business problem, measurable objectives, scope, stakeholders, and success criteria for an initiative, before any solution is defined. Use when a leadership team, business sponsor, or cross-functional stakeholder group needs alignment on why an initiative should happen and what business outcome it's meant to produce — typically the step before a PRD gets written.

savvides Skill

Draft a JTBD-native product brief from Job Map data. Accepts a Job Map YAML file (.jtbd/jobs/*.yml). Outputs to .jtbd/briefs/. Use when: "product brief", "jtbd brief", "write prd".

blockchainhb Skill

Use this skill when the user wants to research Amazon FBA products, evaluate a niche or keyword for viability, find product opportunities, or validate whether a product idea meets launch criteria. Covers market analysis, competitor assessment, profitability estimation, keyword validation, and the "rabbit hole" discovery strategy. Powered by the LegacyX FBA methodology and LaunchFast MCP tools.

bytelandtechnology Bundle

P0 phase skill for Headless Ghidra intake. Use when a target binary/archive needs identity confirmation, workspace initialization, Ghidra discovery, binary inspection, or analysis scope setup before any Ghidra analysis runs.

bytelandtechnology Bundle

P3 phase skill for Headless Ghidra metadata discovery. Use after P2, or after a P4 batch exposes missing context, to enrich function names, signatures, types, constants, strings, and hotpath metadata in YAML before serialized CLI apply.

horizonrobotics Bundle

Guided feature development with codebase understanding and architecture focus. Use when implementing a non-trivial feature that benefits from structured discovery, exploration, architecture comparison, implementation, and review.

hypertopos Bundle

End-to-end sphere design and construction — from data discovery through pattern strategy, YAML generation, build, calibration, and iterative tuning. Use when user asks to "design a sphere", "build a sphere", "create a sphere from my data", "optimize my sphere", "set up hypertopos", "generate sphere.yaml", "import my data into GDS", "what patterns should I build", "why is my recall low", "too many false positives", "how to split dimensions", "which dimensions should I use", "my anomaly rate is wrong", "review my sphere design", or "what's wrong with my detection". Covers both conceptual design (WHAT) and materialization (HOW).

ibrahim-3d Skill

Select, scaffold, or integrate Model Context Protocol (MCP) servers with a Claude Code plugin. Use when the user asks to "add an MCP", "which MCP for X", "connect to [service]", "find a server for [API/tool]", "wrap [tool] as an MCP", ".mcp.json", "MCP server config", or when a domain needs external tools Claude doesn't have (Blender, Figma, ClickUp, arxiv, a CAD program, etc.). Covers MCP discovery via registry, config schema, env/userConfig wiring, and fallback to CLI when no MCP exists.

janrummel Skill

Adversarial stress-testing of ideas, plans, decisions, and strategies. Finds weak points, simulates stakeholder objections, surfaces hidden assumptions, and runs pre-mortems. Use when the user says 'challenge', 'stress-test', 'red team', 'objections', 'counter-arguments', 'what could go wrong', 'weaknesses', 'devil's advocate', 'blind spots', 'find holes', or wants to pressure-test thinking before committing.

javimosch Skill

Using machin-mcp as a tool server from any MCP-compatible client (Claude Code, Claude Desktop) or directly via bash from pi or other agents. Covers registration, tool discovery, and direct protocol calls.