Product & Planning

ravsau Skill

Decide when to use Shorts vs long-form. Shorts = discovery ($0.01-0.06 RPM). Long-form = revenue ($1-30 RPM). Both = 3x subscriber growth. Use when planning content mix or considering Shorts.

steloit Skill

Refine backlog requirements through structured user interview. Turns rough task descriptions into concrete, actionable requirements with goal, scope, acceptance criteria, and edge cases.

strapi Skill

Expert guidance for integrating shadcn/ui components in this Next.js monorepo (apps/ui). Handles component discovery, installation via CLI, customization to local conventions (cn() in @/lib/styles, Tailwind v4, radix-ui primitives), and best practices. Use this skill whenever the user wants to add, install, customize, or troubleshoot a shadcn/ui component — even if they just say 'add a button' or 'install tabs'. Also triggers on: shadcn, radix, UI component, cn utility, component library.

strapi Bundle

Create a structured PRD (Product Requirements Document) as a JSON task file with prioritized stories for automated execution. Ralph is the project's task runner script that processes stories sequentially. Use this skill whenever the user wants to plan work, break down a feature into stories, create a task plan, or prepare a batch of component migrations. Triggers: create PRD, plan tasks, break down work, create stories, task planning, batch migration, ralph, plan component work.

superplanehq Skill

Implements and configures SuperPlane canvas consoles (markdown, node, table, board, chart, number, scorecard panels), widget data sources, CEL/templates, table row trigger actions, and console YAML. Use when editing console UI, panelTypes, useWidgetData, WidgetTable, WidgetBoard, canvas_console_yml, Get/UpdateCanvasConsole, or docs/prd/console-and-widgets.md.

nvidia Skill

Use when the user runs `/aicr-triage` or asks to triage, review, or clean up a GitHub org-level Projects v2 board (default NVIDIA AICR project 248). Reviews active non-Done issues, then promotes P2 issues to P1, demotes Ready items to Backlog, closes superseded issues, and classifies unclassified ones — applying only user-confirmed changes via `gh` CLI. Triggers on backlog hygiene before sprint planning or release prep, or when the user files a new issue and asks to classify it on the board.

opensearch-project Skill

Query OpenSearch Dashboards APIs for workspace configuration, index pattern discovery, APM correlation configs, and saved objects.

ortus-boxlang Skill

Use when working with BoxLang ORM entity mapping: entity discovery via MappingGenerator, EntityRecord construction, metadata inspection (IEntityMeta, ClassicEntityMeta, AbstractEntityMeta), HBM XML generation via HibernateXMLWriter, property metadata (IPropertyMeta, ClassicPropertyMeta), entity file scanning (.bx/.cfc), parallel processing thresholds, and save-mapping options.

rawgroundbeef Bundle

Create a PRD through user interview, codebase exploration, and module design, then output as a markdown file. Use when user wants to write a PRD, create a product requirements document, plan a new feature, or scope out work before implementation. Triggers on "write a prd", "create a prd", "let's plan this feature", "scope this out", "product requirements", or any request to formalize feature planning into a document.

rawgroundbeef Bundle

Vertical-slice planning pipeline that turns rough requirements into slice-local discovery, decisions, UAT, PRD, follow-ups, and a bootstrap prompt before implementation. Use when starting feature work, shaping a vertical slice, converting rough requirements into acceptance criteria, or preparing a fresh-context agent to implement from durable artifacts.

rca32 Bundle

Write a product requirements document from a brief, conversation, supplied artifacts, or existing software. Use for PRDs, product specs, and product-level reconstruction. Not for implementation or engineering task decomposition.

rshade Skill

Infer JSON structure and types with jq-based schema discovery.

rweisssieker-xp Skill

Apply bounded industry-specific ERP discovery questions without treating industry patterns as client facts.

kandil7 Bundle

PRD Analyzer Skill - Execution Prompt

mouchegmouradian Bundle

Keep PRD and RFC documents in sync with code changes made during a session. Trigger when: user says "sync the specs/PRD/RFCs", "update the docs", "reflect these changes in the docs", "the PRD is stale", "docs are out of date", or after implementing an RFC. Also trigger when a hook reminder fires after a git commit and PRD docs exist. Reads git diff to understand what changed, compares against existing docs, and makes targeted edits — not wholesale rewrites. Never rewrite sections unaffected by code changes.

mouchegmouradian Bundle

Build comprehensive product requirements documents (PRDs) and technical RFC specifications for software projects. Guides the user through structured discovery — from problem statement and user personas to technical architecture, data models, and implementation RFCs. Use this skill whenever the user wants to plan a new product, define requirements for a feature, create technical specs, write an RFC, break down a project into implementable pieces, or prepare documentation for AI-assisted coding (Claude Code, Cursor, etc.). Also use when the user says things like "help me spec this out", "let's plan this project", "write a PRD", "create an RFC", "break this into tasks", or "I need to define requirements for...".

muqian2026-rgb Bundle

PRD completeness gate before dev: boundary → module breakdown → 95% review checklist. Triggers on "PRD review", "review this PRD", "PRD gate", "acceptance criteria check".

mustafahasanain Bundle

Maintain FEATURE_CHANGELOG.md - the functional feature registry. Baseline discovery, duplicate/extension detection before planning, deterministic feature IDs, post-approval updates, and index validation.

niftymonkey Skill

Create a PRD through user interview, codebase exploration, and module design, saved as a local markdown file with optional GitHub issue submission. Works for new projects, features, or refactors. Use when user wants to write a PRD, create a product requirements document, plan a new feature, or spec out a new project.

niftymonkey Bundle

Sketch a new module, feature, or project's architecture using deep-module thinking before any code is written. Apply proactively any time you are proposing module structure, naming new boundaries, classifying dependencies, or designing interfaces for new functionality. Runs standalone for ad-hoc design, and composes with PRD and planning workflows (populating their architecture sections) when you use them.

xiaoweidotnet Bundle

从 PRD 文档或产品描述自动生成高保真移动端 App 原型 HTML 页面。Use when the user provides a PRD, product requirements doc, feature description, or app idea and wants to generate high-fidelity mobile app prototypes, create UI mockups, visualize product features as mobile screens, or build interactive HTML prototypes. Also triggers on "原型图", "高保真原型", "mockup", "app prototype", "UI 设计稿", "手机界面", "移动端原型", or when user pastes product requirements and asks for visual output. Covers the full pipeline — UX analysis, interface planning, UI design, HTML implementation with iPhone 15 Pro device frames.

yaojingang Bundle

Route GEO and generative engine optimization requests to an available GEOHub capability. Use for broad GEO requests, GEOHub workflow selection, capability checks, or requests spanning discovery, brand/site/page diagnosis, multi-page website diagnosis, content, strategy, knowledge, publishing, and measurement.

yaojingang Bundle

Discover evidence-aware GEO questions, query rewrites, intent clusters, and prioritized content opportunities from a structured brief. Use for AI search intent mining, question or keyword expansion, query research, FAQ discovery, 拓词, and GEO topic discovery in Chinese or English.

yaojingang Bundle

Build an offline GEO optimization plan from explicit goals, diagnosis actions, approved evidence IDs, and a measured baseline. Use for GEO strategy, roadmap, experiment planning, intervention candidates, 策略, 路线图, and 优化实验. Exclude autonomous publication, fabricated outcome evidence, and memory promotion without positive external measurement.

abtdomain Skill

Scan for typosquats and lookalike registrations around a brand, assess each domain individually, surface unconfirmed defensive candidates, and offer monitoring. Not for single-domain analysis (use domain-analyze), general discovery, or keyword trends.

aibjohnson Skill

Turn raw meeting notes or a transcript into a summary, decisions, action items with owners, and open questions. Use after a client call, a discovery call, or any meeting where notes were scribbled fast.

cavalry-collective Bundle

Build an interactive, drag-and-drop user story map so the user can re-slice work across release phases. Use when the user wants a story map, a phased roadmap, release slicing, a backbone/activities journey map, or to decide "which stories go in which phase" and move them around.

dom1ng0s Bundle

Audits an existing SaaS or multi-user web application codebase to find security/architecture gaps and missing product features, then produces a prioritized Markdown action plan to make it production-ready. Use this whenever the user wants to review, audit, or assess a codebase for scalability, multi-tenancy readiness, security holes, or "what's missing before launch" — even if they only mention one of those angles (e.g. just "check for security issues" or just "what features are we missing"), since the two are almost always linked in a SaaS context. Trigger on phrases like "review my SaaS codebase", "is this ready for production", "find gaps in my multi-user app", "audit this repo", "what am I missing before I launch", or requests to create a roadmap/action plan from an existing codebase.

emanueleminotto Bundle

Use this skill to turn an audit output into a prioritized improvement plan — executive summary, top blockers, a three-horizon roadmap, and action items. Trigger when the user pastes or already has an audit report (from the audit skill or a saved .minottobot/ snapshot) and asks "what should we do about this", "build us a plan", "what's our strategy", or similar. This skill expects an audit output as input — if the user hasn't run an audit yet, use the audit skill first, or use the minottobot skill for the two combined.

giving-back-studio Skill

Sharpens an Earth Care Network workspace's ideal customer profile into a specific, testable beachhead using disciplined-entrepreneurship framing. Use when someone wants to define, tighten, or re-target who they sell to, when lead quality is poor, or when discovery returns off-target companies.

giving-back-studio Skill

Create and save a grounded Earth Care Network journal strategy for an enterprise. Use when someone wants a content strategy, editorial pillars, topic roadmap, publishing cadence, or a journal that supports sales without generic promotion.

ezos26 Skill

Ralph 2.0 — Autonomous phased build system. Reads a PRD, generates scoped briefs, dispatches worker agents per phase, runs find→fix→verify gates between phases, checkpoints to disk for cross-session continuity. Usage: /ralph2 [prd-path]

ezos26 Skill

Ralph Dry Run — Simulate PRD implementation without writing code. 4 agents trace data flow, execution paths, system boundaries, and step completeness against the real codebase. Finds interpretation gaps between what the PRD says and what the code requires. Produces an amended PRD v2 ready for /ralph2 execution. Usage: /ralph-dry-run [prd-path]

gary-ash Bundle

Visualizes tasks as a Discovery Tree using Mermaid diagrams. Use when planning or tracking multi-step work with parent and child task relationships.

ipea Skill

Scaffold a new skill that follows this repo's conventions — interviews for purpose, trigger phrases, and tool needs, then writes `.claude/skills/<name>/SKILL.md` from the skill template with frontmatter and body that pass the integrity gates on first try. Use when user says "write a skill", "scaffold a skill", "create a new skill", "I keep doing X, make it a skill", "new slash command", or "turn this workflow into a skill". NOT for capturing a one-off session discovery — that is `/learn`.

maddada Bundle

Use this skill for anything involving Ghostex or the `ghostex`/`gx` CLI: projects and workspaces, terminal panes and sessions, agent orchestration (creating agent sessions, messaging agents, reading their output, queueing prompts, sleeping/waking/killing sessions), scheduled automations, the Kanban/Beads project board, quick actions, session chat and prompt queues, prompt history and previous-session search/resume/fork, server management, UI controls, logs, screenshots, and diagnostics. It teaches help-first command discovery, stable target selection, JSON inspection, safe execution, verification, and routing to Ghostex's more specialized skills.