Product & Planning

mrvladd-d Bundle

Optional Analysis before PRD: route vague ideas through facilitated brainstorming and a concise product brief without creating tasks.

mrvladd-d Bundle

Turn a PRD into a traceable Memory Bank with product, requirements, epics, and features.

mrvladd-d Bundle

Map an existing codebase into an as-is Memory Bank without inventing roadmap items.

adol1111 Bundle

Explicitly initialize or operate a repository-local Feature owner index only when no external tracker exists. Use for local actor identity, Feature ownership, owner-filtered target discovery, Feature lifecycle transitions, and generated Feature views without making local tracking a dependency of other skills.

adol1111 Bundle

Select or revise a shared Milestone as a frozen batch of owned Features from a requirement pool, and reconcile completed Features into a concise global history. Use for backlog scoring, shared iteration or release scope, Feature ownership, cross-Feature dependencies, exit coverage, completion indexing, or explicit Milestone replanning; never decompose Feature Tasks or drive implementation.

akashp1712 Bundle

Gives Claude Code durable project memory so the developer stops re-teaching the repository. This skill should be used when the user asks to remember a project decision, rejected approach, architectural constraint, debugging discovery, undocumented repo behaviour, or open loop; when they ask what was previously decided, "use OneCue", "project memory", or "don't forget this"; and when later work might repeat a past constraint. Do not use for personal notes, cross-AI memory, chat transcripts, or routine chatter. Unsolicited recall returns at most one cue. Silence is a successful result.

akashp1712 Bundle

Scaffold and implement agent-readiness / AEO for Next.js App Router marketing sites — llms.txt, markdown twins, robots policy, discovery catalogs, optional OpenAPI/MCP/OAuth modules. Use for orank/ora.ai gaps, ChatGPT/Perplexity citations, llms.txt, or "make this site agent-ready". Triggered by /agent-ready-nextjs.

alexismaya Bundle

Generación de una presentación (PPTX) de un proyecto de software como entregable puntual (snapshot para una presentación concreta, no se sincroniza con el proyecto). Una entrevista de arranque detecta la AUDIENCIA —técnica, cliente/stakeholder o manual de usuario— y adapta todo el deck: estructura de slides, profundidad, vocabulario y qué diagramas incluir. Consume la documentación que el usuario provea, idealmente la ya generada por project-onboarding en Notion (bloque diagrams-export), o insumos adjuntos directamente. Renderiza los diagramas Mermaid como imágenes usando la skill pptx del entorno. Usar esta skill SIEMPRE que el usuario quiera: generar una presentación del proyecto, un 'deck', un 'PPTX', 'diapositivas' o 'slides'; 'presentar el sistema', hacer un 'pitch del proyecto', 'slides para el cliente', 'slides técnicos' o un 'manual de usuario en presentación'. NO reemplaza a project-onboarding: si el usuario quiere documentar Y presentar, recomendar correr primero project-onboarding (que produce la d

alexismaya Bundle

Úsala cuando un desarrollador quiera comenzar a escribir pruebas para un módulo, preparar un release, investigar cobertura existente, o cuando se reporte un bug y haya que decidir qué tipo de prueba de regresión agregar. Esta skill analiza un repositorio —detectando su stack antes de aplicar cualquier convención— y produce un mapa de "superficies de prueba" priorizado, un diagnóstico de cobertura actual, y una propuesta guiada de qué probar a continuación — sin generar código de tests todavía. Úsala también cuando alguien diga "no sé por dónde empezar a probar", "¿qué debería cubrir primero?", o "necesito un plan de QA para este módulo". Es la puerta de entrada obligatoria al ciclo de QA de esta suite.

alexismaya Bundle

Materializa en código de prueba concreto el "Contexto de handoff" que produce qa-discovery. Úsala SIEMPRE que un desarrollador ya haya corrido qa-discovery y elegido una opción (A–E), o cuando pida "genera las pruebas de X", "escribe los tests unitarios / de integración / e2e", "prepara la base de testing", o "materializa el handoff" de un módulo ya analizado. Opera en cuatro modos alineados a qa-discovery — unitario, integracion, e2e, infraestructura — y NUNCA genera un test sin un handoff trazable a una superficie del mapa de discovery. Usa el runner de pruebas del stack declarado en el handoff, sin imponer ninguno. Si no existe handoff de discovery, detente y remite a qa-discovery primero. Es el segundo eslabón obligatorio del ciclo de QA de esta suite.

alexismaya Bundle

Auditoría de un proyecto de software EXISTENTE para detectar debilidades, deuda técnica y áreas de mejora, evaluándolo contra 4 pilares: seguridad, escalabilidad, rendimiento y mantenibilidad. Cada hallazgo se sustenta con evidencia file:line, severidad e impacto; el propósito final es servir de insumo para rehacer el proyecto con la mejor arquitectura posible. Usar esta skill SIEMPRE que el usuario quiera: 'auditar' o hacer una 'auditoría' de un proyecto/repo/API/app; saber 'qué tan mal está' algo, 'dónde está la deuda técnica', 'qué debilidades' o 'riesgos' tiene; evaluar seguridad, escalabilidad, rendimiento o mantenibilidad de una base existente; o preparar el diagnóstico previo para 'rehacer esto bien' / 'rehacer con mejor arquitectura'. NO usar para: crear un proyecto nuevo a partir de otro (esa es derivar-proyecto), planear o generar tests (qa-discovery / qa-generator), implementar features o arreglar un bug, ni optimizar/mejorar/endurecer directamente un componente aunque se mencione un pilar (p. ej.

amd Bundle

Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs, and writes a prioritized stakeholder report (analysis.md). Use when the user asks to follow the analysis orchestrator, run the agentic analysis workflow, analyze a trace, compare two traces, or mentions standalone or comparative TraceLens analysis.

amgrbi96 Bundle

Use when running or configuring the PRISMA Literature Review Pipeline, constructing CLI commands, setting up literature review runs, choosing screening providers, configuring discovery sources, interpreting output artifacts, or creating per-project config files. Also use when the user mentions systematic reviews, literature screening, paper discovery, PRISMA flow, citation snowballing, or anything related to academic paper search and analysis — even if they don't explicitly name the tool.

dpolivaev Bundle

Choose the planning form for new work and plan it before execution. Use this skill to decide whether the work is taskless, chat-only, a task file, a task file with subtasks, or multiple task files / backlog items, and to create the needed plan for non-trivial implementation work or investigation work that needs its own task.

dpolivaev Skill

Create or revise file-based Spec Loop work breakdown artifacts for task-file work, including splitting a requested single item into subtasks or multiple task files / backlog items when planning or design shows that split is needed.

elan6666 Bundle

Create an appropriately detailed execution plan. Use when the user explicitly asks for a plan, roadmap, implementation approach, sequencing, dependencies, or acceptance criteria before execution.

bitsandtea Skill

Run SEO / GEO from seed keywords to published, AI-citation-friendly articles using PostKing — seed, expand, cluster, roadmap, brief, write, and publish.

bydeng01 Bundle

Find open PhD positions, funded studentships, fellowships, or labs actively recruiting students that match the applicant's profile. Use this whenever the user wants to discover, search for, find, or surface PhD opportunities — e.g. "find me PhD positions in NLP in Europe", "any funded studentships in computational biology?", "what programs should I be looking at?", "search for open PhD spots with professors working on diffusion models", or "are there openings in these three departments?". Sweeps position boards, department and lab pages, and funding databases, filters by the applicant's field/region/constraints, de-duplicates, and writes structured opening records to knowledge-base/openings/. Trigger even when the user names a board, a region, or a topic instead of saying "position" — any intent to locate PhD opportunities to apply to should use this skill.

byteseek Skill

Discover listed, pending, filed, or newly announced ETFs and create a structured candidate watchlist for ETF listing analysis.

caoyuan-fire Bundle

Materialize direct or Package execution contracts and orchestrate Phase, PAK, and Job records without executing them. Use after classification, for package creation or revision, roadmap planning, Job decomposition, and rework after package review.

cblanquera Bundle

Use for brand identity support, guided greenfield or brownfield branding, brand research, competitor discovery, market positioning, naming and domain checks, logo generation guidance, brand strategy, voice, messaging, visual guidelines, brand kit generation, brand audits, launch readiness, transparent PNG preparation, and PNG/ICO conversion.

cerebrocybersolutions Bundle

CEO-level cross-department briefing for {{operator_name}} at {{company_name}}. Reads all department Brain sessions and decisions, synthesizes into a structured brief covering what moved, what's stuck, pending decisions, and upcoming deadlines. Use this skill whenever {{operator_name}} says: "brief me", "what's the state of the company", "morning brief", "company status", "what happened", "catch me up", "how are we doing", "daily brief", "what do I need to know", or at the end of any sessionend to close the loop. Also triggers on: "what's moving", "macro view", "give me a company update". This is the Chief of Staff brain — always run it when the operator needs a company-wide picture, even if they don't say "brief" explicitly. NOTE: backlog-lane intents (aging / pending / unresolved decisions) route to cross-dept-decisions, not here. See {brain_root}/AGENTS.md §Known DRY pairs.

mindtheflo Skill

Use when an agent accesses Notis through the hosted generic MCP server and needs the discovery, validation, execution, connection, and skill-backed guide workflow.

mingfer Bundle

Use when users describe a new feature, analyze business requirements, write user stories, define acceptance criteria, discuss product needs, author a PRD, plan a process optimization, or say things like "我想做个...功能". Signals include vague requirements, technical solution proposals, missing acceptance criteria, undefined user roles, or unclear business rules.

mshadmanrahman Skill

Stress-test a design through three lenses, confused user, skeptical engineer and impatient PM, before it goes to a stakeholder. Requires an actual design, an HTML file, Figma link or screenshot.

danilods Skill

Use when user is in Phase 10 discovery for a feature — runs parallel research subagents and produces a research markdown that feeds matilha-plan.

datashaman Bundle

Jira project health audit via the Atlassian MCP. Identifies velocity trends, backlog rot, bug clusters, assignee concentration risk, and firefighting patterns. Requires the Atlassian MCP to be connected. Use when asked to "audit jira", "project health", "backlog analysis", or "team velocity".

datashaman Bundle

Trello board health audit. Identifies throughput trends, backlog rot, blocker clusters, member concentration risk, and overdue patterns. Use when asked to "audit trello", "board health", "backlog analysis", or "what's overdue".

datashaman Bundle

Build a multi-stage website specification pipeline that moves from discovery through IA, page planning, UX structure, design system, responsive rules, wireframes, and review using JSON contracts between stages. Use when the user wants to design a website through agent handoffs, create auditable page specifications, generate downstream UI from structured artifacts, or avoid burying site architecture inside prompts.

davemaynard Skill

Collapse a project to its North Star — the one defensible sentence that makes every roadmap decision easy — then restructure its roadmap file (TASKS.md or equivalent) around it (re-cut phases, promote the moat, archive shipped work, preserve any machine-read anchors). Trigger with /north-star <repo or idea>, or when the user asks "what's the why of this / what's our North Star / reshape the roadmap around why this exists."

daydreamsai Skill

Builds and deploys a production-ready paid Lucid Agent from user requirements. Scaffolds with CLI, implements entrypoints, reviews code, tests, publishes to GitHub, and deploys to Railway. Use when: "create a paid agent for X", "build and deploy an agent", "make a monetized agent". Not for: automated topic discovery (agent-factory) or platform-hosted JS handlers (lucid-agent-creator).

daydreamsai Skill

Meta-skill that orchestrates the full agent creation pipeline. Composes: trend-discovery → api-research → lucid-agents-sdk → railway-deploy. Use when creating new monetized agents from scratch.

daydreamsai Skill

Discovers trending topics on X/Twitter and the web. Finds opportunities where people need data/APIs. Use when starting any agent creation workflow.

decentraland Skill

Use when editing the Vercel SEO function (`api/seo.ts`), the rewrite rules (`vercel.json`), or anything CMS-origin related across env config and the vite dev proxy. Covers the OG/Twitter meta rewrite flow, HTML escaping, origin allowlist, and the CMS_BASE_URL coherence rule. Triggers on edits to `api/seo.ts`, `vercel.json`, `src/config/env/{dev,stg,prd}.json`, or `vite.config.ts` (proxy section). Also on mentions of "SEO", "OG tags", "open graph", "Twitter card", "crawler", "Helmet titles", "Vercel function", "CMS_BASE_URL", "Contentful API", "PAGES map".

dojocodinglabs Bundle

Applies MoSCoW (bucket) + RICE-adapted (intra-bucket ranking) to Linear issues of a product pillar, traceable to its PIBER+IDCF sub-spike and the latest vision audit. Use when the user asks to "prioritize issues", "priorizar el pillar", "aplicar MoSCoW", "rank the backlog", "RICE scoring", "/prioritize", or wants a data-backed decision on what to work on next within a pillar. Do NOT trigger for: generic backlog ranking without pillar context (use spike-recommend or implement-advisor instead), issue creation, or PR review.

dojocodinglabs Skill

Computes the ORDER in which a set of open PRs should be merged so that each one is still mergeable when its turn arrives. Measures pairwise file collisions, latent conflicts that only appear after an earlier PR lands, artifacts anchored to a base SHA that every other PR must regenerate, and CI queue capacity. Use when the user asks "in what order do I merge these", "which PR goes first", "how do I avoid conflicts merging all of these", "will merging this break the others", or has a backlog of open PRs against one base. Do NOT trigger for: reviewing a single PR, checking whether one branch is behind (that is sync-advisor), or listing PR status (that is review-open-prs).