Maintain a running decision record for the work — decisions, failures, constraints, and open questions discovered while doing it. Use throughout, not as documentation written afterwards.
Turn raw user notes into a complete, developer-ready requirements folder through iterative clarification. Produces one or more focused requirement files plus a QA test-case file per feature. Use when the user explicitly invokes this skill to scope a feature, bug fix, or development iteration before any code is written.
Use when work is multi-step, context-heavy, research-heavy, or delegated. Contains bulky context, phases work, bounds retries, delegates independent reasoning, and reserves capacity for verification.
A requirements-interview method that explores four kinds of information: what was already stated, what needs an answer, what the user knows but omitted, and risks they may not have considered. It produces a short requirements specification before work begins.
A unified super-mode orchestrator inspired by Doubao. It normalizes any user request into a v1/v2-compatible task protocol, determines the execution mode first, decomposes the work into subtasks, and dispatches them to the right capability modules—complex-task-handler, deep-web-search, multi-content-generator, and the…
Digests outputs from parallel review sprints by reading their markdown files. Synthesizes a 5-domain factual check, forces an executive Go/No-Go decision, and generates the final markdown data contract and HTML dashboard for Phase 4.
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).
A guided architecture-design process that turns requirements into documented system designs and architecture diagrams. Architecture describes how a software system is divided and how its parts fit together.
A feature-scenario writing skill that turns a rough idea or feature description into a detailed document covering the user flow, conditions, user experience, effort, and open questions.
A software-opportunity discovery assistant for independent developers. It examines existing products, markets, or news and turns them into possible software ideas using ten defined strategies.
Use when user wants to turn an idea into a shipped product using AI tools — activate this workflow before any code, scaffold, or implementation action.
Use on a fortnightly or post-milestone cadence, or when the user says "retrospective" / "retro" / "what's been recurring" / "what did we learn" / "review the last few sessions". Reads multiple session transcripts, distils each, measures token-weighted wasted effort (including abandoned-and-restarted sessions), and…
Master orchestrator for the full LinkedIn weekly workflow. Use this skill when the user wants to plan their LinkedIn week, run a full LinkedIn session, get a weekly content plan, or coordinate multiple LinkedIn tasks at once. Trigger for phrases like "prepare my LinkedIn week", "run my LinkedIn session", "what should…
Use the WNP Loop methodology for sustained AI-assisted software development with solo developers or small teams. Trigger when the user asks to work in a What's Next/Proceed cadence, wants research-before-build planning, milestone-driven implementation, project continuity across context resets, iterative tooling…
A review method for business plans, product specifications, and software deliverables. It checks them against five criteria covering coverage, quality, clarity, coherence, and practical usefulness.
Plan, research, implement, debug, and verify software changes deliberately. Use for product or coding work that needs current technical choices, explicit tradeoffs, minimal-scope edits, and delivery-grade validation.
Sistema completo de OKR e Execução Estratégica — da visão à execução semanal. Cobre duas camadas: OKRs de Time/Empresa (resultados coletivos) e OKRs Individuais (contribuição + desenvolvimento com metodologia 70-20-10). Também cobre hierarquia de metas, redação de OKRs, rubricas de pontuação, cascateamento, dashboards…
Grill an app idea before any code is written — two waves of hard product questions, each with a recommended answer the user edits or accepts — then hand off to the BEFOREVIBE MCP connector for the visual storyboard, production-ready PRD, logo and screen mockups. Use when the user shares a new app or product idea, asks…
Interview the user relentlessly about a plan or design until reaching shared understanding. Use when user wants to stress-test a plan, challenge a design, or says things like "grill me", "poke holes in this", "what am I missing", "tear this apart", or "challenge this".
Stress-test an idea or domain model through evidence-backed interview rounds when the user asks to be challenged or grilled. Record agreed terminology and durable decisions.
★not rated 2
changed 2d agoA32 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: