Loading...
Loading...
Found 20 Skills
Use when the user asks to enhance, improve, refine, rewrite, strengthen, or validate a prompt, or says "make this prompt better". Returns a clearer, more specific, better structured version of the prompt without executing it, picking validation checks from the prompt's own context. Contexts include coding, research, writing, image or video generation, agentic tasks, data work, and system prompts. Flags ambiguity, contradictions, missing constraints, missing success criteria, format gaps, and leaked secrets. Do not use when the user wants the prompt's task performed.
Review and process app submissions for the Pollinations showcase. Parse issues, validate submissions, create PRs, handle user corrections.
Safely track pull request feedback, resolve review comments or merge conflicts, validate fixes, and use a read-only cross-review before committing or pushing follow-up changes.
AI SDLC QA workflow. Use when an AI assistant is asked for QA planning, acceptance validation, regression scope, exploratory checks, smoke tests, release verification, or change-focused manual validation evidence. Supports `--quick-flow` for fast assumption-driven execution and `--full-flow` for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.
Validate review completeness for one task in review and finalize the Nexus decision when probe next routes validate_reviews.
[Hyper] Create and refactor AI-readable docs, instruction bases, runbooks, specs, and harness-ready rule packs for context, prompt, tool, eval, sourcing, safety, and validation workflows.
Design Solana/Anchor instructions with clear inputs, constraints, authority checks, and invariants. Use when defining or reviewing instruction APIs.
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
Create Product Requirements Documents (PRD) following SDD methodology - Layer 2 artifact defining product features and user needs
Aggregate generated maintainer reports into a skill-quality summary. Use when reviewing docs, link, and eval health. NOT for editing report sources.
Automated jaan-to release preparation with validation, docs sync, version bump, and PR creation
Validación con usuarios reales sobre RumIAndo: prepara la sesión desde el contrato de la ficha (qué hipótesis se testean, con qué prototipo, con quiénes), guía la conducción (mirar sin ayudar, no vender), y registra TODO en RumIAndo — sesión de validación, hallazgos tipados (ux/funcional/tecnico/bloqueante), decisiones (aceptar/rechazar/iterar/derivar) — cerrando el loop: procesa las decisiones a transiciones de ficha. Usar cuando una ficha/fichero en PARA_VALIDAR se testea con productores/técnicos/usuarios, y también para registrar a posteriori una sesión que ya ocurrió. NO es QA técnico (wachi-qa) ni review interno (wachi-validacion-interna).