Showing 61951–61980 of 77202 skills
Motor GraphRAG local que responde perguntas complexas de lore usando travessia do grafo do universo ficcional com SLM local.
Ryanzucchi/Eldritch_Lich
Monitora a flutuacao emocional (valencia e arousal) de personagens ao longo da historia mapeando arquetipos dramaticos.
Ryanzucchi/Eldritch_Lich
Motor de recomendacao de enredo, nomes e referencias literarias com busca paralela vetorial, grafo e notas fundidas com RRF.
Ryanzucchi/Eldritch_Lich
Responde perguntas do autor sobre o manuscrito usando RAG hibrido local com citacao de fontes (capitulos e notas).
Ryanzucchi/Eldritch_Lich
Resolve referencias pronominais e aliases de personagens em romance, unificando mencoes sob um ID canonico.
Ryanzucchi/Eldritch_Lich
Sincroniza dados relacionais estruturados (fichas, cronogramas) offline-first entre IndexedDB e PostgreSQL sem conflitos.
Ryanzucchi/Eldritch_Lich
Sincroniza bases SQLite com indice vetorial entre dispositivos usando Delta-State CRDTs e resolucao LWW offline-first.
Ryanzucchi/Eldritch_Lich
Gera resumos de romances longos em multiplos niveis (cena, capitulo, obra) sem estourar janelas de contexto de modelos locais.
Ryanzucchi/Eldritch_Lich
Valida candidatos a tropos usando LLM local com contexto global do enredo, distinguindo ocorrencias canonicas de subversoes criativas.
Ryanzucchi/Eldritch_Lich
Compila assincronamente o contexto de escrita do autor em vetor unificado (CAC) para alimentar motores de recomendacao locais.
Ryanzucchi/Eldritch_Lich
Renderiza redes de personagens e locais com filtros temporais e agrupamento semantico para evitar saturacao visual no navegador.
Ryanzucchi/Eldritch_Lich
Hotel competitive intelligence and market positioning. Use when the user asks about 'comp set analysis', 'competitor rates', 'market positioning', 'new supply impact', 'competitor renovations', 'rate shopping', 'SWOT analysis', or benchmarking against competing properties.
hospitalityos/hotel-ai-skills
Hotel sales and marketing content generation. Use when the user asks to 'write a group proposal', 'draft an RFP response', 'create marketing email', 'social media content for hotel', 'OTA listing optimization', 'press release', 'wedding package brochure', or any hotel sales/marketing collateral.
hospitalityos/hotel-ai-skills
Hotel forecasting and budget modeling. Use when the user asks to 'build a forecast', 'create a hotel budget', 'reforecast revenue', 'project GOP', 'model occupancy scenarios', 'forecast F&B revenue', 'labor forecast', or any forward-looking financial projection for a hotel.
hospitalityos/hotel-ai-skills
Hotel labor optimization and staffing analysis. Use when the user asks about 'staffing levels', 'labor cost', 'overtime prevention', 'scheduling optimization', 'housekeeping productivity', 'FTE recommendations', 'CPOR labor', or any workforce planning task for a hotel.
hospitalityos/hotel-ai-skills
Hotel owner and asset manager reporting. Use when the user asks to 'build an owner report', 'quarterly business review', 'asset manager update', 'investor report', 'management report', 'capital planning report', or any reporting package for hotel ownership groups.
hospitalityos/hotel-ai-skills
Guest review analysis and reputation management for hotels. Use when the user asks to 'analyze reviews', 'check our ratings', 'draft a management response', 'reputation report', 'sentiment analysis', 'guest feedback trends', or any review monitoring and response task.
hospitalityos/hotel-ai-skills
Hotel sales pipeline and group business management. Use when the user asks about 'group pipeline', 'RFP response', 'displacement analysis', 'catering proposal', 'sales production report', 'total revenue contribution', 'tentative blocks', or any hotel sales and events management task.
hospitalityos/hotel-ai-skills
Hotel SOP and training documentation generator. Use when the user asks to 'create an SOP', 'write training materials', 'onboarding checklist', 'department procedures', 'brand standards documentation', 'housekeeping standards', 'front desk procedures', or any hotel operations documentation.
hospitalityos/hotel-ai-skills
Run a multi-agent build session: the main session acts as manager — cutting a goal into units, spawning implementer, tester, and adviser subagents, and running the test-and-review loop to completion under anti-thrash guardrails.
NagareNegishi/DJ-App
Apply whenever writing or editing code in any language, even if comments are not explicitly requested. Enforces comment and documentation discipline: concise file headers, function docs in the language's native format, inline comments for non-obvious logic, and protection of existing comments. Not required during suggestion-only or discussion when no file is written.
NagareNegishi/DJ-App
Audit the repository for comment coverage and bring under-commented source up to standard. Walks one file at a time, proposes comments per file for approval, and tracks progress to resume across sessions. Invoke with /comment-audit.
NagareNegishi/DJ-App
Upgrade outdated dependencies one package at a time, with a changelog check for breaking changes and a test run between upgrades. Invoke with /dependency-upgrade; pass package names to limit scope.
NagareNegishi/DJ-App
Use this skill whenever the user needs help choosing between programming technologies, libraries, frameworks, tools, patterns, or architectural approaches. Covers all programming domains. Trigger even if the user doesn't say "suggest" explicitly — any programming decision where options exist and verification matters should use this skill.
NagareNegishi/DJ-App
Improve the visual design of the <project> frontend. Use when asked to improve, redesign, restyle, or enhance the UI in <frontend-dir>/.
NagareNegishi/DJ-App
Write documents in a plain, human voice and remove phrasing that reads as machine-generated. Use this skill EVERY time you produce a written artifact meant to be read by a person: READMEs, official documentation, design or planning docs, summaries, reports, proposals, release notes, changelogs, commit messages, GitHub issues, pull request descriptions, letters, emails, blog posts, and similar deliverables. Trigger it whenever the task is "write/draft/generate a doc" rather than answering a question in chat. Do NOT trigger it for direct conversational replies, inline explanations, or code. Run it in two passes: write the document, then re-read the finished draft and rewrite anything that signals a machine wrote it, presenting only the corrected version.
NagareNegishi/DJ-App
Create or reconcile a repository's labels from the preset in `labels.yml`. Writes labels only — never deletes, never touches labels outside the preset. Invoke with /label-setup.
NagareNegishi/DJ-App
At session end, write the one-file session baton (docs/session/baton.md): a high-level summary of what this session was about, the goal, and the single next task. Overwrites the file — no change lists, no task lists, no detail. Read-only on git; writes only the baton. Use `session-wrapup` for git state and progress.md.
NagareNegishi/DJ-App
Close out a working session: update `docs/progress.md`, report uncommitted and unpushed work, and list the session's decisions and open threads. Read-only on git — never commits, stages, or pushes.
NagareNegishi/DJ-App
Apply whenever the task is diagnosing a bug, a failing test, or unexpected behavior — even if the user only says "fix it". Core rule: never fix what has not been reproduced. Not required for feature work, or when the user has already stated the cause and only wants the change made.
NagareNegishi/DJ-App