seedance-storyboard-skill
Seedance 2.0 分镜编写技能。将导演讲戏内容转化为 Seedance 2.0 格式的动态视频提示词。
104 repo starsObserved in 1 repos
Documents
Documents skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
storyboard-review-skill
分镜审核技能。用于审核影视分镜产出（节拍拆解、Beat Board、Sequence Board），通过逐项比对、脑内预演和评分制确保分镜质量达标。
104 repo starsObserved in 1 repos
Documents
update-claude-md
Analyze all changes in the current git branch and update CLAUDE.md if architectural or important changes warrant it. Use this skill when the user asks to update CLAUDE.md, sync docs with branch changes, review what changed architecturally, or before creating a PR to ensure documentation is current. Also trigger when the user says things like "update docs for this branch", "does CLAUDE.md need updating", or "what architectural changes did we make".
104 repo starsObserved in 1 repos
Documents
aigc-detector
Academic paper AI content detection, rewriting, and thesis writing assistant. Analyzes text for AI-generated characteristics, provides detailed rewrite suggestions, and generates full thesis drafts. Supports .docx files, outputs reports and rewritten/formatted documents. Bilingual: Chinese & English.
103 repo starsObserved in 1 repos
Documents
apresentacao-slides
Slides executivos: estrutura, narrativa visual e design para apresentações no Brasil
103 repo starsObserved in 1 repos
Documents
board-deck-builder
Monta apresentações abrangentes para conselhos e atualizações para investidores, reunindo perspectivas de todos os papéis do C-suite. Use ao preparar reuniões de conselho, atualizações para investidores, revisões trimestrais de negócios ou narrativas de captação. Cobre estrutura, framework narrativo, entrega de más notícias e erros comuns.
103 repo starsObserved in 1 repos
Documents
code-to-prd
Faça engenharia reversa de qualquer base de código em um Documento de Requisitos de Produto (PRD) completo. Analisa rotas, componentes, gerenciamento de estado, integrações de API e interações do usuário para produzir documentação legível para negócios, detalhada o suficiente para engenheiros ou agentes de IA reconstruírem completamente cada página e endpoint. Funciona com frameworks frontend (React, Vue, Angular, Svelte, Next.js, Nuxt), frameworks backend (NestJS, Django, Express, FastAPI) e aplicações fullstack. Acione quando os usuários mencionarem: gerar PRD, fazer engenharia reversa de requisitos, código para documentação, extrair especificações de produto do código, documentar lógica de página, analisar campos e interações de página, criar inventário funcional, escrever requisitos de uma base de código existente, documentar endpoints de API ou analisar rotas de backend.
103 repo starsObserved in 1 repos
Documents
consistency-audit
Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every finding span-anchored to the evidence ledger (claims.json), reviewer≠adjudicator. Emits consistency-audit.findings.json; NEVER computes the verdict. Triggers: "consistency audit", "check the paper against itself", "self-consistency", "内部自洽".
103 repo starsObserved in 1 repos
Documents
documentation-manager
Creates and updates README files, API documentation, changelogs, architecture docs, and user guides for Loom projects. Use when docs are outdated, a feature needs documenting, a changelog entry is missing, or code changes require documentation updates.
103 repo starsObserved in 1 repos
Documents
evidence-ledger
Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers, comparisons, scope, method, baselines, citations, captions, table cells) into claims.json. An OPTIONAL additive cross-model pass ADDS span-anchored semantic claims — method, theorem statements with their assumptions, definitions, proof/derivation steps and equations, scope, baselines, conclusions, the motivation span, and reproducibility-artifact references (the proof, derivation, and structure anchors the family B/D/G auditors need) — it never invents a number, emits a finding, or computes a verdict. Run FIRST, before any audit skill. Triggers: "build the ledger", "extract claims", "prep for integrity audit", "evidence ledger", "建证据账本".
103 repo starsObserved in 1 repos
Documents