Explorar skills

Architecture principles (layering, boundaries, dependency direction). Preloaded into agents that reason about structure; not user-facing.

Run CLIP-based quality scoring on AI-generated image frames against configurable thresholds. Returns a GOOD / PASS / FAIL verdict with per-metric breakdown (prompt match, character similarity, palette match, composite). Use whenever the user generates an AI frame and needs objective quality feedback, says "verify", "check quality", "CLIP score", "does this pass", "score this frame", "is this good

Use when user says "execute prompt queue", "resume prompt queue", "run the queue", "reset prompt queue", "reset queue prompt", or has a docs/prompt_queue.md file with sequential prompts to execute. Orchestrates multi-step prompt pipelines with dynamic variable passing between steps, fresh subagent per step, and cross-session resumability via state file.

Fornece um servidor MCP que permite a integração e o gerenciamento contínuos de dados SkillsMP com ambientes Node.js que suportam o Protocolo de Contexto do Modelo.

Camada de segurança obrigatória para QUALQUER sessão ou ação do Claude Code que processe conteúdo externo, como WebFetch, WebSearch, leituras do GitHub, READMEs de repositórios externos, PDFs obtidos, artigos, sites de documentação e saídas de ferramentas MCP de serviços externos. Protege contra injeção de prompt (quarentena de saída, varredura de padrões de injeção, defesa contra injeção de chamadas de ferramentas, proibição de busca recursiva, truques de Unicode oculto) e vazamentos de PII em URLs.

Use when Claude Code needs to explain a SpecDD spec, target, behavior, or effective spec chain without editing it.

Master writing skill. Orchestrates the full pipeline (seed → draft → edit → slop-check → optional repurpose) for any post type — long-form (long-form-weekly-newsletter, long-form-monthly-devlog, long-form-hot-take, long-form-how-to, long-form-launch-retro, long-form-manifesto) or short-form (short-form-x-vs-y, short-form-listicle, short-form-observation, short-form-motivational, short-form-present

Meta Ads deep analysis covering Facebook and Instagram advertising. Evaluates 46 checks across Pixel/CAPI health, creative diversity and fatigue, account structure, and audience targeting. Includes Advantage+ assessment. Use when user says "Meta Ads", "Facebook Ads", "Instagram Ads", "Advantage+", or "Meta campaign".

Use when bringing forward priors from PAST sessions / cross-agent history before doing new work — NOT about re-reading the current context window (which is trivially in-context). Specifically triggered when auto-compact is lossy, when cross-session reference is needed, when the same topic has been treated before, or when the original work was done in a different agent's session. The discipline is

Verifies canon status, naming compliance, frontmatter completeness, writing standards, and cross-reference validity across worldbuilding files. Use when checking naming consistency, verifying frontmatter, auditing prose standards, or when user says "canon audit", "check names", "verify frontmatter", "writing standards check", or "naming audit". Does NOT check physics equations — use /auditing-phys

Manages the writing cadence using per-ISO-week directories under scribetronic/calendar/. Combines recurring rules + per-week plan.md + history. Subcommands: show, plan-week, add, skip, done, rules. Used by /write router and /write-publish.

Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.