Explorar skills

Esta skill oferece um loop de otimização autônoma generalizada, utilizando RLVR suave para aprimorar iterativamente qualquer artefato mensurável, como código, prompts ou designs. Ela realiza isso executando experimentos estruturados, avaliando resultados com uma rubrica multidimensional e aprendendo a cada tentativa.

Use when the user wants to run the optimization loop, improve agent performance, evolve the agent, or iterate on quality. Requires .evolver.json to exist (run harness:setup first).

End work session intentionally. Use at natural stopping points, before context limits, or when switching contexts.

Pressure test an idea through core lenses. Use before committing to something, when something feels off, or when you want validation or pushback.

Identifica e elimina padrões típicos de escrita de IA em textos chineses, como clichês e estruturas formulaicas, para que o texto soe natural e humano. Aplicável a todos os cenários de escrita chinesa, desde mídias sociais até resumos acadêmicos.

Use when the user wants to smoke-test the evolve pipeline, test tools, or verify the plugin works end-to-end. Also use when the user says 'dry run', 'smoke test', or 'test pipeline'.

Use when the user wants to verify that the evolved agent's score is stable and reliable. Runs evaluation multiple times and reports mean ± std.

Pick up a workstream across sessions. Load context, find texture, align, then go. Use when jumping back into something that has history.

Use when the user asks about evolution progress, current scores, best version, how many iterations ran, or whether the loop is stagnating.

Generate content briefs by analyzing top-ranking SERP results. Extracts common topics, identifies content gaps, and creates actionable briefs for content-writer. Input: target keyword. Output: content brief with must-cover topics + gap opportunities.

Monitor your own website's SEO performance using Google Search Console data. Track keyword rankings, clicks, impressions, CTR, and position changes over time. Identify top performing pages, declining keywords, and new ranking opportunities. Use when user says "monitor my site", "my rankings", "GSC data", "Search Console", "my keywords", "position changes", "CTR", "impressions", or "clicks".

Detect VM/sandbox escape vulnerabilities in packages using node:vm, simpleeval, or custom sandboxes that can be bypassed to achieve code execution.