--- title: "ifixai.ai (@ifixai-ai) skills ยท skilld" canonical_url: "https://skilld.dev/gh/ifixai-ai" meta: description: "1 agent skill published by ifixai.ai on skilld." "og:description": "1 agent skills published by ifixai.ai." "og:title": "ifixai.ai on skilld" --- ` ![Avatar for ifixai.ai](https://skilld.dev/_img/avatar?url=https%3A%2F%2Fgithub.com%2Fifixai-ai.png) # **ifixai.ai** [@ifixai-ai](https://github.com/ifixai-ai)org 1 skill 18k United Kingdom [GitHub](https://github.com/ifixai-ai) ## Skills ### [ifixai-ai/ifixai](https://skilld.dev/gh/ifixai-ai/ifixai) 1 skill 18k `npx skilld add ifixai-ai/ifixai` - [ **/ifixai**18k Guide the user through an independent iFixAi audit of their own agent, checking whether it does the job it is supposed to do given their business rules and org structure. Prefer pointing it at the user's REAL deployed agent over its HTTP endpoint (its actual tools, retrieval, and governance) with \`--provider http --endpoint \\`; only when no endpoint is reachable, fall back to replicating the model beneath as a bare stand-in (Anthropic, OpenAI, Gemini, Azure, Bedrock, etc.). Graded by the judge(s) of their choice (the same model, one independent judge, or a cross-vendor panel). You are the operator who walks them through it and explains the scorecard, running the SAME \`ifixai run\` engine as the guided CLI. Use when the user asks to run iFixAi or to audit an agent. /ifixai by ifixai-ai](https://skilld.dev/gh/ifixai-ai/ifixai) Skills published by ifixai.ai. Checked GitHub just now