Evals Start

ai-evals-course/evals-skills/skills/evals-start

作者 ai-evals-course80d5f7b0127c7572ed9e9339937adbfd7240ffeb無授權條款1.4K 個星標收錄於 2026年10月9日更新於 2026年10月9日儲存庫2 週前更新

Entry point for evals. Use when the user asks for help with evals, does not know where to begin, or asks for something no other skill in this plugin matches. Do NOT use when a more specific skill in this plugin already matches; load that skill directly.

僅含說明AI & Agents
AI 產生的概覽

將評估相關請求路由到同一個外掛中合適的專用技能。

功能
這個技能是評估工作的進入點。它提供一張表格,將使用者情況對應到特定技能,例如錯誤探索、評估稽核、程式碼評估撰寫、評審提示撰寫、評估器驗證、合成資料產生、審查介面建置和 RAG 評估。它會告知使用者正在載入哪個技能及原因,然後交接到該技能的工作流程。它只包含路由說明,本身不產生任何產出。
適用情境
當使用者請求評估方面的協助、不知道從何開始,或請求外掛中沒有其他技能符合的內容時使用。當外掛中已有更具體的技能符合時不要使用;應直接載入該技能。
執行需求
不需要指令碼或工具;它是一份僅含說明的路由文件。

Evals Start

This plugin splits eval work into targeted skills. Your job here is small: find the row below that matches the user's situation, tell the user which skill you are loading and why, then load that skill and follow its workflow from start to finish instead of improvising your own version of it.

SituationSkill to load
Has traces, wants to find failure modes, no established taxonomy yeterror-discovery
Has an existing eval pipeline and wants to know if it can be trustedeval-audit
Has a known failure mode that code can check (e.g., format, schema, regex, execution)write-code-eval
Has a known failure mode and wants an LLM judge for itwrite-judge-prompt
Has an LLM judge or evaluator and wants to check its qualityvalidate-evaluator
Has no traces to review yetgenerate-synthetic-data, then error-discovery
Wants a custom annotation interface for some other labeling taskbuild-review-interface
Wants to evaluate a RAG pipelineevaluate-rag

Most requests that mention error analysis with traces in hand mean error-discovery. New users with an existing pipeline usually need eval-audit first. This file holds only routing. When in doubt about which row fits, ask the user instead of guessing. The workflow lives in the targeted skill.

來源與署名

來源:ai-evals-course/evals-skills位於skills/evals-start提交80d5f7b

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架