SkillHey.
Добавить навык

Найти навыки

Авторские процессы для сайтов, изображений, презентаций и анимации.

14 навыковпо запросу “evaluation”
Сбросить фильтры

Agent Evaluation

Google

Build evaluation datasets, run and grade agent traces, and investigate failures.

  • agent evaluation
  • testing
6,3 тыс.Звёзды732Форки
Последний push репозитория
Codex Autoresearch — Codex Autoresearch dashboard with synthetic example measurements
Бесплатно
Продуктивность и автоматизация

Codex Autoresearch

Run resumable improvement loops or bounded investigations in local projects with explicit objectives, allowed changes, budgets, and evidence.

837Звёзды59Форки
Последний push репозитория
Albert
Career Ops workflow principles
Бесплатно
Продукт и бизнес

CareerOps: Job Search Workspace

Route job evaluation, tailored CVs, application tracking and interview preparation through one workspace.

82,1 тыс.Звёзды15,1 тыс.Форки
Последний push репозитория
career-ops-hq

Web Typography

wondelai

Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.

  • typography
  • Web design
2,7 тыс.Звёзды266Форки
Последний push репозитория
Illustrative Claude Academy recommendation linking to the official Claude Code learning resource.
Бесплатно
Skills и MCP

MCP Builder

Design and implement MCP servers with discoverable tools, clear schemas and task-based evaluations.

193,4 тыс.Звёзды22,8 тыс.Форки
Последний push репозитория
Anthropic

Agent Development Workflow

Google

Plan and follow an agent lifecycle from requirements and scaffolding through evaluation and deployment.

  • agent development
  • Workflow
6,3 тыс.Звёзды732Форки
Последний push репозитория

Yao Meta Skill

YAO

Create, revise, package, and evaluate agent Skills from workflows, prompts, SOPs, and scripts using a routed review process.

  • skills
  • workflow-design
  • evaluation
2,7 тыс.Звёзды253Форки
Последний push репозитория
dontbesilent’s official dbskill Claude Code plugin-installation demo, resized and compressed while preserving the complete loop.
Бесплатно
Skills и MCP

dbs-skill-maker · Skill Creation and Validation

Turn a recurring problem into one installable skill through needs analysis and staged validation; prepare public distribution only when requested.

11,4 тыс.Звёзды1,3 тыс.Форки
Последний push репозитория
dontbesilent

Skill Optimizer

Matteo Collina

Improve Skill activation and clarity using scenario comparisons and regression checks.

  • agent skills
  • evaluation
2 тыс.Звёзды146Форки
Последний push репозитория
Career Ops workflow principles
Бесплатно
Исследования и данные

CareerOps: Sponsorship Data Check

Attach a factual employer sponsorship signal from configured data to US-role evaluations.

82,1 тыс.Звёзды15,1 тыс.Форки
Последний push репозитория
career-ops-hq
Illustrative Claude Academy recommendation linking to the official Claude Code learning resource.
Бесплатно
Skills и MCP

Skill Creator

Create and improve reusable skills with test cases, comparative evaluations and trigger-description refinement.

193,4 тыс.Звёзды22,8 тыс.Форки
Последний push репозитория
Anthropic

AI Evals Skills

AI Evals Course

Practical workflows for assessing and improving product-specific LLM evaluations.

  • ai evaluation
1,8 тыс.Звёзды126Форки
Последний push репозитория

Eval Audit

AI Evals Course

Audit an LLM evaluation pipeline for missing error analysis, unvalidated judges, data leakage and stale checks.

  • llm evaluation
  • ai evaluation
1,8 тыс.Звёзды126Форки
Последний push репозитория

SkillOpt Sleep

microsoft

Consolidate previous agent sessions into reviewed memory and skill improvements through an offline sleep workflow.

  • skill-evaluation
  • agent-workflows
19 тыс.Звёзды1,8 тыс.Форки
Последний push репозитория

Небольшая библиотека, созданная с заботой. Скоро появятся новые навыки.