Навыков: 28 594. Сортировка по числу звёзд.
Etsy Ads strategy — budget allocation, bid management, promoted listings, offsite ads opt-out analysis
EU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 8 prohibited p...
Trigger word — when the user types "eureka" after finishing a piece of work, review the just-completed changes and surfa...
Skippable Phase 0 of the Gaia evidence verification pipeline. Use only on declared need for higher-quality Stage-2 evide...
Compare an EV against a comparable gas car on total cost — upfront gap after incentives, energy vs fuel per year, mainte...
Evaluate and rank agent results by metric or LLM judge for an AgentHub session.
Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks...
Rank finished AgentHub agents by metric or judge. Use when asked which agent won.
Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking
Evaluate a local skill with the terum-skills CLI — hygiene, trigger evals and execution cases against a baseline, billed...
Compares the eval scores of two plugin folders, such as a plugin and a variant of it. Use when the user wants to know wh...
[Beta] Creates permanent eval cases from promoted learnings and runs regression checks against them. Turns failures into...
Use to design the evals for a build before you build it, right after the Goal and Constraint Brief, and again to run the...
克劳德代码会话的正式评估框架，实施评估驱动开发（EDD）原则
Frozen evaluation harness that gates self-improvement with benchmarks, regressions, and human approval loops.
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals before coding, g...
Formal evaluation framework for OpenAI Codex sessions implementing eval-driven development (EDD) principles
Formal evaluation framework for Claude Code
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Use when a C...
Formal evaluation framework for Codex sessions implementing eval-driven development (EDD) principles
Formal evaluation framework for AI-agent sessions implementing eval-driven development (EDD). Use when an Agent workflow...
Claude Code toolkit - agents, commands, skills, rules, and hooks for productive AI-assisted development
Holdout-safe Outcomes grading: project the locked eval substrate, then ingest one verdict.
Guide for diagnosing and improving MSBuild project evaluation performance. Only activate in MSBuild/.NET build context....
Show a team skill's eval history — committed receipts per version and this machine's local runs — as a Markdown board fr...
Provides context about the Roo Code evals system structure in this monorepo. Use when tasks mention "evals", "evaluation...
Use when a published goldset is ready to become executable graders and configs — Python graders and metrics with auto-ru...
Use when standing up evals/{system}/ for the first time — scaffolds the EDD directory structure, picks PromptFoo or Deep...
Evaluate a single retort experiment run. Score the generated code against the task's TASK.md requirements, run its build...
A fast, cheap sanity check on a Claude Code skill or plugin while you are still writing or iterating on it — not the ful...
Structured evaluation before adopting a library, tool, or hosted service — enumerate candidates wide, then score every o...
Evaluates Node.js packages before installation by checking bundle size impact, comparing alternatives, verifying latest...
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context eng...
Guidelines for creating evaluation suites, including spec.md templates, rubric structures, and code-based validation pat...
Build evaluation frameworks for agent systems
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensi...
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choice...
name: evaluation-plan
eve framework guidance for durable AI agents and agent-powered applications. Use when creating, editing, or debugging an...
Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent...
EVE Online ESI API integration skill for third-party development. Use when building EVE Online tools, apps, or games tha...
Forge a personalized eve agent for a business end-to-end — absorb the business's artifacts, author the eve agent/ dir, v...
Build an event budget that survives the event — every cost line including the ones people forget, the contingency sized...
Use when designing or debugging an event-driven system — choosing Kafka partitioning strategies, implementing the outbox...
Use when designing event-driven architectures and patterns for loosely coupled, asynchronous .NET systems. USE FOR: even...
Use events to decouple producers from consumers Use when designing system architecture. Architecture category skill.
Chokidarライブラリを中心としたファイルシステム監視の専門スキル。 Observer Patternによる効率的なファイル変更検知、クロスプラットフォーム対応、 EventEmitterによる疎結合な通知システムを設計・実装する。...