Agent Skills: llm-evaluation
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
ID: microck/ordinary-claude-skills/llm-evaluation
39953
Install this agent skill to your local
Skill Files
The files that make up llm-evaluation.
Loading file tree…
More agent skills
- swift-concurrencyGuide for building, auditing, and refactoring Swift code using modern concurrency patterns (Swift 6+). This skill should be used when working with async/await, Tasks, actors, MainActor, Sendable types, isolation domains, or when migrating legacy callback/Combine code to structured concurrency. Covers Approachable Concurrency settings, isolated parameters, and common pitfalls.
- search-strategyQuery decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.
- adsWhen the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad budget,' 'cost per click,' 'ad spend,' 'should I run ads,' 'ABM,' 'account-based marketing,' 'B2B ads,' 'lead quality,' 'negative keywords,' 'Performance Max,' 'thought leader ads,' 'when should I kill an ad,' 'search terms report,' 'wasted spend,' or 'is this campaign working.' Use this for campaign strategy, audience targeting, bidding, and optimization. For bulk ad creative generation and iteration, see ad-creative. For landing page optimization, see cro. For outbound to target accounts, see cold-email. For pixels, CAPI, and tracking audits, see conversion-tracking. End every recommendation with facts, hypotheses, and missing data, and label unavailable inputs MISSING instead of estimating them.
- unity-cliGuide for using the experimental Unity CLI with bound UnitySkills projects
- github-issuesGitHub issue comment guidelines for community interaction. Use when: "respond to this issue", "reply to this bug report", "close this issue", or any GitHub discussion.
- projection-patternsBuild read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.