Dev & Engineering llm-evaluationpairwise-comparisondirect-scoringrubric-designbias-mitigationconfidence-calibrationquality-assessment

Advanced LLM Evaluation

Build auditable, calibrated LLM-output evaluations with explicit rubrics, confidence scoring, and bias controls.

FollowSkills review · FSRS-2.0
Not recommended
56/ 100 5-point scale 2.8 / 5
Trust17 / 25 · 3.4/5

The skill mainly provides evaluation guidance and example code, with no evidence of malware, credential theft, covert exfiltration, or destructive defaults, supporting a relatively strong score; however, it does not clearly specify data flows, sensitive-data handling, user confirmation, permission boundaries, rollback, or dependency security, and its examples invoke external model calls, so points are deducted.

Reliability8 / 20 · 2.0/5

The documentation is internally coherent and covers input validation, error handling, retries, bias mitigation, and testing patterns; however, the implementation is pseudocode, relies on unspecified dependencies, lacks a directly runnable end-to-end implementation, and has no dedicated test suite for this skill, so the static cap and uncertainty require deductions.

Adaptability11 / 15 · 3.7/5

Activation conditions, adjacent-skill boundaries, and direct-scoring, pairwise-comparison, and rubric-generation scenarios are fairly clear, with platform-agnostic framing; however, input/output contracts and non-fit boundaries remain limited, and there is no Chinese-language guidance or mainland-China environment adaptation, so points are deducted.

Convention10 / 15 · 3.3/5

The skill includes progressive structure, references, script examples, creation and update dates, author, version, and MIT licensing; however, maintenance ownership and update procedures are not specific, installation and dependency guidance is mostly repository-level, and some production-grade wording does not fully match the pseudocode implementation, so points are deducted.

Effectiveness6 / 15 · 2.0/5

It offers actionable frameworks for evaluation taxonomy, bias mitigation, confidence calibration, and rubric design, with structured examples; however, users must still adapt the material to a runtime, and there is no directly deployable implementation, locked dependency set, or target-task validation, requiring a deduction under static calibration.

Verifiability4 / 10 · 2.0/5

The files contain named academic and industry references, code examples, testing patterns, and repository-level CI evidence; however, the selected skill lacks dedicated reproducible tests for key paths, citations are not mapped claim by claim, and some numeric or effectiveness claims lack third-party execution evidence in the supplied files, so only limited credit is warranted.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision c578e85e40fe
Before you use it
  • The example code is described as pseudocode and should not be treated as directly runnable or integration-tested.
  • External research links and claims such as 40–60% variance reduction are not supported by claim-level, reproducible evidence within the selected skill.
  • When using real models, third-party libraries, or fact-checking services, separately review network access, privacy, cost, version pinning, and fallback behavior.
  • The skill provides no dedicated Chinese terminology, Chinese prompt templates, or mainland-China reachability guidance.
See the full review method →

What does this skill do, and when should you use it?

This skill is for production-grade evaluation systems that use LLMs as judges. It helps practitioners choose between direct scoring, pairwise comparison, and reference-based evaluation, then define scales, domain-specific rubrics, and confidence calibration. It addresses position, length, self-enhancement, verbosity, and authority bias. It is a fit for teams that need to compare automated judgments with human assessments, monitor systematic disagreement, and improve evaluations over time.

It guides users in defining evaluation criteria, weights, and scoring scales, with evidence required before a judge emits a score; designs two-pass pairwise evaluation with swapped positions, consistency checks, tie handling, and confidence calculation; generates domain-specific rubrics with level descriptions, observable characteristics, examples, and edge cases; maps task structures to metrics such as Precision, Recall, F1, Spearman's rho, Kendall's tau, agreement rate, and position consistency; and outlines pipelines containing criteria loading, scoring, bias mitigation, confidence scoring, and structured output.

  1. An evaluation engineer builds a direct-scoring workflow for individual LLM responses when objective criteria such as factual accuracy or instruction following exist.
  2. A model team compares two candidate responses on tone, style, persuasiveness, or creativity while swapping presentation order to reduce position bias.
  3. A quality team creates a domain-specific rubric for code readability, factual accuracy, or another criterion with score levels and edge-case guidance.
  4. A researcher measures correlation between automated judges and human judgments while tracking disagreement by criterion, response type, or model.
  5. A high-volume evaluation system uses a panel of models, hierarchical screening, or human review for high-stakes and low-confidence cases.

What are this skill's strengths and limitations?

Pros
  • Covers the main judge-design stages: direct scoring, pairwise comparison, rubric generation, bias mitigation, and confidence calibration.
  • Includes adaptable prompt structures, a decision tree, a metric-selection table, and layered production-pipeline guidance.
  • Clearly separates objective from subjective criteria and emphasizes evidence-first scoring, position swapping, and systematic-bias monitoring.
  • Provides scaling strategies involving model panels, hierarchical evaluation, and human-in-the-loop review.
Limitations
  • The skill provides patterns and examples but does not show an independent test suite or validation results on a target evaluation set.
  • LLM judges can still exhibit position, length, verbosity, self-enhancement, and authority bias, requiring calibration and monitoring.
  • Model panels and high-quality human review add cost; no specific model, vendor, or budget is prescribed.
  • It does not own general deterministic checks, regression suites, production quality gates, evaluation-tool API contracts, or autonomous-loop governance.

How do you install this skill?

Obtain the repository from https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering and copy the complete skills/advanced-evaluation directory into the target client's skill directory, for example: mkdir -p .codex/skills && cp -R skills/advanced-evaluation .codex/skills/. It may also be copied to .claude/skills/ or the generic .agents/skills/ directory. Do not flatten the skill into a single markdown file. The source does not document platform-specific installation commands beyond these directory layouts.

How do you use this skill?

In an Agent Skills-compatible client with the skill installed, give it a concrete advanced-evaluation request such as: “Design a pairwise LLM-as-a-Judge workflow for comparing two customer-support responses, including position swapping, bias mitigation, confidence scoring, and JSON output.” Activate it for LLM-judge systems, response comparison, prompt or model A/B tests, rubric creation, or analysis of automated versus human judgments.

How does this skill compare with similar options?

The source explicitly distinguishes direct scoring from pairwise comparison: use direct scoring when objective ground truth or criteria exist, pairwise comparison for subjective preference or quality judgments, and reference-based evaluation when a reference is available. It does not compare the skill with named third-party products.

FAQ

Does this skill require a specific model or paid service?
No specific model or service is named. The source notes that multi-model judging is more expensive but can be more reliable for high-stakes decisions.
Does it automatically run evaluations or call external tools?
The SKILL.md presents methods, prompt structures, and examples; it does not declare MCP, external API, or specific tool dependencies.
Why should pairwise evaluations run twice?
A single pass can be distorted by position bias. The skill requires swapping A and B, checking consistency, and returning a lower-confidence tie when the passes disagree.
Is it intended for every quality gate or regression test?
No. It owns LLM-judge design and bias mitigation. Deterministic checks, regression suites, production quality gates, and monitoring belong to the adjacent evaluation skill.

More skills from this repository

All from muratcankoylan/Agent-Skills-for-Context-Engineering

Dev & Engineering

Agent Evaluation Methods

Build repeatable evaluation, regression detection, and quality gates for agent pipelines.

Dev & Engineering

Long-Horizon Prompting

Designs auditable launch briefs for autonomous agents and parallel multi-agent work on difficult, long-running tasks.

Dev & Engineering

Persistent Semantic Memory Design

Design durable, retrievable agent memory that scales from simple files to temporal knowledge graphs.

Dev & Engineering

Agent Tool Design Guide

Design tool interfaces agents can route, call, and recover from reliably.

Dev & Engineering

Context Compression Strategies

Compress long-running agent sessions while preserving files, decisions, risks, and next actions.

Dev & Engineering

Project Development Methodology

Decide whether an LLM fits the job, then design a staged agent pipeline with predictable parsing, iteration, and cost control.

Dev & Engineering

Autonomous Agent Harness

Designs autonomous agent loops that remain controlled, recoverable, and auditable.

Dev & Engineering

Context Engineering for Production Agents

A structured guide to designing, optimizing, and evaluating production agent systems with reliable context management.

Dev & Engineering

Self-Improvement Loops

Evolve agent harnesses, workflows, and context mechanisms under bounded, evidence-based evaluation.

Dev & Engineering

Context Engineering Fundamentals

Understand and shape reliable agent context through attention budgets, context-window mechanics, and signal-density principles.

Dev & Engineering

Latent Briefing

Share task-relevant orchestrator state with workers through task-guided KV-cache compaction when the inference runtime is controllable.

Dev & Engineering

Multi-Agent Architecture Patterns

Design multi-agent systems with context isolation, explicit handoffs, coordinated execution, and controlled failure handling.

Dev & Engineering

Context Degradation Diagnosis

Identify and mitigate lost attention, poisoning, distraction, confusion, and conflict in long agent contexts.

Dev & Engineering

BDI Mental State Modeling

Turn RDF context into explainable belief, desire, and intention chains.

Dev & Engineering

Rigorous Research Agent

A validation, recovery, and source-tracking protocol for multi-step research.

Dev & Engineering

Filesystem Context Engineering

Move large, durable, or shared agent context into files and retrieve it selectively when needed.

Dev & Engineering

Context Efficiency Optimizer

Reduce context cost with caching, masking, compaction, and partitioning while preserving answer quality.

Dev & Engineering

Agent Skill Blueprint

A reusable structure for authoring well-scoped context-engineering skills.

Productivity & Collaboration

Digital Brain Personal OS

Manage content, relationships, knowledge, and goals through structured files and AI.

Dev & Engineering

Reasoning Trace Optimizer

Diagnose context, tool, and instruction failures by analyzing agent traces and iteratively improving prompts.

Related skills