advanced-evaluation

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/advanced-evaluation/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete prompt templates, examples, and a validated pairwise workflow, supported by a well-structured reference layout. Its main weakness is mild prose padding in the intro and an orphaned script bundle that is not signaled from the overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tables, prompt templates, decision tree) but contains padded prose such as 'synthesizes research from academic papers, industry practices…' and the 'Key insight' framing that could be trimmed without losing substance.	3 / 5
Actionability	It provides copy-paste-ready prompt templates for direct scoring and pairwise comparison, a concrete decision tree, a metric-selection table, and full JSON input/output examples, covering the common cases executably.	5 / 5
Workflow Clarity	The pairwise comparison workflow is a clearly numbered 5-step sequence with an explicit consistency-check validation checkpoint and a tie/disagreement feedback loop, meeting the anchor for explicit validation and error-recovery loops.	5 / 5
Progressive Disclosure	The SKILL.md is an overview pointing to four well-signaled one-level-deep reference files (all verified to exist) with 'Read when' triggers, but the bundled scripts/evaluation_example.py is never referenced or navigated from the body, a minor organization gap.	4 / 5
	Total	17 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and names many concrete evaluation techniques with decent natural trigger terms, but it omits any explicit 'Use when…' guidance, which caps its completeness. Adding a concrete trigger clause would notably strengthen it.

Suggestions

Append an explicit 'Use when…' clause naming concrete triggering situations, e.g. 'Use when building LLM-as-judge systems, calibrating rubrics, or diagnosing bias in automated evaluation.'

Add natural synonyms users might say ('eval', 'benchmarking', 'automated scoring', 'human-LLM agreement') to broaden trigger coverage.

Reframe the opening away from 'This skill should be used for' toward a direct gerund/imperative style ('Evaluates LLM outputs using…') to match the strongest reference examples.

Dimension	Reasoning	Score
Specificity	The description enumerates seven concrete techniques ('LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment'), giving comprehensive coverage of the domain's actions.	5 / 5
Completeness	It clearly states what the skill does (the listed techniques) but provides no explicit 'Use when…' trigger clause, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural domain terms like 'LLM-as-judge', 'pairwise comparison', 'rubric calibration', and 'bias mitigation' are present, but common synonyms and variations (e.g. 'eval', 'benchmarking', 'human evaluation') are missing, so it is not quite comprehensive.	4 / 5
Distinctiveness Conflict Risk	'Advanced LLM evaluation' with LLM-as-judge/pairwise/rubric triggers carves a distinct niche, with only minor overlap risk against the sibling 'evaluation' skill referenced in the body.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
Path: skills/advanced-evaluation/SKILL.md
Commit: 6dbe1a1

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.