---
title: "Post-hoc skill analyzer: review, role & definition · Undominated.ai"
canonical: https://undominated.ai/agents/anthropic-skill-analyzer/
description: "Skill-creator agent that reads a finished blind comparison, then opens both skills and transcripts to say why the winner won."
---

# Post-hoc skill analyzer: review, role & definition · Undominated.ai

> Skill-creator agent that reads a finished blind comparison, then opens both skills and transcripts to say why the winner won.

[← Explore all agents](/agents/)

EVALUATION / Anthropic

# Post-hoc skill analyzer

Skill-creator agent that reads a finished blind comparison, then opens both skills and transcripts to say why the winner won.

 [Use this definition ↓](#setup)[Original source ↗](https://github.com/anthropics/claude-plugins-official/tree/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/plugins/skill-creator/skills/skill-creator/agents)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 2 linked sources
 Publisher Anthropic
 Licence [Apache-2.0 ↗](https://github.com/anthropics/claude-plugins-official/blob/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/plugins/skill-creator/LICENSE)
 Revision 8bd00f08f0b0
 [Read what was—and wasn’t—checked ↓](#review)

“Runs after the comparator has chosen A or B, reads winner and loser paths, and writes improvement notes to output_path.”

 [Anthropic · upstream description ↗](https://github.com/anthropics/claude-plugins-official/blob/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/plugins/skill-creator/skills/skill-creator/agents/analyzer.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The catalogue has the skill-creator grader and not this post-hoc analyzer.
- The file is explicit that it runs only after a blind winner exists, so it is not a second copy of the comparator.

### A good fit for

 - Explaining a completed A/B skill comparison
- Writing improvement notes for the losing skill
- Supply blinded-run comparison evidence or benchmark results with the appropriate analysis mode.
- Return grounded improvement hypotheses for comparison analysis or cross-run patterns for benchmark analysis.

### Weigh up before choosing

 - This review did not execute the agent.
- The file spells the reveal step unblids; that spelling was not corrected.
- No sample transcripts were supplied.
- Post-hoc explanations are hypotheses rather than causal proof; benchmark-mode descriptive analysis must not be silently converted into a skill-quality verdict.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/skill-creator/skills/skill-creator/agents/analyzer.md
- plugins/skill-creator/LICENSE
- Round 2: pinned definition, output contract and permission/dependency boundaries reread on 2026-10-14

### Our findings

 - The agent receives winner, both skill paths, both transcript paths, the comparator JSON, and an output path.
- It reads the comparator result before it reads the skills, then looks at instruction specificity, tool use, examples, and edge cases.
- The file says it unblids the comparison by reading the skills and transcripts after the blind winner is known.
- The comparison mode examines instruction, tooling, example and reference differences after seeing the winner.
- The benchmark mode forbids improvement recommendations and instead highlights nondiscriminating assertions, variability and quality/cost patterns.

### Not established by this review

 - The agent was not executed.
- No transcript was read with it.
- No output file was written.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Use the role in your project.

[Upstream setup instructions ↗](https://github.com/anthropics/claude-plugins-official/blob/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/README.md)
 - No concrete install command without a placeholder is in the marketplace README.
- This agent is invoked by the skill-creator evaluation flow, which was not run.
- Keep the task mode explicit and retain all run evidence, failed cases and scoring definitions before interpreting an apparent winner.

### Before you start

 - A finished blind comparison with paths to both skills and transcripts
- Claude Code skill-creator

### Compatibility

Claude Code · skill-creator

### Reads eval artifacts and writes analysis

 - Read both skills, both transcripts, and the comparator JSON
- Write the analysis to output_path

### Cost model

Apache-2.0 in plugins/skill-creator/LICENSE

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [analyzer.md ↗](https://github.com/anthropics/claude-plugins-official/blob/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/plugins/skill-creator/skills/skill-creator/agents/analyzer.md) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/plugins/skill-creator/skills/skill-creator/agents/analyzer.md Supports: post-hoc role and inputs
- [skill-creator LICENSE ↗](https://github.com/anthropics/claude-plugins-official/blob/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/plugins/skill-creator/LICENSE) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/8bd00f08f0b04705e610cf132fbe2cf5ec44cfe3/plugins/skill-creator/LICENSE Supports: Apache-2.0

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Skill eval grader ↗ Grades each expectation pass or fail from cited evidence, treats uncertainty as a failure, and writes grading.json.](/agents/anthropic-skill-eval-grader/)[### Agent evaluator ↗ Scores an agent answer on five axes and requires evidence for the score.](/agents/ecc-agent-evaluator/)[### Blind skill-output comparator ↗ Compares two anonymized task outputs against an explicit content and structure rubric, then writes a reasoned comparison JSON.](/agents/anthropic-skill-eval-comparator/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Find reusable instructions](/skills/)
- [Inspect connections](/mcp-servers/)
- [Build a toolkit](/tools/)
- [Choose the model](/compare/)
