mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers
cs.AI
Submitted: 2026-08-31
Updated: 2026-08-31
Comments: 42 pages, 6 figures. Toolkit and expert profiles: https://github.com/K-Dense-AI/mimeo
Code: https://github.com/K-Dense-AI/mimeo
License: http://creativecommons.org/licenses/by/4.0/
The gist: Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides.
Terminology
Abstract
Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides. These are different claims. We test each one. mimeo is an open-source tool that finds a person's public work, checks each extracted quotation against the cached source text, and writes a file an agent can load. Eight logged builds averaged 38 model calls; the check rejects 13.2% of extracted quotations. We tested four expert files with one coding-agent harness. Knowledge access was clearest: mimeo answered all 20 obscure, quotation-heavy questions; no closed-book condition answered more than 10. Keyword search (BM25) over the same pages answered 15-17, a gap this sample cannot resolve. Grounding showed one clear benefit: personas written from model memory misstated a documented position on 1-4 of 20 answers under every grader; the plain agent and mimeo never did. Every persona was easy to spot on short open prompts, and adding task material lowered identification by 18-23 points. mimeo was no more identifiable than a from-memory profile. Judgment transfer remained unresolved because both tests hit their ceiling: every condition found 94-97% of the problems planted in engineering tasks and scored 94-100% on 16 new application scenarios. An AI-judged "sounds like the expert" score changed with the judge: two of four preferred answers based on a model's stereotype, while two found no difference on the same text. That is a caution against relying on a single AI judge. The evidence supports mimeo as a compact, inspectable reference on a person, not as a demonstrated transfer of their judgment. Toolkit and expert profiles: https://github.com/K-Dense-AI/mimeo
Sources
- ExpertPrompting: Instructing Large Language Models to be Distinguished Experts
- When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
- Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
- AI Can Learn Scientific Taste
- Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior
- Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM
- Representation Engineering: A Top-Down Approach to AI Transparency
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills
- Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents
- Knowledge Activation: AI Skills as the Institutional Knowledge Primitive for Agentic Software Development
- Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents
- Agent Skill Evaluation and Evolution: Frameworks and Benchmarks
- CODESKILL: Learning Self-Evolving Skills for Coding Agents
- SkillGen: Verified Inference-Time Agent Skill Synthesis
- SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
- Teaching language models to support answers with verified quotes
- Self-Preference Bias in LLM-as-a-Judge
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection