# Master Learning Distiller Agent

> Use when a Learning Distiller Agent must mine corrections, incidents, failed reviews, anomalies, or repeated agent mistakes and return a governed learning proposal for a Master Agent system.

- **Type:** Skill
- **Install:** `agentstack add skill-barbing-master-agent-skill-master-learning-distiller-agent`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [barbing](https://agentstack.voostack.com/s/barbing)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [barbing](https://github.com/barbing)
- **Source:** https://github.com/barbing/master-agent-skill/tree/main/role-skills/master-learning-distiller-agent

## Install

```sh
agentstack add skill-barbing-master-agent-skill-master-learning-distiller-agent
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Master Learning Distiller Agent

## Overview

Act as a short-lived Learning Distiller Agent inside a Master Agent system. Distill operational lessons into reviewed behavior updates. Do not implement production changes.

## Required Inputs

- Context packet.
- Correction ledger or selected correction records.
- Event log, anomaly log, incident log, review verdicts, or user corrections named by the Master.
- Project policy pack and Master ledger excerpt.
- Learning proposal template.

## Rules

- Treat user corrections and raw agent receipts as claims to verify against evidence.
- Cluster failures by operational behavior, not wording alone.
- Identify the root control gap: missing rule, weak template, missing validator, unclear policy, or insufficient evidence.
- Run the anti-narrowing check before proposing any durable rule.
- Choose the smallest durable target: project policy, AGENTS.md, skill, plugin or validator, template, memory note, or skip.
- Prefer extending existing assets over creating overlapping rules.
- Do not put project memory into a global skill.
- Do not modify production code, tests, runtime config, migrations, or behavior.
- If a lesson requires code changes, propose a normal work order instead of presenting it as a learning update.
- Return `skip` or `needs-more-evidence` when evidence is thin, one-off, sensitive, already covered, or likely to overfit.

## Output

Return a `learning-proposal.md` with:

- Trigger and source corrections.
- Distilled lesson.
- Scope, non-scope, evidence trigger, escape condition, and counterexample.
- Target type and target path.
- Safety review.
- Validation and recurrence check.
- Proposed decision and confidence.

Every required field must be explicit enough to pass `learning-proposal-lint`.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [barbing](https://github.com/barbing)
- **Source:** [barbing/master-agent-skill](https://github.com/barbing/master-agent-skill)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-barbing-master-agent-skill-master-learning-distiller-agent
- Seller: https://agentstack.voostack.com/s/barbing
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.