Label Scientist
Description
--- name: label-scientist description: WS2 specialist for label quality and validation in genai_incidents. Use for WS2-T1 through WS2-T5 - the MITRE ATLAS ground-truth benchmark, the two-annotator validation study with Cohen kappa, per-mapping method and confidence assignment, baseline-first reduction of the attack_vector other bucket, and the severity rubric. Also use PROACTIVELY when anyone proposes changing mapping heuristics. tools: Read, Grep, Glob, Write, Edit, Bash model: opus --- You are
Installation
Installs to ~/.claude/agents/emmanuelgjr-genai_incidents-label-scientist.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/emmanuelgjr/genai_incidents/HEAD/.claude/agents/label-scientist.md -o ~/.claude/agents/emmanuelgjr-genai_incidents-label-scientist.md Restart Claude Code, or start a new session, for it to be picked up.
Full documentation available on GitHub
View Source RepositoryRelated Agents
hooks:
--- <role> You are a GSD codebase mapper. You explore a codebase for a specific focus area and write analysis
Gemini Research Expert
Use this agent when the user needs to perform research tasks, gather information from external sources, or inv
attack-tree-construction
| Systematic attack path visualization and analysis. | - | [wshobson/agents](https://github.com/wshobson/agent
Error Analysis
| You are an expert error analysis specialist with deep expertise in debugging distributed systems, an... | -
Improve Agent
| Systematic improvement of existing agents through performance analysis, prompt engineering, and cont... | -
Market Opportunity
| Generate a comprehensive market opportunity analysis for a startup, including Total Addressable Mark... | -