Reporting Specialist — Research agent for Claude Code
Use for generating evaluation reports, creating visualizations, and documenting findings.
How to install Reporting Specialist
Installs to ~/.claude/agents/homericintelligence-scylla-reporting-specialist.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/HomericIntelligence/Scylla/HEAD/.claude/agents/reporting-specialist.md -o ~/.claude/agents/homericintelligence-scylla-reporting-specialist.md Restart Claude Code, or start a new session, for it to be picked up.
What Reporting Specialist does
name: reporting-specialist description: Use for generating evaluation reports, creating visualizations, and documenting findings. Invoked for producing benchmark reports and analysis summaries. tools: Read,Write,Edit,Bash,Grep,Glob model: sonnet
Reporting Specialist Agent
Role
Level 3 Specialist responsible for generating evaluation reports and visualizations. Creates clear, comprehensive reports of benchmark results and analysis findings.
Hierarchy Position
- Level: 3 (
Alternatives in Research
- Skill — Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis 31.7k ★
- Braintrust Analyst Agent — You are a specialized analysis agent 3.6k ★
- Fable Worker Sonnet — Fable stage worker for tasks needing real reasoning — research synthesis, nontrivial code, analysis, document 837 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Paper Analysis
Fetches one paper and reports its claim, method, and rigor check. Dispatched once per paper by paper-research,
Chief Evaluator
Use for strategic evaluation decisions, tier selection, methodology oversight, and cross-domain coordination.
Finding Extractor
Extracts atomic, testable findings from a single research paper. Invoked alongside lite-drafter and metadata-e
Report Compiler Agent
Transforms research findings into polished APA 7.0 academic reports; activated in Phase 4 and Phase 6
Explore Manager
WF-MAX Manager for W0 exploration wave. Spawns 5-10 read-only researchers/explorers, synthesizes findings, rep
Deltacodecube
DeltaCodeCube Analysis - codebase quality scoring, architecture analysis, and visualizations. Use proactively
Related Skills
Work Spike
Run the spike work items in the active release — investigation only, producing one Findings/Recommendations do
Researcher Writing Profiler
A Claude Code skill that analyzes a researcher's publication record and writing style from Google Scholar, pro
Cc Judge
Shared LLM-evals framework for running Claude Code agents in containers, scoring outcomes with an LLM judge, a
