Narrative Evaluator Agent — Testing & QA agent for Claude Code
Reviews CFO narrative for support, audience fit, and unsupported claims after numerical QA.
How to install Narrative Evaluator Agent
Installs to ~/.claude/agents/mlobo2012-round-finance-agents-narrative-evaluator-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mlobo2012/round-finance-agents/HEAD/agents/narrative-evaluator-agent.md -o ~/.claude/agents/mlobo2012-round-finance-agents-narrative-evaluator-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Narrative Evaluator Agent does
name: narrative-evaluator-agent description: Reviews CFO narrative for support, audience fit, and unsupported claims after numerical QA. tools: Read, Grep, Glob
Narrative Evaluator Agent
You check the story after the numbers have been reviewed. You do not override numeric QA.
Inputs
contract.jsonsource_ledger.jsongenerator_output.mdor extracted PPTX contentnumerical_qa.jsonrevision_log.md
Outputs
narrative_eval.json- concise status summary
Alternatives in Testing & QA
- Civitai Test Review — Reviews the tests in a feature segment of the main Civitai Next.js app (src/) for whether they would actually 7.2k ★
- Review Code Quality — Reviews code changes for code quality, conventions, readability, DRY violations, error handling, test coverage 432 ★
- Writ Reviewer — Reviews an implementation diff in two passes (spec-compliance first, then code quality) 187 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Evaluator
Independently attempts to disprove implementation claims using acceptance criteria, tests, browser inspection,
Sub Agent Evaluator
PROACTIVELY used as gate G1 of the inner loop - the mechanical quality gate. MUST BE USED immediately after Co
Generator Agent
Drafts CFO artifacts while tagging every displayed number for independent QA.
Numerical QA Agent
Independently recomputes every displayed number and writes fail-closed numerical QA evidence.
AI Prompts
Design, test, and optimize AI prompts for NPCs, world generation, quest creation, and narrative elements. Use
Value Auditor
Enterprise demo QA auditor. Use for value proposition testing, narrative coherence, or data credibility checks
Related Skills
Useslidekit
Comprehensive presentation design skill for Claude Code. 33 reference modules covering audience-adaptive desig
Charlie CFO: Bootstrapped Financial Management
Your AI CFO for bootstrapped, profitable companies. Named after Charlie Munger, who embodied the principle tha
Cwc Long Running Agents
Claude Code's built-in /goal command gives you a generator/evaluator loop out of the box: set a completion con