economist-agents

This directory contains YAML configuration files for all agents in the economist-agents pipeline.

Agent YAML configurations — both the generic public templates and any

Rules for writing, numbering, and superseding Architectural Decision Records. Use when creating a new ADR, when changing an ADR's status, when consolidating or auditing the ADR tree.

Rules for assigning stories to the correct agent runtime with appropriate constraints. Use when planning sprint assignments, when deciding between Claude Code / Copilot / Human for a story, when launching parallel sub-agents.

Log every agent's inputs, outputs, and decisions as structured JSON for end-to-end auditing. Use when adding trace logging to a pipeline stage, when diagnosing a failed article, when the editorial judge needs pipeline context in a GitHub issue.

Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

Reference patterns for designing and reviewing CrewAI multi-agent systems. Use when designing a new crew or flow, reviewing a proposed agent configuration, or auditing an existing system against industry conventions.

Score articles on 5 quality dimensions with deterministic metrics and persist for trend tracking. Use when evaluating a generated article, when tuning scoring rubrics, when adding a new quality dimension.

Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.

Codify editorial failure patterns as deterministic prevention rules. Use when a new bug pattern is detected by the editorial judge, when adding post-mortem rules after a defective article ships.

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when deciding whether to maintain or sunset existing code.

Infrastructure automation, CI/CD pipeline health, and GitHub Projects integration. Use when configuring CI workflows, when setting up GitHub Projects, when automating sprint visibility, when debugging deployment pipelines.

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

Define the writing standard for every article in the content pipeline. Use when configuring the Writer Agent, when reviewing article prose quality, when tuning the deterministic polish stage.

Define visual standards for featured images and charts in the content pipeline. Use when generating a DALL-E featured image, when creating chart specifications, when reviewing visual quality of a generated article.

Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.

Refines ideas iteratively. Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

Standards for building MCP servers in this project. Use when creating a new MCP server, when reviewing MCP server code, when debugging import or tool registration issues.

Track article quality metrics over time and alert on degradation. Use when adding a new metric to the quality dashboard, when investigating a quality trend, when configuring alert thresholds.

Optimizes application performance. Use when performance requirements exist, when you suspect performance regressions, or when Core Web Vitals or load times need improvement. Use when profiling reveals bottlenecks that need fixing.

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Python coding standards for the economist-agents multi-agent pipeline. Use when writing new Python code, when reviewing PRs for code quality, when configuring linting and type checking.

Multi-layer quality gate strategy for automated checks at commit, push, and PR levels. Use when configuring pre-commit hooks, when setting up CI workflows, when debugging why a commit or push was blocked.

Enforce source freshness, diversity, and attribution standards for article research. Use when configuring the Research Agent, when evaluating source quality in articles, when adding new source discovery integrations.

Sprint orchestration, ceremony enforcement, and data-driven performance tracking. Use when running sprint ceremonies, when enforcing Definition of Ready/Done, when tracking sprint metrics, when managing blockers.

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.

Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

Grounds every implementation decision in official documentation. Use when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.

GitHub-integrated sprint lifecycle management with automated sync. Use when starting a sprint, when syncing sprint status with GitHub, when closing a sprint with retrospective.

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

Testing patterns for the economist-agents multi-agent system. Use when writing tests for agent code, when mocking API calls, when setting up test fixtures, when debugging coverage gaps.

Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

Use when validating Economist-style charts for publication. Defines the 5-gate rubric, approved palette, and common failure patterns. Referenced by visual-qa-agent and any pipeline that auto-rejects charts.

GitHub MCP for PR management, issues, and repository operations

Browser automation for navigating web UIs, taking screenshots, and interacting with pages

Scores article drafts across 5 quality dimensions and returns a pass/fail verdict before publishing

Query and update the ChromaDB-backed style memory store for Economist voice consistency

Publication validation — checks front-matter fields (layout, title, date, author, categories, image) and image-path existence before a post is published

Web search (Serper/Google), Google Scholar, arXiv academic search, and page fetching as MCP tools

DALL-E 3 image generation for the content pipeline

Query the published article archive for topic similarity and duplicate detection before commissioning new content