foundry-works

foundry-works/foundry-research

Agent

Audit draft reports for clarity, accessibility, and plain-language style without changing meaning or weakening scientific accuracy.

foundry-works/foundry-research

Agent

Audit draft reports for internal contradictions, unsupported claims, missing context, and citation integrity.

foundry-works/foundry-research

Agent

Draft research reports from source notes. Produces theme-based synthesis with verified citations.

foundry-works/foundry-research

Hook

Runs when a session starts, executing bootstrap-venv.sh via bash. From foundry-works/foundry-research.

foundry-works/foundry-research

Skill Claude CodeCodex

Revision orchestrator that takes an existing research session and runs a structured review-then-revise cycle to improve accuracy, correctness, and clarity. Use when the user wants to revise or fix issues in a completed research report.

foundry-works/foundry-research

Skill Claude CodeCodex

Deep research agent that searches academic databases, downloads sources, and produces structured evidence-backed reports. Use when the user asks for deep research, literature review, systematic investigation, or any question requiring multiple sources and synthesis.

foundry-works/foundry-research

Skill Claude CodeCodex

Pipeline improvement planner that analyzes multiple research sessions to identify systemic patterns and produce actionable improvement plans. Use when the user wants to improve the research pipeline based on past session performance.

foundry-works/foundry-research

Skill Claude CodeCodex

Research quality evaluator that analyzes session artifacts and produces structured quality assessments with scores and recommendations. Use when the user asks to evaluate, reflect on, review, or score a completed deep-research session.