RichardHightower

RichardHightower/reliable-agentic-lab

Agent

Scores a finished white paper against a fixed rubric and reports whether it is done. Holds no write tool.

RichardHightower/reliable-agentic-lab

Agent

Turns one topic into a white paper outline, the questions that outline needs answered, and the figures worth drawing. Runs once, at the start of a run.

RichardHightower/reliable-agentic-lab

Agent

Answers one research question from primary sources and returns the atomic claims it found, each attached to a source and a quote. Writes nothing.

RichardHightower/reliable-agentic-lab

Agent

Independently checks one claim against a source it finds itself. Never sees the original research. Writes nothing.

RichardHightower/reliable-agentic-lab

Agent

Writes one section of the white paper from verified claims only. Writes under sections/ and nothing else. Assembly owns paper.md.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Produce an evidence-backed technical white paper from one topic. Plans the paper, researches each question from primary sources, verifies every claim against a second independent source, renders the figures, writes the sections, and checks the result before it ships.

RichardHightower/reliable-agentic-lab

MCP server Claude CodeCodexCursor

Context7's hosted MCP server: up-to-date library documentation and code examples on demand. Remote server at mcp.context7.com.

RichardHightower/reliable-agentic-lab

MCP server Claude CodeCodexCursor

Real-time web search, reasoning, and research through Perplexity's API. Runs locally from the @perplexity-ai/mcp-server npm package. Needs 1 environment variable to run.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Draw mermaid and plantuml sources for the concepts that need a picture.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Retrieve primary sources and report what they actually say.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Grade a draft against the rubric. Name failing rows and nothing else.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Cross-check important claims against a second, independent source.

RichardHightower/reliable-agentic-lab

Skill Claude CodeCodex

Write technical white paper prose from bound claims only.

RichardHightower/reliable-agentic-lab

Agent

Repairs the application code until a failing suite passes. Writes under app/ and nothing else, and cannot reach the tests.

RichardHightower/reliable-agentic-lab

Agent

Scores one repair attempt and reports whether the branch is genuinely fixed. Holds no write tool.