Agent skills for Codex CLI

Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper…

Verify citations against the research corpus to prevent hallucinated references and enforce GRADE compliance

APPLIES/consumes a `citation-diversifier` budget report (`output/CITATION_BUDGET_REPORT.md`) to inject *in-scope* citations into an…

Use when formatting a PMLA (Publications of the Modern Language Association) essay in MLA style — in-text parenthetical citations keyed to…

For citation style in legal writing: establishes the legal standard, burden of proof, and counterargument; result: test product with risk…

For citizen's income — dispute with the job center: clarifies norm, burden of proof and counter-argument; result: test product with risk…

Automate Claid AI tasks via Rube MCP (Composio).

Rewrite `outline/claim_evidence_matrix.md` as a projection/index of evidence packs (NO PROSE), so claims/axes are driven by…

Configure, validate, run, and troubleshoot CLAM attention heatmap

Diagnose and fix Clari API errors including auth failures, export issues,

Configure Clari API authentication with API key and set up export access.

Secure Clari API tokens and implement data handling best practices.

Separates core objectives from proposed solutions and constraints before coding to prevent scope creep and misaligned implementations.

Make user-facing narrative text clear, precise, concise, and useful.

Pre-ingestion verification for epistemic quality in RAG systems.

Maintain and migrate langchain-classic legacy chains, retrievers,

Enriched IAB classification — returns audience categories plus topics, keywords, and inferred intent.

Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude…

Provides specialized prompt engineering patterns and optimization strategies tailored for Claude Opus 4.7 and legacy model architectures.

Use when Codex should ask Claude CLI for an adversarial challenge review that pressure-tests implementation direction, design choices…

Use when creating or configuring Claude AI agents using the Agent SDK.