Codex

verify-citations

Verify all citations in a document against the research corpus

104 stars

byjmagly

View on GitHub Installation ↓

Best use case

verify-citations is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

It is a strong fit for teams already working in Codex.

Verify all citations in a document against the research corpus

Teams using verify-citations should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/verify-citations/SKILL.md --create-dirs "https://raw.githubusercontent.com/jmagly/aiwg/main/.agents/skills/verify-citations/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/verify-citations/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How verify-citations Compares

Feature / Agent	verify-citations	Standard Approach
Platform Support	Codex	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Verify all citations in a document against the research corpus

Which AI agents support this skill?

This skill is designed for Codex.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

Cursor vs Codex for AI Workflows

Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.

AI Agents for Startups

Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.

SKILL.md Source

# Verify Citations Command

Validate that all citations, references, and factual claims are backed by actual sources in the research corpus.

## Instructions

When invoked, perform systematic citation verification:

1. **Parse Target File**
   - Load the specified file (or all markdown files if no path given)
   - Extract all citation patterns:
     - `@.aiwg/research/sources/*` references
     - `@.aiwg/research/findings/*` references
     - `REF-XXX` inline references
     - DOI patterns (`10.XXXX/...`)
     - Author-year patterns (`Author et al., YYYY`)

2. **Verify Each Citation**
   - Check file existence for @-mention references
   - Validate REF-XXX against frontmatter in corpus
   - Verify DOI format validity
   - Check page number ranges
   - Validate quoted text against source

3. **Detect Hallucinations**
   - Flag citations to non-existent files
   - Flag fabricated DOIs
   - Flag statistics without sources
   - Flag author names not in corpus

4. **Check GRADE Compliance**
   - Load quality assessment for each cited source
   - Compare hedging language to evidence quality
   - Flag overclaiming (HIGH-confidence language for LOW evidence)

5. **Generate Report**
   - Display summary table (total, valid, issues)
   - List each issue with severity and fix suggestion
   - Provide overall PASS/FAIL verdict

6. **Auto-Fix Mode (--fix)**
   - Downgrade hedging language for GRADE violations
   - Remove citations to non-existent sources (with comment)
   - Add TODO markers for sources needing verification

## Arguments

- `[file-path]` - File to verify (default: all `.md` files in current directory)
- `--strict` - Treat warnings as errors
- `--fix` - Automatically fix GRADE violations and remove hallucinated citations
- `--report` - Save report to `.aiwg/reports/citation-verification.md`
- `--corpus-only` - Only check @-mention references, skip author-year patterns

## References

- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/citation-policy.md - Citation enforcement rules
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/agents/citation-verifier.md - Citation Verifier agent
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/citation-audit.yaml - Audit schema
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/hallucination-detection.yaml - Detection patterns

Related Skills

verify-archive

104

from jmagly/aiwg

Verify archive integrity with self-verifying SHA-256 checksums, generate VERIFY.md, and optionally create W3C PROV provenance

Codex

aiwg-orchestrate

104

from jmagly/aiwg

Route structured artifact work to AIWG workflows via MCP with zero parent context cost

venv-manager

104

from jmagly/aiwg

Create, manage, and validate Python virtual environments. Use for project isolation and dependency management.

pytest-runner

104

from jmagly/aiwg

Execute Python tests with pytest, supporting fixtures, markers, coverage, and parallel execution. Use for Python test automation.

vitest-runner

104

from jmagly/aiwg

Execute JavaScript/TypeScript tests with Vitest, supporting coverage, watch mode, and parallel execution. Use for JS/TS test automation.

eslint-checker

104

from jmagly/aiwg

Run ESLint for JavaScript/TypeScript code quality and style enforcement. Use for static analysis and auto-fixing.

repo-analyzer

104

from jmagly/aiwg

Analyze GitHub repositories for structure, documentation, dependencies, and contribution patterns. Use for codebase understanding and health assessment.