Best use case
research-cite 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.
Generate properly formatted citation from research corpus
Teams using research-cite 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/research-cite/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How research-cite Compares
| Feature / Agent | research-cite | Standard Approach |
|---|---|---|
| Platform Support | Codex | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate properly formatted citation from 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.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
SKILL.md Source
# Research Cite Command Generate a properly formatted, policy-compliant citation from the research corpus. ## Instructions When invoked, generate a correct citation: 1. **Locate Source** - Search `.aiwg/research/sources/` and `.aiwg/research/findings/` for the specified reference - Match by REF-XXX identifier, author name, or keyword - If multiple matches, present options for user selection 2. **Load Metadata** - Extract frontmatter: ref_id, title, authors, year, DOI, source_type - Load quality assessment if available - Determine GRADE level 3. **Generate Citation** - Format @-mention citation with full path - Include page numbers if specified - Apply GRADE-appropriate hedging language - Include quality level annotation 4. **Output Formats** - `inline` - Ready to paste into markdown - `bibtex` - BibTeX format - `reference` - Full reference section entry ## Arguments - `[ref-id or keyword]` - REF-XXX identifier or search keyword (required) - `--format [inline|bibtex|reference]` - Output format (default: inline) - `--page [n]` - Include page reference - `--quote "[text]"` - Include direct quote ## Example ``` /research-cite REF-020 --page 4 Output: According to @.aiwg/research/findings/REF-020-tree-of-thoughts.md (p. 4), Tree of Thoughts enables "deliberate decision making" through systematic exploration of reasoning paths. GRADE: HIGH (peer-reviewed conference, NeurIPS 2023) Hedging: "demonstrates" / "shows" appropriate for HIGH quality evidence ``` ## References - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/rules/citation-policy.md - Citation enforcement rules - @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/frontmatter-schema.yaml - Source metadata - @.aiwg/research/docs/grade-assessment-guide.md - GRADE levels
Related Skills
research-workflow
Execute multi-stage research workflows
research-status
Show research corpus health and statistics
research-query
Search the local research corpus, read matching findings, and synthesize an answer with inline citations to REF-XXX sources. The "query" operation for the research pipeline.
research-quality
Assess source quality using GRADE methodology
research-quality-audit
Audit research corpus for shallow stubs, incomplete sections, missing source files, and doc depth issues. Detects docs written from abstracts rather than full papers and optionally auto-dispatches expansion agents.
research-provenance
Query provenance chains and artifact relationships
research-lint
Run the research corpus lint ruleset to detect structural and referential integrity issues — orphan notes, missing frontmatter, broken references, missing GRADE assessments.
research-gap
Analyze gaps in research coverage
research-gap-detect
Build the mutual citation graph, find connected components, identify isolated clusters, and optionally search for bridge candidates and file gap issues. Automates the manual cluster analysis workflow.
research-document
Generate summaries and literature notes from research papers
research-discover
Search for research papers across academic databases
research-archive
Package research artifacts for long-term archival