# Trace Citations

> Trace the citation neighborhood around one focal paper into foundations, descendants, bridges, weak edges, and optional second-hop links

- **Type:** Skill
- **Install:** `agentstack add skill-zongmin-yu-semantic-scholar-skills-trace-citations`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [zongmin-yu](https://agentstack.voostack.com/s/zongmin-yu)
- **Installs:** 0
- **Category:** [Search](https://agentstack.voostack.com/c/search)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [zongmin-yu](https://github.com/zongmin-yu)
- **Source:** https://github.com/zongmin-yu/semantic-scholar-skills/tree/main/skills/trace-citations

## Install

```sh
agentstack add skill-zongmin-yu-semantic-scholar-skills-trace-citations
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Trace Citations

Map the citation graph around one focal paper into useful buckets.
Use this when the human wants lineage, influence, and strong versus weak citation edges around a paper.

## Arguments

- The positional argument is the focal paper query. Quote multi-word titles.
- `--depth 1|2` controls whether to expand a second hop from the strongest first-hop edges.
- `--max-references ` and `--max-citations ` cap the first-hop fetch sizes.
- `--second-hop-limit ` caps how many first-hop anchors get expanded at depth two.

## Workflow

1. Run `python scripts/run.py ...`.
2. Read `result.foundations` for strong references behind the focal paper.
3. Read `result.direct_descendants` for strong citing descendants.
4. Read `result.bridge_nodes` for medium-confidence connectors with rich context or intent signal.
5. Read `result.weak_edges` for low-signal edges that are probably less useful.
6. If `depth=2`, read `result.second_hop` only after the first-hop picture looks sensible.

## Output

- The script prints the unified JSON envelope described in `output_contract.md`.
- The underlying workflow result is `CitationTraceResult.to_dict()`.
- `result.reference_count_examined` and `result.citation_count_examined` show the first-hop search breadth.

## When To Escalate

- The focal paper resolves incorrectly.
- The API returns very sparse context and intent data, making edge interpretation weak.
- The first-hop graph is too noisy and needs a tighter focal paper choice before going to depth two.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [zongmin-yu](https://github.com/zongmin-yu)
- **Source:** [zongmin-yu/semantic-scholar-skills](https://github.com/zongmin-yu/semantic-scholar-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-zongmin-yu-semantic-scholar-skills-trace-citations
- Seller: https://agentstack.voostack.com/s/zongmin-yu
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.