Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/uynajgi-citation-tracking
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/citation-tracking
What's inside
- Skill name
citation-tracking- Description
- Track and analyze citation relationships between papers. Use this skill whenever the user asks "who cites this?", "what does this paper reference?", "find related work", "are these papers connected?", "show me the citation graph", "check my citations", or wants to discover papers that share references but don't cite each other (knowledge frontier signal). Also use when the user mentions "shared references", "citation neighborhood", "verify citations", wants to check if their writing properly cites papers in the library, or needs to explore the intellectual lineage of a research area. Trigger proactively whenever the user discusses citation relationships, asks about paper-to-paper connections, or wants to validate reference lists.
- License
- MIT
- Instructions
- 76 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Citation Tracking Analyze citation relationships to map the knowledge frontier. The citation graph reveals hidden connections, missing links between research communities, and shared intellectual heritage. ## Prerequisites Papers must be ingested (`paper-ingest` skill). For `check-citations`, the local library should have papers with known DOIs for matching. ## Workflow ### Step 1: Basic citation queries ```bash drbrain citations p3f8a2 # both refs and citing papers drbrain citations p3f8a2 --type refs # only what this paper references drbrain citations p3f8a2 --type citing # only papers that cite this one drbrain citations p3f8a2 --type all --json # full structured output ``` ### Step 2: Shared-reference analysis (frontier signal) ```bash drbrain citations p3f8a2 --type shared-refs ``` Papers marked `unlinked` share references but don't cite each other. This is a knowledge frontier signal: two groups working on the same problem, reading the same literature, but unaware of each other. High `shared_count` with `unlinked` status indicates: - Parallel discovery worth investigating - Literature review opportunities that bridge communities - Potential duplicated effort ### Step 3: Citation verification Check if in-text citations in writing match papers in the library: ```bash drbrain check-citations "Smith (2023) proposed a method that Jones et al. (2022) extended." drbrain check-citations --file draft.txt ``` Output shows matched and unmatched citations. Unmatched ones may exist under a different name variant or need ingest. ### Step 4: Workspace-scoped analysis ```bash drbrain citations p3f8a2 --type shared-refs --workspace attention-methods ``` ## Examples **Find unlinked papers that share references (frontier detection):** ```bash drbrain citations p3f8a2 --type shared-refs --json | jq '.[] | select(.status == "unlinked")' ``` **Verify a draft's citations against the library:** ```bash drbrain check-citations --file intro-draft.txt ``` ## CLI Reference | Command | What it does | |---------|--------------| | `drbrain citations <id>` | Both refs and citing papers | | `drbrain citations <id> --type refs` | References only | | `drbrain citations <id> --type citing` | Papers citing this one | | `drbrain citations <id> --type shared-refs` | Shared-reference frontier signals | | `drbrain citations <id> -w <ws>` | Workspace-scoped citation analysis | | `drbrain check-citations "<text>"` | Verify in-text citations | | `drbrain check-citations --file <path>` | Verify citations in a file |
From UynajGI/drbrain, MIT.
More from UynajGI/drbrain
- 0.529score
neat-freak
UynajGI
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots.
SkillBFreshness: BClaude Code +9 - 0.524score
kg-build
UynajGI
Build the knowledge graph from ingested papers — 5-stage LLM extraction, TransE graph embeddings, and rule-based closure inference.
SkillBFreshness: BClaude Code +9 - 0.524score
audit
UynajGI
Scan the entire library for data quality issues across 15 severity-graded rules.
SkillBFreshness: BClaude Code +9 - 0.524score
fsearch
UynajGI
Search local evidence and external sources (arXiv) in one command, with ingested annotation.
SkillBFreshness: BClaude Code +9 - 0.524score
graph
UynajGI
Direct knowledge graph operations — traverse neighbors, find shortest paths, and analyze shared concepts across papers.
SkillBFreshness: BClaude Code +9 - 0.524score
index
UynajGI
Prepare, inspect and verify the searchable index.
SkillBFreshness: BClaude Code +9 - 0.524score
ingest-link
UynajGI
Ingest web URLs and online PDFs by extracting rendered content via an external qt-web-extractor service.
SkillBFreshness: BClaude Code +9 - 0.524score
kg-reason
UynajGI
Reason over the knowledge graph using LLM agents — natural language Q&A and tool-calling iterative reasoning with bidirectional LLM↔KG validation.
SkillBFreshness: BClaude Code +9 - 0.474score
document
UynajGI
Inspect Office documents (DOCX, PPTX, XLSX) and output structured text summaries.
SkillCFreshness: CClaude Code +9 - 0.474score
enrich
UynajGI
Enrich paper metadata by backfilling missing fields from CrossRef and detecting records that need cleanup.
SkillCFreshness: CClaude Code +9 - 0.474score
explore
UynajGI
Manage explore silos — lightweight literature discovery collections separate from the main library.
SkillCFreshness: CClaude Code +9 - 0.474score
export
UynajGI
Export papers to BibTeX, RIS, or Markdown format.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 17, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/UynajGI/drbrain
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from UynajGI
- 0.529score
neat-freak
UynajGI
End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code so nothing rots.
SkillBFreshness: BClaude Code +9 - 0.524score
graph
UynajGI
Direct knowledge graph operations — traverse neighbors, find shortest paths, and analyze shared concepts across papers.
SkillBFreshness: BClaude Code +9 - 0.524score
kg-build
UynajGI
Build the knowledge graph from ingested papers — 5-stage LLM extraction, TransE graph embeddings, and rule-based closure inference.
SkillBFreshness: BClaude Code +9 - 0.524score
fsearch
UynajGI
Search local evidence and external sources (arXiv) in one command, with ingested annotation.
SkillBFreshness: BClaude Code +9 - 0.524score
audit
UynajGI
Scan the entire library for data quality issues across 15 severity-graded rules.
SkillBFreshness: BClaude Code +9 - 0.524score
index
UynajGI
Prepare, inspect and verify the searchable index.
SkillBFreshness: BClaude Code +9
Cite this page
citation-tracking skill. Agent Mart. https://agentmart.dev/skills/uynajgi-citation-tracking (last updated 2026-10-24)