Bib Search Citation

Capability Summary

Use this skill when the user provides a local .bib file and needs

research-oriented bibliography retrieval rather than a single citation-key lookup.

It is designed for large BibTeX/BibLaTeX libraries, including Zotero exports with

mixed standard and custom fields such as shorttitle, annotation, keywords,

abstract, file, DOI, URL, and eprint metadata.

The skill can:

• search by topic words and field-specific filters

• filter by author, year, entry type, DOI, arXiv/eprint, PDF, code, keywords,

annotation, or abstract

• return stable JSON for downstream tooling

• generate compact human-readable previews from JSON results

• emit LaTeX and Typst citation snippets

• return raw BibTeX only when exact export or manual verification requires it

Triggering

Use this skill for requests such as:

• "Search my .bib file for recent Mamba forecasting papers."

• "Find entries by Cheng after 2024 that have code and return cite snippets."

• "Show the raw BibTeX for the best TimeMachine match."

• "Filter Zotero-exported entries whose annotation mentions CodeAvailable."

• "Preview the JSON output from a saved bibliography search."

If the user gives only a natural-language request, infer a conservative search

spec and state the assumptions. If the user gives a compact filter expression,

preserve it as closely as possible instead of translating it into vague prose.

Do Not Use

Do not use this skill for:

• validating citations already used inside a .tex or .typ project

• compiling, formatting, or diagnosing manuscript source trees

• rewriting related-work prose

• online literature discovery when there is no local bibliography file

• inventing missing bibliographic metadata that is not present in the .bib file

For manuscript citation integrity, use the relevant writing skill's bibliography

module. For online paper discovery, use a research-oriented workflow and verify

metadata from external sources before adding it to a library.

Module Router

Module

Best for

Command

query

one-shot compact search with inline filters

uv run python -B $SKILL_DIR/scripts/search_bib.py --bib references.bib --query 'mamba forecasting author:Cheng year>=2024 has:code cite:both limit:5'

spec-json

structured search spec generated from a complex request

uv run python -B $SKILL_DIR/scripts/search_bib.py --bib references.bib --spec-json '{"query":"mamba forecasting","filters":{"year_min":2024},"citation_mode":"both"}'

spec-file

repeatable saved search workflow

uv run python -B $SKILL_DIR/scripts/search_bib.py --bib references.bib --spec-file search.json

preview

compact human-readable summary after JSON search output exists

uv run python -B $SKILL_DIR/scripts/preview_bib_search.py --input results.json

Keep search_bib.py as the source of truth for parsing, filtering, scoring,

sorting, raw BibTeX preservation, and citation snippet generation. Treat

preview_bib_search.py as a renderer only.

Required Inputs

Minimum inputs:

• path to one local .bib file

• either a compact --query, inline --spec-json, or saved --spec-file

• optional sort, limit, citation-mode, raw BibTeX, or returned-field preferences

Common search spec fields:

• query: free-text topic query

• filters.year_min, filters.year_max, filters.years_in, filters.exclude_years

• filters.author_contains, filters.author_excludes

• filters.type_in, filters.exclude_type_in

• filters.has, filters.exclude_has

• filters.field_contains, filters.field_excludes

• sort: relevance, year_desc, year_asc, or title

• limit: default 5 unless the user asks for more

• return_fields: fields to expose in the JSON result

• include_raw_bib: true only when the user asks for original entries or exact export

• citation_mode: latex, typst, both, or none

Output Contract

When presenting results to the user, use this order:

• Briefly state how many matches were found and which filters were applied.

• List top matches with requested research fields.

• Include LaTeX and/or Typst snippets when requested or useful.

• Include raw BibTeX only when requested or materially needed.

• If no entries match, suggest specific filter relaxations.

For each selected entry, usually include:

• citation key

• title and optional shorttitle

• authors

• year and venue/journal/booktitle

• DOI and/or eprint when present

• the supporting fields that made the entry relevant, such as keywords,

annotation, or a short abstract excerpt

If the user supplied compact filters, echo the interpreted filters when negation,

field filters, or mixed citation/export options could otherwise be ambiguous.

Workflow

• Identify the .bib file path. If multiple candidates exist, use the one the

user named or ask one concise clarification only if choosing would be risky.

• If rtk is available, use it only for model-facing exploration such as locating

.bib files or inspecting representative fields.

• Translate the request into a compact query or JSON search spec.

• Run search_bib.py with uv run python -B and preserve the JSON output.

• Optionally run preview_bib_search.py after JSON output exists.

• Inspect the result payload before answering.

• Report matches, citation snippets, raw entries, or empty-result recovery advice

according to the output contract.

RTK fast path guidance:

• locate bibliography files with rtk find . -name "*.bib"

• inspect a representative slice with rtk read /path/to/library.bib -l aggressive -m 80

• confirm fields with rtk grep "doi|keywords|annotation|eprint" /path/to/library.bib

• do not wrap machine-readable search_bib.py JSON output with RTK compression

Search Planning

Use these defaults unless the user says otherwise:

• research discovery request -> sort: relevance

• no explicit limit -> limit: 5

• no explicit field list -> return key, title, shorttitle, author, year,

venue, doi, eprint, keywords, annotation, and abstract

• asks for "original", "full entry", or "bib" -> include_raw_bib: true

• asks for citation snippets in a mixed LaTeX/Typst workflow -> citation_mode: both

Supported compact operators include:

• author:cheng

• year>=2024, year<=2025, year:2024, year:2023,2024

• type:article,misc, -type:misc

• has:code,doi, -has:pdf

• annotation:CodeAvailable, keywords:mamba, abstract:photovoltaic

• sort:year_desc, limit:10, fields:key,title,year,doi

• cite:latex, cite:typst, cite:both, cite:none

• raw:true

The useful has values are doi, abstract, keywords, annotation,

shorttitle, eprint, pdf, and code. The code flag is inferred from

fields such as url, abstract, keywords, annotation, note, and

howpublished when they mention GitHub, GitLab, code, repository, or source.

Safety Boundaries

• Do not fabricate missing titles, authors, venues, DOIs, URLs, or eprint IDs.

• Treat raw BibTeX as source data; preserve it exactly when quoting or exporting.

• Do not claim an entry strongly supports a manuscript claim unless the relevant

fields actually support that relationship.

• If the .bib file is malformed, report that entries may have been skipped

instead of silently presenting the result set as complete.

• Keep online discovery out of this skill unless the user explicitly asks to

extend beyond the local bibliography and the external metadata is verified.

• Do not edit the user's .bib file unless they explicitly ask for a rewrite or

export operation.

Reference Map

• scripts/search_bib.py: parses .bib files, applies filters, ranks results,

and formats citation snippets.

• scripts/preview_bib_search.py: renders search_bib.py JSON into a compact

human-readable summary.

• references/query-syntax.md: maps natural-language requests into compact query

expressions and JSON search specs.

• examples/compact-query.md: typical topic search with filters and citations.

• examples/raw-bib-export.md: exact-entry export workflow.

• examples/preview-summary.md: JSON search plus preview rendering workflow.

Example Requests

Search references.bib for Cheng papers after 2024 on Mamba forecasting and return both LaTeX and Typst citations.

Find entries in library.bib whose annotation contains CodeAvailable and show the raw BibTeX.

List the newest transformer forecasting papers in references.bib, but exclude misc entries and require DOI.

Find the best TimeMachine match in references.bib and return one raw entry plus cite snippets.

Error Handling

Parse errors

If a .bib file contains malformed entries, the script processes the valid

entries it can parse. When unexpectedly few entries are returned, inspect the

file encoding and look for obvious structural corruption such as missing closing

braces.

Empty result sets

When zero entries match, suggest broadening the search in this order:

• remove has: constraints such as has:code

• widen or remove the year range

• use fewer or shorter topic keywords

• check author spelling or try partial-name matches

Large files

The helper scripts use linear scans and no external parser dependency. For very

large libraries, expect proportionally longer runtime but the same JSON contract.