Agent skill

Search Bibtex

by steeliron550-ui in steeliron550-ui/search-bibtex

A skill your agent uses when the user provides one or more academic PDF files or an existing BibTeX file and wants the search-bibtex binary to extract metadata, fuzzy-search bibliographic sources…

MITAuto-check passedResearch & Science

Install Search Bibtex

skills CLI
$ npx skills add steeliron550-ui/search-bibtex --skill search-bibtex -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install steeliron550-ui/search-bibtex search-bibtex --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
search-bibtex
GitHub stars
115
Token cost
~885 tokens
SKILL.md length
344 words
Files
73 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user provides one or more academic PDF files or an existing BibTeX file and wants the search-bibtex binary to extract metadata, fuzzy-search bibliographic sources…

  • Works in 7 steps: Confirm the binary is available → Inspect PDF metadata and generated… → Search and rank candidates. In a TTY,… → …
  • The user provides one
  • SKILL.md covers Workflow, Source Priority, Interaction and Failure Handling
  • More academic PDF files

What it does

Search Bibtex is an agent skill from steeliron550-ui/search-bibtex. Use when the user provides one or more academic PDF files or an existing BibTeX file and wants the search-bibtex binary to extract metadata, fuzzy-search bibliographic sources, refresh BibTeX, rank candidates with configurable source priority, load defaults from config.toml, and present an interactive Vim-key selection UI. Handles computer science preprints, conference papers, and journal papers through an independent CLI; does not depend on Paperlib.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 76 other files, including scripts (for example `.github/workflows/build-binaries.yml`, `.github/workflows/release.yml` and `CHANGELOG.md`).

It sits in Research & Science, covering Citation management. It works with LaTeX. The repository describes itself as: [PolyCite] 基于多智能体协同、多源汇聚的论文引用元数据检索工具 A command-line tool for quickly scraping BibTeX information from computer science conferences and journals, optimized for LLM Multi-Agents. The licence is MIT.

When your agent uses it

  • The user provides one
  • More academic PDF files
  • An existing BibTeX file and wants the search-bibtex binary to extract metadata
  • Fuzzy-search bibliographic sources

Example prompts

  • “/search-bibtex”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the binary is available
  2. Inspect PDF metadata and generated search queries
  3. Search and rank candidates. In a TTY, search opens the selector; when piped, it prints JSON
  4. For title strings instead of PDFs, use search-bibtex search-title. Multiple titles in one input are split by ; by default, and stdin is…
  5. Let the user choose a BibTeX entry
  6. If the user already has a .bib file and wants refreshed fields without changing citation keys
  7. For non-interactive use, select by ranked index

What it can do on your machine

Read from SKILL.md and the folder at commit b19de5e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Search Bibtex loads about 885 tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 344 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~885

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from steeliron550-ui/search-bibtex at commit b19de5e, republished under its MIT licence (© steeliron550-ui). 344 words, ~885 tokens.

Download SKILL.mdSave it as .claude/skills/search-bibtex/SKILL.md (or your agent's skills folder). This skill also uses 72 other files; get the full folder from GitHub.
name
search-bibtex
description
Use when the user provides one or more academic PDF files or an existing BibTeX file and wants the search-bibtex binary to extract metadata, fuzzy-search bibliographic sources, refresh BibTeX, rank candidates with configurable source priority, load defaults from config.toml, and present an interactive Vim-key selection UI. Handles computer science preprints, conference papers, and journal papers through an independent CLI; does not depend on Paperlib.

Search BibTeX

Use this skill for the search-bibtex binary. The binary is independent of Paperlib. Grok search may be used while improving or debugging this project, but it must stay out of the CLI runtime and skill workflow.

Workflow

  1. Confirm the binary is available:

    bash
    search-bibtex --help
  2. Inspect PDF metadata and generated search queries:

    bash
    search-bibtex metadata <pdf-path>
  3. Search and rank candidates. In a TTY, search opens the selector; when piped, it prints JSON:

    bash
    search-bibtex search <pdf-path> --limit 10 --timeout 30 --source-priority dblp,arxiv,crossref,openalex,doi

    Parallel source search is enabled by default. Use --no-parallel only when serial lookup is explicitly wanted. If the user has a config file, pass --config <path> and let CLI flags override it.

  4. For title strings instead of PDFs, use search-bibtex search-title. Multiple titles in one input are split by ; by default, and stdin is accepted when no title argument is provided.

  5. Let the user choose a BibTeX entry:

    bash
    search-bibtex select <pdf-path> --limit 10 --timeout 30 --source-priority dblp,arxiv,crossref,openalex,doi
  6. If the user already has a .bib file and wants refreshed fields without changing citation keys:

    bash
    search-bibtex update <bibtex-path> --in-place
  7. For non-interactive use, select by ranked index:

    bash
    search-bibtex select <pdf-path> --select-index 0 --format bibtex
Show full SKILL.md (179 more words)Show less

Source Priority

The built-in default source order is:

text
dblp,arxiv,crossref,openalex,doi,semantic-scholar

For computer science papers, this order avoids Semantic Scholar's anonymous rate limits:

bash
--source-priority dblp,arxiv,crossref,openalex,doi

Include semantic-scholar only when the user wants it or the local environment can tolerate anonymous API rate limits:

bash
--source-priority dblp,arxiv,crossref,openalex,semantic-scholar,doi

Use --weights when ranking behavior should change:

bash
--weights title=0.5,author=0.2,year=0.1,identifier=0.15,source=0.05

search-bibtex config-template prints a TOML starter file. Config files can add custom HTTP sources and include their names in source_priority. Full config docs are in docs/CONFIGURATION.md.

Interaction

The interactive selector supports:

  • j / k or arrow keys to move.
  • g / G to jump to first or last visible candidate.
  • / to filter candidates.
  • Enter to select.
  • q, Esc, or Ctrl-C to cancel.

Render UI goes to stderr and selected BibTeX or JSON goes to stdout. When the user presses Enter, the screen shows formatted BibTeX and the tool attempts to copy it to the clipboard if a local clipboard command is available.

Failure Handling

Do not hide source failures. search returns explicit sourceErrors; select prints source errors to stderr before selection. If no candidates are returned, surface the CLI error instead of fabricating a BibTeX entry.

© steeliron550-ui, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 72 other files (scripts) in the repository root of steeliron550-ui/search-bibtex.

  • SKILL.md
  • .github/workflows/build-binaries.yml
  • .github/workflows/release.yml
  • .gitignore
  • CHANGELOG.md
  • CHANGELOG.zh-CN.md
  • CONTRIBUTING.md
  • CONTRIBUTING.zh-CN.md
  • LICENSE
  • Makefile
  • README.en.md
  • README.md
  • RELEASING.md
  • RELEASING.zh-CN.md
  • agents/openai.yaml
  • docs/ARCHITECTURE.md
  • docs/ARCHITECTURE.zh-CN.md
  • … and 56 more

Open the folder on GitHubat commit b19de5e

Compare with similar skills

Search Bibtex next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Search Bibtex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Search Bibtex this skillsteeliron550-ui/search-bibtex115—~885Automated safety check: PassMIT
Citation Managementneflibata-feng/MyArxiv-Agent12619 repos~8.1kAutomated safety check: NotesMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Literature Review AgentAr9av/PaperOrchestra6791 repos~5.2kAutomated safety check: PassCustom licence
Academic Searchustc-ai4science/academic-search668—~1.1kAutomated safety check: PassMIT
Collaborating With Claudeappautomaton/latex-arxiv-SKILL4581 repos~1.5kAutomated safety check: PassMIT

Similar skills

  • Citation Management

    neflibata-feng/MyArxiv-Agent

    Comprehensive citation management for academic research. An agent skill from neflibata-feng/MyArxiv-Agent.

    126 GitHub starsUsed in 19 repos~8.1k tokens
    Research & ScienceAuto-check: notes
  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Literature Review Agent

    Ar9av/PaperOrchestra

    Step 3 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from Ar9av/PaperOrchestra.

    679 GitHub starsUsed in 1 repo~5.2k tokens
    Research & ScienceAuto-check passed
  • Academic Search

    ustc-ai4science/academic-search

    A skill your agent uses when the user asks to search or review academic papers, retrieve scholarly metadata or citation counts, validate or deduplicate scholarly records, find an author's…

    668 GitHub stars~1.1k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Collaborating With Claude

    appautomaton/latex-arxiv-SKILL

    Use the Claude Code CLI to consult Claude and delegate coding tasks for prototyping, debugging, and code review.

    458 GitHub starsUsed in 1 repo~1.5k tokens
    Research & ScienceAuto-check passed
  • Arxiv MCP Server

    blazickjp/arxiv-mcp-server

    A skill your agent uses when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or…

    3.2k GitHub stars~353 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

Works with

Questions about Search Bibtex

What does Search Bibtex do?

A skill your agent uses when the user provides one or more academic PDF files or an existing BibTeX file and wants the search-bibtex binary to extract metadata, fuzzy-search bibliographic sources…. Search Bibtex is an agent skill from steeliron550-ui/search-bibtex.toml, and present an interactive Vim-key selection UI.

When should I use Search Bibtex?

Search Bibtex fits situations like: the user provides one; more academic PDF files; an existing BibTeX file and wants the search-bibtex binary to extract metadata; fuzzy-search bibliographic sources.

How do I install Search Bibtex in Claude Code?

Run `npx skills add steeliron550-ui/search-bibtex --skill search-bibtex -a claude-code`. Or copy the skill folder (the steeliron550-ui/search-bibtex repository) into .claude/skills/search-bibtex in your project. Claude Code loads it when a task matches its description.

How do I install Search Bibtex in Codex?

Run `npx skills add steeliron550-ui/search-bibtex --skill search-bibtex -a codex`. Or copy the skill folder (the steeliron550-ui/search-bibtex repository) into .agents/skills/search-bibtex in your project. Codex loads it when a task matches its description.

Can I use Search Bibtex in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add steeliron550-ui/search-bibtex --skill search-bibtex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/search-bibtex, .gemini/skills/search-bibtex, .github/skills/search-bibtex and .opencode/skills/search-bibtex in your project.

What does Search Bibtex need to run?

SKILL.md names no scripts, command-line tools or credentials: Search Bibtex is instructions for the agent only.

Does Search Bibtex access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Search Bibtex safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Search Bibtex use?

Search Bibtex is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Search Bibtex use?

About 885 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Search Bibtex?

Skills that share tags, products or a category with Search Bibtex: Citation Management (neflibata-feng/MyArxiv-Agent, 126 stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars), Literature Review Agent (Ar9av/PaperOrchestra, 679 stars) and Academic Search (ustc-ai4science/academic-search, 668 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Search Bibtex?

steeliron550-ui (a GitHub user) maintains it in steeliron550-ui/search-bibtex, which has 115 GitHub stars. The repository was last updated on May 30, 2026.

Source: steeliron550-ui/search-bibtex on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.