Journal Meta

Community

Agents365-ai

journal-meta

Use when the user wants full metadata for a paper — from a DOI, PMID, arXiv id, OpenAlex id, or title. Returns title, author list, first author, corresponding author(s), publication date, journal name + ISO-4 abbreviation, impact factor, volume/issue/pages, DOI/PMID, citation count, and abstract in one record. Triggers on "paper metadata", "who is the corresponding author", "first author of", "what journal / impact factor for this DOI/PMID", "cite this paper", "文献元数据", "通讯作者", "第一作者", "影响因子". PROACTIVELY USE when the user pastes a DOI/PMID/arXiv id or paper title and asks about its authors, venue, or impact.

Overview

Publisher	Agents365-ai
Repository	`365-skills`
Skill name	`journal-meta`
Stars	99
Forks	16
Bundled files	1
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Agents365-ai on GitHub. Read the source before you install it.

Installation

Install the Journal Meta AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Agents365-ai/365-skills/tree/main/plugins/journal-meta/skills/journal-meta
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/Agents365-ai/365-skills/tree/main/plugins/journal-meta/skills/journal-meta

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Agents365-ai/365-skills.git /tmp/365-skills
mkdir -p .claude/skills
cp -r /tmp/365-skills/plugins/journal-meta/skills/journal-meta .claude/skills/journal-meta

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Journal Meta in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Journal Meta on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Journal Meta is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Paper Metadata Lookup

Resolve one paper identifier into a full metadata record. Primary source is OpenAlex (free, no API key); Crossref is a fallback for DOIs OpenAlex hasn't indexed. The journal name is enriched by delegating to two sibling skills when installed:

journal-abbrev → ISO-4 / MEDLINE journal abbreviation (JabRef cache, ~25K journals)
journal-if → curated JCR impact factor

If those skills aren't found, it falls back to AbbrevISO (abbreviation) and OpenAlex 2yr_mean_citedness (approximate IF) automatically.

Critical rule: Always use journal_meta.py. Never fabricate authors, corresponding authors, dates, or impact factors — resolve them.

Quick Reference

User wants...	Command
Metadata from a DOI	`python3 journal_meta.py "10.1038/s41586-020-2649-2"`
Metadata from a PMID	`python3 journal_meta.py 32939066`
Metadata from an arXiv id	`python3 journal_meta.py 1706.03762`
Metadata from a title	`python3 journal_meta.py "Attention is all you need"`
Process a list	`python3 journal_meta.py batch papers.txt`
Skip impact-factor lookup	`python3 journal_meta.py <id> --no-if`
Skip abbreviation lookup	`python3 journal_meta.py <id> --no-abbrev`
Machine-readable contract	`python3 journal_meta.py schema`

The subcommand lookup is optional — a bare identifier works. Identifier type (DOI / PMID / arXiv / OpenAlex id / title) is auto-detected.

Output format

Stdout is a stable JSON envelope when piped/captured, and a human key-value view on a TTY. Force it with --format json|human|auto (--json = --format json).

Envelope: { "ok": true, "data": {...}, "meta": { "schema_version", "cli_version", "sources", "latency_ms" } }. meta.sources records where each field came from (e.g. journal-abbrev (JabRef), journal-if (local cache), or a fallback), so you can tell curated data from approximations.

Data fields (`data`)

title, authors (list), author_count, first_author, corresponding_authors (list; empty if OpenAlex has no corresponding flag for the record), publication_date, year, journal, journal_abbrev, impact_factor, impact_factor_source, impact_factor_year, volume, issue, pages, doi, pmid, openalex, issn, type, is_oa, cited_by_count, abstract.

Exit codes

Code	Meaning
`0`	success
`1`	runtime / upstream error (retryable)
`2`	validation / bad input (missing file, empty query)
`3`	not found (no paper matched)

Workflow

Identify the input. A DOI (10.x/...), PMID (digits), arXiv id (NNNN.NNNNN), OpenAlex id (W...), or a title string — all auto-detected. Prefer a DOI or PMID: title search returns OpenAlex's single top match, which for very common titles can be a preprint or re-indexed copy rather than the version of record. Confirm the returned DOI/year if the user gave a title.
Run python3 journal_meta.py <id>.
Present the fields the user asked for. For a full citation, use first_author, journal_abbrev, year, volume, issue, pages, doi. State the impact_factor_source when reporting IF — a curated JCR number and an OpenAlex approximation are not the same thing.

Notes & caveats

Corresponding author comes from OpenAlex's is_corresponding flag, which is only populated when the publisher supplied it. An empty list means "not marked in the metadata," not "there is none" — say so rather than guessing.
Impact factor from journal-if is curated JCR; the fallback is OpenAlex's 2-year mean citedness, which differs from the official JCR IF. Cite formally only the curated value, and flag approximations.
arXiv ids resolve via the arXiv DataCite DOI (10.48550/arXiv.<id>); if a preprint isn't indexed there, it falls back to a title search.

Environment variables

Variable	Effect
`JOURNAL_META_MAILTO` / `OPENALEX_MAILTO`	Email for OpenAlex's polite pool (faster, recommended).
`JOURNAL_ABBREV_CLI`	Explicit path to `journal-abbrev`'s `jabbrv.py` (skips auto-discovery).
`JOURNAL_IF_CLI`	Explicit path to `journal-if`'s `journal_if.py`.

If the sibling skills live in a non-standard location, set these so enrichment uses their curated data instead of the built-in fallbacks.

Troubleshooting

Issue	Solution
IF shows "OpenAlex ... (approx)" not JCR	`journal-if` not found — install it or set `JOURNAL_IF_CLI`.
Abbreviation looks wrong / same as full name	Single-word titles (Nature, Cell, Science) are not abbreviated per ISO 4. For others, `journal-abbrev` gives the ISO-4 form.
Title search returned the wrong paper	Use the DOI or PMID instead — title search takes OpenAlex's top hit only.
`not_found` on a brand-new DOI	OpenAlex indexing lags; the Crossref fallback covers most, but the newest DOIs may need a day.
`corresponding_authors` is empty	The publisher didn't mark it in the metadata; don't infer one.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

journal_meta.py26 KB

Frequently asked questions

What does the Journal Meta AI skill do?

Why use Journal Meta on TypingMind?

Because you install it once and use it with any model. Journal Meta is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Journal Meta in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Agents365-ai/365-skills/tree/main/plugins/journal-meta/skills/journal-meta. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Journal Meta?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Journal Meta?

As many as you like. As long as a model supports skills, you can use Journal Meta with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Journal Meta AI skill free?

It is published on GitHub by Agents365-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Advisor Orchestrator Worker

Shubhamsaboo

CommunityPopular

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple…

Openai Docs

Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when…

Caveman Explore

Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line…

Delegate Work

Delegate user-requested work to an existing Paperclip agent, with a durable task reference and clear execution expectations.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Paper Metadata Lookup

Quick Reference

Output format

Data fields (data)

Exit codes

Workflow

Notes & caveats

Environment variables

Troubleshooting

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

Data fields (`data`)