acl-anthology
Skill3 starsChanged 14 days agoMITView on GitHub
Search the ACL Anthology and add papers (PDF, text, BibTeX) to an acl-paper project. Use when looking for NLP/CL papers from ACL, EMNLP, NAACL, EACL, Findings, TACL, COLING, LREC or workshops, when an Anthology id or URL comes up, or when another skill needs an Anthology paper or its BibTeX.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- templates/CLAUDE.mdCLAUDE.md
- arxivSkill
- camera-readySkill
- guidelines-checkSkill
- initSkill
- literatureSkill
- new-sourceSkill
- proofreadSkill
- rebuttalSkill
- reviewerSkill
- revisionSkill
- writingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Search and fetch from the ACL Anthology through the acl-anthology package.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Search and fetch from the ACL Anthology through the acl-anthology package. Reading and citing what you fetch follows the literature skill.
PK means python3 ${CLAUDE_PLUGIN_ROOT}/scripts/paperkit.py, run from the project root. It switches to the project's Python env by itself.
Search
PK search acl-anthology "<query>" [--limit 10] [--year-from 2020] [--year-to 2025]Ranking is keyword overlap: title words weigh most, abstract words count too. Use the task's technical terms ("aspect sentiment quad prediction"), and run a second search with synonyms or the abbreviation spelled out when the first one is thin. Each hit shows its Anthology id and whether it is already in the library.
The first search in a fresh setup clones the Anthology metadata (about 300 MB) into ~/.cache/acl-paper/anthology. PK anthology-update pulls newer data, worth doing when looking for papers from the last few weeks.
Present hits as a short list (title, year, venue, id). The abstract snippet is for triage only: pick what to fetch and read, then judge the paper after reading its body.
Add
PK add acl-anthology <anthology-id> [--key <key>]<anthology-id> is the id from the search or the URL (2023.acl-long.1); the Anthology bibkey works too. The command stores the official Anthology BibTeX in literature/archive.bib, downloads the PDF, converts it to Markdown and creates the notes file. The entry moves into the paper bib once the paper is cited.
--key only when key_scheme in paper.config.json is not native: build the key by that scheme.
On "a bib entry with the same title exists": the paper is already in the library under that key (often the arXiv version). Ask the user which version to keep and cite.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.