agentleFS
Sign inStart free
NilsHellwigNilsHellwig/acl-paper-skills/skills/new-source/SKILL.md

new-source

Skill3 starsChanged 12 days agoMITView on GitHub

Add a literature source beyond ACL Anthology and arXiv (e.g. Semantic Scholar, ACM DL, OpenReview, PubMed) as a project skill with its own adapter.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. mampfes/hacs_waste_collection_schedule★ 2.3ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository13 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add "<name>": ".claude/skills/<name>-source/adapter.py" under sources in paper.config.json.

    line 26
  2. Very specific:

    Every line must read ✅. PK doctor must list the source without ⚠️.

    line 32
  3. Very specific:

    Create .claude/skills/<name>-source/SKILL.md, modelled on ${CLAUDE_PLUGIN_ROOT}/skills/arxiv/SKILL.md:

    line 36

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build a project-local source: an adapter the core scripts call, plus a skill that tells the agent when and how to use it. It lives in the paper project, not in the plugin.

PK means python3 ${CLAUDE_PLUGIN_ROOT}/scripts/paperkit.py, run from the project root.

1. Pin down the source

Research the source's public API: search endpoint, how to get a PDF, and where an authoritative BibTeX entry comes from (an export endpoint, a DOI resolved via https://doi.org/<doi> with Accept: application/x-bibtex, DBLP). A source without an authoritative BibTeX route cannot be added as is: say so and offer the fallback (search and PDF here, entries pasted by the user via bib-paste).

Also find the source's rate limits, API key requirements and terms of use. Show the user what you found and agree on the source name (kebab-case, e.g. semantic-scholar) before writing code. An API key goes in an environment variable the adapter reads, never in a file.

2. Write the adapter

Copy ${CLAUDE_SKILL_DIR}/adapter_template.py to .claude/skills/<name>-source/adapter.py and implement the three functions. The docstring of ${CLAUDE_PLUGIN_ROOT}/scripts/paperkit/sources.py defines the contract, and ${CLAUDE_PLUGIN_ROOT}/scripts/sources/arxiv_source.py is a worked example. Keep the adapter to fetching: duplicate checks, files, notes and bib handling belong to the core.

Third-party packages go in REQUIRES. Ask before installing them into the project env (python in paper.config.json).

3. Register and test

Add "<name>": ".claude/skills/<name>-source/adapter.py" under sources in paper.config.json. Ask the user for a paper they know is on the source, then run:

PK test-source <name> "<query matching that paper>" <its id>

Every line must read ✅. PK doctor must list the source without ⚠️.

4. Write the project skill

Create .claude/skills/<name>-source/SKILL.md, modelled on ${CLAUDE_PLUGIN_ROOT}/skills/arxiv/SKILL.md:

  • frontmatter name: <name>-source and a description that names the source and the cases that should reach it (paper types, id formats, URLs)
  • the search command with the query syntax the source supports and its rate limit
  • the add command, and a pointer to the literature skill for reading and citing

Finish by showing the user the two files and the config change.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free