Skip to content

fix: describe the research paper index accurately across CLI surfaces - #186

Merged
hmishra2250 merged 5 commits into
mainfrom
fix/lifesci-discoverability-20260812
Aug 12, 2026
Merged

fix: describe the research paper index accurately across CLI surfaces#186
hmishra2250 merged 5 commits into
mainfrom
fix/lifesci-discoverability-20260812

Conversation

@hmishra2250

@hmishra2250 hmishra2250 commented Aug 12, 2026

Copy link
Copy Markdown
Contributor

Why

The CLI's research command group was branded arXiv-only ("Research arXiv papers and GitHub history") while the index it fronts is mostly biomedical (PubMed, bioRxiv, medRxiv). In 8/8 measured agent traces on biomedical tasks, agents read firecrawl --help, concluded the command was not relevant, and hand-scraped PubMed instead. The README also taught firecrawl search --categories research (a website filter) as the way to "Find research papers" and never mentioned firecrawl research at all.

Summary

  • Root --help line and all five research subcommand descriptions now name the real corpus; multi-source id examples (pmid:, pmcid:, doi:) used throughout
  • search --categories help disambiguates research (website filter) from firecrawl research (paper index); the wire value research is untouched
  • README: wrong worked example fixed; a ### research command section added (it was the only command without one); tagline updated
  • Skills: firecrawl-search SKILL gains a Paper search section (parity with its Developer search section); firecrawl-cli routing table gains research rows
  • 3 new regression tests guard research's help visibility (parity with the existing developer guards)
  • package.json → 1.20.0; homebrew/nfpm descriptions synced

Test Plan

  • pnpm test 422/422 (incl. 3 new argv guards), pnpm run build + type-check + format:check clean
  • Rendered firecrawl --help / firecrawl research --help verified from the built binary

🤖 Generated with Claude Code


Summary by cubic

Clarifies and correctly brands the research paper index across the CLI, docs, and skills so users run firecrawl research for papers (PubMed, bioRxiv, medRxiv, arXiv) instead of the web category filter or hand-scraping. This fixes arXiv-only wording that led users to skip the paper index.

  • Root --help and all research subcommands name the real corpus and show pmid:, pmcid:, and doi: examples; search-papers/related-papers docs note arXiv taxonomy limits and accept multi-source ids.
  • Disambiguated search --categories research (website filter) from the paper index; help now points to firecrawl research search-papers (wire value unchanged).
  • README and skills: added a research section, corrected examples, routed paper workflows through research, and added a Paper search section to firecrawl-search.
  • Install and run commands now use @latest instead of pinned versions; sample --status reflects v1.20.0.
  • Added 3 CLI argv tests guarding help visibility and biomedical wording; updated packaging descriptions and keywords; bumped firecrawl-cli to 1.20.0.

Written for commit ab0f63a. Summary will update on new commits.

Review in cubic

Why: over 40 agent traces, 8/8 biomedical CLI runs read the root-help
research line ("Research arXiv papers and GitHub history"), concluded the
index was arXiv-only, and hand-scraped PubMed instead of ever running
`firecrawl research`. The index is ~43M abstracts, ~90% biomedical. The
group description is the single highest-leverage string: it renders both
in `firecrawl --help` and as the `firecrawl research --help` header.

Summary:
- research group description now names the corpus (PubMed/bioRxiv/medRxiv
  plus arXiv), its scale, and routes agents away from hand-scraping.
- search-papers description drops the three "arXiv" claims and names the
  multi-source id forms it actually returns; keeps the load-bearing
  "run several distinct framings" guidance verbatim.
- search-papers --categories only claims what is true: arXiv-style
  taxonomy labels, not applicable to biomedical records.
- search --categories disambiguates `research` (a ~web-domain filter)
  from the paper index, pointing at `research search-papers`. The wire
  value 'research' is unchanged.
- related-papers accepts pmid:/pmcid:/doi:/arxiv: forms in its docs, in
  line with inspect-paper and read-paper.
- research examples now include biomedical ids, not arXiv only.
- cli-argv tests gain the research pair that mirrored `developer`, plus a
  regression guard that root help names the biomedical corpus.
Why: the README taught the wrong tool. "# Find research papers" was
followed by `firecrawl search --categories research`, which is only a
website filter over ordinary web results, not the paper index. README
also had a `###` section for every command except `research`, so the
index had no documentation surface at all, and the tagline omitted both
`research` and `developer`.

Summary:
- the "Find research papers" example now leads with `research
  search-papers`; the `--categories research` example stays but is
  labelled as the website filter it is.
- same disambiguation added to the category example block and the search
  options table.
- new `### research` section beside `developer`: corpus and scale, the
  explicit "not the same as --categories research" note, all five
  subcommands, search-papers options, and workflow tips.
- line-3 tagline now mentions research papers and developer sources.
Why: npm search and package listings carried no research, paper, or
biomedical vocabulary, so the paper index was undiscoverable from outside
the CLI too. Behavioural metadata change across help text, docs, and
skills -> minor bump.

Summary:
- package.json description names the paper index and its sources.
- keywords gain research, paper/literature search, biomedical, pubmed,
  biorxiv, medrxiv, arxiv, life sciences.
- 1.19.31 -> 1.20.0.
- nfpm.yaml and homebrew/firecrawl-cli.rb carry the same one-line
  description; both updated. The brew `desc` is kept under the 80-char
  audit limit.

Note: homebrew/firecrawl-cli.rb `version` is 1.10.0 and is not written by
any release tooling in this repo; left as found rather than guessed at.
Why: agents load skills before they load `--help`. firecrawl-search had a
full "Developer search" section and nothing for research; its options
table listed `research` with no elaboration, so the naming collision with
the paper index was invisible. firecrawl-cli's routing table and "When to
Load References" omitted research entirely, so nothing ever pointed an
agent at `firecrawl research`.

Summary:
- firecrawl-search: new "## Paper search" section parallel to "##
  Developer search" — states plainly that `--categories research` is not
  the paper index, routes to `research search-papers`, and shows the
  find/expand/verify loop with real id forms.
- firecrawl-search: `--categories` options row and "When to use" now
  disambiguate the two; frontmatter description gains literature triggers
  so the skill actually loads on a biomedical task.
- firecrawl-cli: research rows added to the routing table and to "When to
  Load References", both stating the anti-pattern (hand-scraping PubMed).

@cubic-dev-ai cubic-dev-ai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

All reported issues were addressed across 8 files

Reply with feedback, questions, or to request a fix.

Fix all with cubic | Re-trigger cubic

Comment thread README.md
Why: cubic flagged the README install example pinning firecrawl-cli@1.19.6
while this PR ships 1.20.0. The pin was already 25 patches behind npm's
published 1.19.31, and the same stale pin appeared in five more places in
the bundled skills rules.

Summary: install and run commands now use @latest, matching the convention
the public docs already use in all 30 of their occurrences. That removes the
drift permanently rather than trading one stale pin for another — and avoids
pinning 1.20.0, which is not published yet and would break the documented
one-shot install until release. The illustrative `--status` sample output now
shows the version this PR ships.

Test Plan: pnpm test 422/422, prettier clean, no hard-pinned versions remain
in any markdown file.
@hmishra2250
hmishra2250 merged commit 23a0df4 into main Aug 12, 2026
8 checks passed
@hmishra2250
hmishra2250 deleted the fix/lifesci-discoverability-20260812 branch August 12, 2026 15:41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant