docs: record literature-review tooling research option - #9
Conversation
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Reviewer's GuideAdds a dated documentation-only setup option describing the known-good CLI workflow for verified literature reviews with LaTeX BibTeX output, its fallbacks and limitations, and the tools deliberately not adopted; no templates or runtime wiring change. Flow diagram for the verified literature review tooling workflowflowchart TD
Start["Literature review need"] --> Primary["claude-scholar\nOpenAlex, DOI to BibTeX, check-refs"]
Primary --> Verify["Verify references and LaTeX .bib"]
Primary --> Thin["Search results look thin"]
Thin --> Fallback["curl fallback\nCrossref, OpenAlex, doi.org"]
Fallback --> Verify
Start --> Discovery["exa\nTrial for non-indexed material"]
Discovery --> Verify
Verify --> Report["Verified literature review\nwith BibTeX output"]
File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
|
|
||
| <!-- entries below --> | ||
|
|
||
| ## 2026-09-11 — tooling for a verified literature review (+ BibTeX for a LaTeX report) |
There was a problem hiding this comment.
PR #5 inserts its entry at the same spot, directly under <!-- entries below -->. git merge-tree of the two branches reports a conflict.
Whichever merges second hits a conflict. The log is documented as "Newest first", so the 2026-09-11 entry has to sit below 2026-09-24. A quick resolution that keeps "theirs on top" (for example, merging #9 after #5) puts the entries out of date order.
Automated review (Claude Code, AI-generated). Validate before acting.
| - Fit: strong. No key, free, and `check-refs` closes the loop against the written report — which | ||
| matches the reproducibility value better than a search-only tool. | ||
| - Maintenance: installed plugin, in use. | ||
| - Verdict: **adopt** — primary tool. Used for the PC1 review in `cursos/concurrente` (issue #5). |
There was a problem hiding this comment.
The bare (issue #5) refers to an issue in cursos/concurrente, but GitHub autolinks it to project-kit#5, the unrelated data-storage PR.
A reader clicking the evidence link lands on the HF/DVC storage PR, so the provenance claim for the "adopt" verdict points at the wrong thing. Use the qualified R0SEWT/<concurrente-repo>#5.
Automated review (Claude Code, AI-generated). Validate before acting.
There was a problem hiding this comment.
Fixed in 688863d: R0SEWT/concurrente#5. (Claude Opus 5.5, on behalf of Rody)
| a paper accepted but not yet in a DOI registry), weak for bibliographic metadata. | ||
| - **Friction found**: the **dblp API is behind a bot check** (`dblp.org/search/publ/api` returns an | ||
| Anubis HTML challenge, HTTP 200). Don't script it; use Crossref for CS-venue coverage instead. | ||
| - **Wiring**: none. All adopted pieces are already installed or plain `curl`; nothing to add to |
There was a problem hiding this comment.
The entry records claude-scholar and exa as installed and adopted, but skills/research-setup/SKILL.md "Already installed (don't re-propose / weigh overlap)" is left unchanged. That list still names only superpowers/frontend-design/github-map/playwright/context7.
The next research-setup run doesn't weigh overlap with claude-scholar or exa, and may re-propose the academic MCP servers this entry just rejected for overlapping with them. "Wiring: none" should include that one-line update to the skill.
Automated review (Claude Code, AI-generated). Validate before acting.
There was a problem hiding this comment.
Fixed in 688863d: added to the research-setup list and bumped the plugin to 0.2.1. (Claude Opus 5.5, on behalf of Rody)
6365624 to
688863d
Compare
Stacked on the data-storage entry (newest first). The research-setup skill now lists claude-scholar and exa as installed, so the plugin goes to 0.2.1. The concurrente issue link is repo-qualified, and exa is marked optional under the no-paid-API constraint. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
688863d to
0a05eb2
Compare
1 participant
Why
Record the tooling research for a verified literature review (with BibTeX for a LaTeX report), done for the PC1 of
cursos/concurrente, so the next literature task starts with the known-good tools and the known pitfalls.Changes
catalog/setup-options.md: new entry dated 2026-09-11.claude-scholarplugin as the primary tool (OpenAlex, DOI → BibTeX,check-refs), and direct Crossref/OpenAlex/doi.orgcalls as the fallback. Crossref finds CS venues better than OpenAlex.exafor discovering material that isn't indexed.No wiring: nothing is added to
templates/.Stacked on #5 (the catalog is newest first, so this entry goes below its 2026-09-24 one). Merge #5 first. Also bumps the plugin to 0.2.1:
skills/research-setup/SKILL.mdnow listsclaude-scholarandexaas installed.Validation
git diff --checkpasses.mainafter docs(catalog): a home for a project's gitignored data (HF trial) + template prompt #5.🤖 Generated with Claude Code
Summary by Sourcery
Record the validated tooling choices and operational pitfalls for reproducible literature reviews without adding template wiring.
Enhancements:
Documentation:
Chores: