Individual skill
food-fetch
Lawfully acquire the full text of academic articles so the research and review skills can read papers, not just abstracts. Routes each article through legal open access (Unpaywall/OpenAlex/PMC/arXiv), the user's own reference-manager library (EndNote/Zotero/Mendeley PDFs), and — only with the user's own logged-in institutional browser session — their library's entitled full text, then extracts the text and writes a manifest of what was and was not obtained. Open-access articles are always downloaded and read, never left at abstract-level. Never bypasses paywalls, DRM, or logins. Use to fetch PDFs for a reference list or DOIs, get full text behind a subscription the user is entitled to, or build a full-text corpus. Triggers: download these papers, get the full text, fetch the PDFs for these DOIs, retrieve full text for my reference list, access the article through my library, build a full-text corpus.
food-fetch/SKILL.md
Source commit 01b2158a48408a8d0e56238c04075080c793d53c
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 11, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 42
- Repository last updated
- Aug 31, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- academic-writing Repository topic
- ai-agents Repository topic
- anthropic Repository topic
- claude-code Repository topic
- claude-skills Repository topic
- codex Repository topic
- food-science Repository topic
- food-technology Repository topic
- literature-review Repository topic
- llm Repository topic
- research Derived category
- legal Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 7,367 bytesSKILL.mdcore · 7,367 bytesSKILL.mdcore · 7,367 bytesagents/access_router.mddoc · 1,195 bytesagents/content_reader.mddoc · 2,062 bytesagents/fetch_coordinator.mddoc · 2,335 bytesagents/institutional_fetcher.mddoc · 3,815 bytesagents/library_fetcher.mddoc · 1,247 bytesagents/oa_fetcher.mddoc · 1,324 bytesreferences/access-routing.mddoc · 1,706 bytesreferences/boundaries.mddoc · 1,916 bytesreferences/format-reading.mddoc · 3,282 bytesreferences/institution-profiles.mddoc · 2,246 bytesreferences/institutional-access.mddoc · 4,844 bytesreferences/manifest-and-status.mddoc · 2,149 bytes
Read excerpt
# Food-Fetch — Lawful Full-Text Acquisition
Turn a list of references or DOIs into **read full text**, so `food-research`,
`food-deep-research`, and `food-review` build their knowledge base from the actual
papers rather than abstracts. Original work; the routing/manifest architecture is
informed by the open-source `nature-downloader` skill (see the repo README
Acknowledgements). Legal-access-only, and **it never fabricates** — a paper that was
not obtained is recorded as not obtained, never summarized as if read.
## First-run setup — ask once, remember, remind if skipped
On the **first** run that needs full text, help the user set up access — this is what
decides whether the review reads real papers. Check
`python3 scripts/food_fetch_setup.py status` (exit 3 = not set up):
