literature-provenance
Skill6 starsChanged 21 days agoMITView on GitHub
Verify DOI identity, retrieve registry-generated citations and locate short verbatim evidence in an authorized offline corpus. Use for source-backed engineering research, reference preparation and claim checks; venue labels are local policy, not proof of correctness.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- claim-ledgerSkill
- critic-reviewSkill
- distributed-orchestrationSkill
- engineering-governanceSkill
- engineering-planSkill
- execution-integritySkill
- multi-agent-collaborationSkill
- technical-writingSkill
- worker-taskSkill
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 12
After authorized acquisition, archive_corpus.py creates an offline index with file hashes and explicit source/version/access/recipient …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Use doi.py to fetch CSL metadata and BibTeX through DOI content negotiation. Supply an independently expected title and an explicit venue policy. DOI/title mismatch, missing fields, unsupported redirects or network failure stop processing. Never invent or silently repair bibliographic fields. The script retains returned citation bytes, source URLs and hashes for approved records; unknown/preprint venues remain blocked unless the policy explicitly permits that tier.
Use locate_quote.py to locate an exact passage in a permitted local PDF or form-feed-delimited text export. Evidence includes source/page hashes, offsets, page index and nearest detectable heading. Quotes are limited to 40 counting units (words, or individual CJK characters). Return all matches, not a preferred occurrence. Missing text, failed extraction or ambiguous equations require manual review; never fabricate a page/heading or reconstruct a formula by guesswork.
An authorized acquisition node can keep a hashed offline archive for other entitled nodes. Metadata access is not full-text access or permission to redistribute copyrighted material. Record retrieval rights, version and permitted recipients before synchronization. Keep restricted corpora and private network facts out of public repositories.
After authorized acquisition, archive_corpus.py creates an offline index with file hashes and explicit source/version/access/recipient records. Missing rights block indexing. The tool does not grant entitlements, download paywalled documents or automatically redistribute the archive.
See tool contracts and provenance for formats, dependencies, venue policy and extraction limitations. Verify a claim against the actual passage and surrounding assumptions; a high-tier venue or a DOI match alone does not validate the claim.
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.

