Scholarfetch — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Scholarfetch (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use ScholarFetch when the task is academic discovery, citation expansion, corpus building, or literature-grounded synthesis.
Move from an initial topic, DOI, author, or seed paper to a curated reading list and an export artifact that another agent or human can use immediately.
Use:
scholarfetch_searchscholarfetch_doi_lookupscholarfetch_author_candidatesGoal:
Use:
scholarfetch_abstractscholarfetch_doi_lookupGoal:
Use:
scholarfetch_author_papersscholarfetch_referencesGoal:
Use:
scholarfetch_saved_addscholarfetch_saved_listscholarfetch_saved_removescholarfetch_saved_clearGoal:
Use:
scholarfetch_saved_exportGoal:
abstract before article_textreferences when the paper looks foundationalauthor_papers when the paper looks representative of an author's line of workAlways choose and reuse one collection name per topic branch.
Examples:
defaultml-governance-reviewdigital-health-citationsThe collection is the agent's session memory.
abstracts or fulltext.citationsBest for:
abstractsBest for:
bibBest for:
fulltextBest for:
Use include_references=true when the export should also preserve citation context.
A good ScholarFetch run should produce:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.