10 actions in 7 pieces of software · ranked by words, meaning and measured trust · 924 ms

1. 1scholar-evaluationverified and signedpassport

   skillaffaan-m/eccrecord

   • scholar-evaluation

     Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback. Use when evaluating academic or scientific work — papers, proposals, methods sections, or evidence quality — against a repeatable rubri

2. 2scholar-evaluationverified and signedpassport

   skillk-dense-ai/scientific-agent-skillsrecord

   • scholar-evaluation

     Provides qualitative-first, evidence-traceable developmental review of scholarly works and audit low-stakes research-assessment rubrics with optional local quality controls. Never use for ranking people or consequential decisions.

3. 3scientific-thinking-scholar-evaluationverified and signedpassport

   skillaffaan-m/eccrecord

   • scientific-thinking-scholar-evaluation

     Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback. Use when evaluating academic or scientific work — papers, proposals, methods sections, or evidence quality — against a repeatable rubri

4. 4Scholar Feedverified and signedpassport
   • annotate_paper

     Record YOUR verdict on a paper — why it matters for your work, when to use it, or why you ruled it out. One note per paper, upserted (writing again replaces it), so it is safe to call repeatedly. Requires SF_API_KEY.

5. 5Scholar Engine MCPfound in code, not yet checkedno passport yet
   • scholar_verify_predicate

     Directly evaluates a boolean or probabilistic proposition against any state or text passage. Returns probability in [0.0, 1.0], decision latency, and provenance source (live vs heuristic).

   • scholar_research

     Executes an autonomous scientific research loop: 1. Discovers candidates on arXiv. 2. Runs Jev System One semantic gatekeeper to filter non-empirical/incompatible papers. 3. Fetches citation graphs and verifies claims against evidence text with exact spans. Returns surviving evidence-backed papers w

   • scholar_verify_claim

     Verifies an empirical or scientific claim against a specific paper's full abstract/text. Extracts the most salient evidence passage with exact character offsets. Outputs strict status (supported, contradicted, unsupported), verification probability, provenance (live vs. heuristic), and exact evidenc

6. 6scholar-aifound in code, not yet checkedno passport yet

   MCP serverxiaolongyao-lut/scholar-ai

   • literature.behavior_eval_pack

     Run deterministic local red-flag evals for MCP and agent outputs.

   • literature.health_check

     Return passive Scholar AI workflow readiness diagnostics.

7. 7Scholar Libraryfound in code, not yet checkedno passport yet
   • save_method_review

     保存宿主的方法评价及局限，必须关联该文献原文；这是AI评价而非已确认的来源身份或客观质量分数。