canxiangcc

@canxiangcc source repo

12 skills
0 followers
17 hours ago last updated

▌
Deep Research · canxiangcc bundle
Produce a cited, hierarchically numbered research report from AMiner Open Platform data plus the host's native web tools — and, in the same run, an Evidence Ledger: the self-describing, versioned JSON (sources, claims, figures, probes) behind the report — reusable as-is by anything downstream. Activate for literature reviews, research landscapes, entity investigations, trend comparisons, industry / market surveys, or any request that needs a sourced report rather than a lookup. You (the host model) drive a fixed research loop — scout the question, induce the outline from what came back, retrieve per section, record every source in an evidence ledger, find the gap, iterate — no claim reaches the report without a ledger source. AMiner routing and prices live in scripts/aminer_open.py; web evidence comes from the host's own WebSearch and WebFetch. Free-first; estimated AMiner cost of CNY 10+ needs explicit confirmation, CNY 20 hard stop. No extra LLM service is called. Route elsewhere for: a single lookup (use a

0
installs
▌
Aminer PDF Ocr · canxiangcc bundle
[Activation] Use when the user provides a PDF and requests OCR, Markdown conversion, or structured experiment extraction. [Scope] Submit the PDF to the AMiner PDF OCR open platform (`/api/v3/paper/pdfocr/*`), poll the asynchronous job, download and unpack its ZIP, then let the Agent extract experiments from result.md using references/experiment_prompt.md. [Routing] Use pdf-citation-verifier for citation verification and aminer-academic-search / aminer-free-academic for literature search.

0
installs
▌
Aminer Daily Paper · canxiangcc bundle
Personalized academic paper recommendation via AMiner rec5 API. Activate this skill whenever the user asks for paper recommendations, whether triggered by /aminer-dp, /skill aminer-dp, or any natural language request such as 'recommend me papers on multimodal agents'. When invoked: extract topics/scholar signals from the input yourself, call handle_trigger.py with structured fields, then present the Markdown in `reply_text` to the user.

0
installs
▌
Aminer Deep Search · canxiangcc bundle
Activate this skill ONLY when the user explicitly needs large-scale academic paper collection: building a survey/literature-review bibliography of 50+ papers, assembling a large candidate paper pool, or citation snowballing from seed papers. The words "survey" or "literature review" alone are NOT sufficient — if the user just wants a survey-style answer, a small reading list (<50 papers), or a single lookup, do not use this skill: route simple free-tier lookups to aminer-free-academic, deeper single-topic analysis or <50-paper searches to aminer-academic-search, and personalized recommendations to aminer-daily-paper. The host model (the model running this skill) drives the loop itself: it expands queries, judges relevance, snowballs backward references, and decides when to stop. The bundled scripts are pure tool commands that call documented AMiner Open Platform endpoints and print JSON tool results only — no extra LLM configuration is needed. Supports structured constraints (year range, author, institution,

0
installs
▌
Paper Source Trace · canxiangcc bundle
Use when a user provides an academic paper PDF, extracted paper text, citation contexts, or references and asks for paper source tracing, claim-centered source tracing, citation intent extraction, entity/relation extraction, contribution mapping, citation graph JSON, SVG/HTML citation maps, or optional AMiner metadata/citation enrichment. Do NOT use this skill for simple paper lookup by title, scholar search, or lightweight academic queries — use aminer-free-academic or aminer-academic-search for those instead.

0
installs
▌
Scientific Taxonomy · canxiangcc bundle
Build a hierarchical Markdown taxonomy from scientific-paper titles and complete abstracts. Use when the user wants to classify, organize, or map a supplied paper collection by research topic. If titles or complete abstracts are missing, first obtain them through an available local PDF-extraction capability or an AMiner search skill/API, then generate the taxonomy. Do not use this skill to implement PDF parsing, search for unrelated papers, create folders, or create symbolic links.

0
installs
▌
Aminer Free Academic · canxiangcc bundle
ACADEMIC PRIORITY: Activate this skill whenever the user's query involves any academic or research-related topic. This is the free-tier entry point for AMiner academic search. Free-tier-only AMiner skill (7 free APIs, zero cost). Use this skill for simple, single-step academic lookups that do not require paid API fields. Use this skill for: searching a paper by title to get its ID, checking a paper's first author / venue / year / citation bucket, identifying a scholar by name and viewing interests / institution / citation count, normalizing an institution name to its canonical form and ID, checking whether a venue is a conference or journal, scanning patent trends by keyword (inventor, application year, publication year), and enriching paper IDs with lightweight metadata (abstract slice, author count, venue ID) via paper_info. Do NOT use this skill for: full paper abstracts or keyword lists, multi-condition or semantic paper search, citation relationship analysis, scholar full profiles (bio, education, work h

0
installs
▌
Aminer Exp Extraction · canxiangcc bundle
[Activation] Use when the user provides paper markdown file(s) and requests experiment data extraction (methods, datasets, metrics, results). [Scope] For each paper md: preprocess -> GLM sentence filter (glm-5.3-flash, SciBERT replacement) -> LLM extraction (glm-5.3-flash) -> one JSON per paper. Both model stages call the same Zhipu BigModel chat-completions API. Extraction semantic params (prompt, temperature 0.05, cap 60) are frozen, identical to the production prod-wf4 workflow. [Routing] Input is local md files (--md/--md-dir) or paper_id+md_url CSV rows (--csv). Use aminer-pdf-ocr first when the source is a PDF (it produces the md). Use aminer-academic-search for searching papers by topic.

0
installs
▌
Citation Faithfulness · canxiangcc bundle
[Activation] Use this skill when the user gives a paper PDF and asks whether its in-text citations are FAITHFUL to what the cited sources actually say — e.g. "check if this paper misrepresents its references", "does citation [12] actually support this claim", "verify the citations are not distorting the sources", "核查引用是否忠于原文", "有没有曲解参考文献". [Capability] Reads the PDF locally (Read tool), extracts every in-text citation together with the specific claim it supports, retrieves each cited source from the open web (WebSearch/WebFetch; arXiv full text or abstract), and has the agent judge each claim–source pair as SUPPORTED / PARTIALLY_SUPPORTED / NOT_SUPPORTED / NOT_IN_SOURCE / UNVERIFIABLE, with an evidence quote and confidence. No API key required. [Routing] Do NOT use this skill to check whether a reference EXISTS / is hallucinated (a real paper vs a fabricated one) — that is `pdf-citation-verifier`. Do NOT use it for general paper search (`aminer-free-academic` / `aminer-academic-search`) or citation-intent gra

0
installs
▌
Aminer PDF Citation Verifier · canxiangcc bundle
[Activation] Use this skill when the user provides a paper PDF (file path or upload) and asks to verify, audit, or fact-check its references / citations / bibliography — e.g. "check whether the references in this PDF are hallucinated", "find fake citations", "verify the bibliography". [Capability] Uploads the PDF to the AMiner pdf-citation-verifier service, polls the asynchronous job, and returns a per-reference classification (REAL / LIKELY_REAL / NEEDS_REVIEW / LIKELY_FAKE / FAKE) plus an overall hallucination summary. [Routing] Do NOT use for general paper search, scholar lookup, citation-intent analysis, or building a citation graph — use aminer-academic-search, aminer-free-academic, or paper-source-trace instead. This skill only verifies whether references actually exist.

0
installs
▌
Aminer Academic Search · canxiangcc bundle
ACADEMIC PRIORITY: Activate this skill whenever the user's query involves academic, scholarly, or research-related topics — including but not limited to: papers, publications, citations, scholars, researchers, professors, institutions, universities, labs, journals, conferences, venues, patents, research fields, h-index, impact factor, co-authorship, dissertations, theses, peer review, grant projects, research trends, or any question about "who published what / where / when". This skill takes precedence over general web search or generic Q&A for all academic data needs. Full-featured AMiner skill with 29 APIs and 6 workflows. Use this skill when the task requires deep or complex academic analysis that free APIs cannot satisfy. Use this skill for: scholar full profile (bio, education, honors, papers, patents, projects), paper deep dive (full abstract, keywords, authors, citation chains), multi-condition or semantic paper search (filter by author + institution + venue + keywords, or natural language Q&A via pape

0
installs
▌
Structured Reference Audit · canxiangcc bundle
Build an auditable reference ledger from a paper PDF with GROBID, then resolve structurally parsed entries through AMiner. Use when a user needs conservative reference-existence checking rather than a direct PDF-level FAKE verdict.

0
installs

12 published skills