「paper」の検索結果

Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the ~200-word rejection paragraph (every accusation tagged to an existing claim_id/finding_id), a defense decomposes it and rules each point against the anchored evidence. MEMO-ONLY: emits adversarial-case-builder.memo.md (fed to the adjudicator via --memo) and carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Honest-null allowed (the paper may survive). Run LAST. Detect-only. Adapted from ARIS kill-argument. Triggers: "adversarial case", "strongest objection", "rejection memo", "kill argument", "最强拒稿点".

日本語の概要は準備中です。原文の説明を表示しています。

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing-style impressions, never moving the verdict). Triggers: "anti-autoresearch", "integrity audit this paper", "forensic review", "audit a submission", "审一篇投稿的诚信".

日本語の概要は準備中です。原文の説明を表示しています。

Generate navigable semantic maps from PDF documents. Extracts section structure via font analysis, then runs LLM extraction per section for claims, symbols, and dependencies — all page-anchored. Produces _MAP.md (progressive disclosure), .symbols.json (definition index), .anchors.json (claim references), and a _USAGE.md snippet for CLAUDE.md. Use when analyzing papers, specs, or legal docs; when asked to "map this document", "index this PDF", "what does this paper say"; or when a coding agent needs grounded reference material from a PDF source. Analogous to tree-sitting but for prose documents.

日本語の概要は準備中です。原文の説明を表示しています。

Art-direct and generate one high-craft minimal-zine bitmap from a landscape, portrait, person, object, product, food, plant, building, interior, photograph, mood, sentence, or article concept. Use when the user wants a standalone poetic poster, editorial cover, visual concept, aesthetic photo upgrade, photo-to-zine restyle, or a subject-aware minimal-zine image without the overhead of a social carousel. Chooses adaptive composition and a physically coherent print process, preserves subject identity, saves the final prompt, invokes the runtime-native image generator, and audits the raster result.

日本語の概要は準備中です。原文の説明を表示しています。

Plan, write, art-direct, generate, and package a coherent 2-10 image minimal-zine social series from notes, articles, photographs, travel stories, products, reviews, cultural topics, data, PDFs, or mixed subjects. Use for Xiaohongshu/小红书图片, Instagram carousels, social visual essays, recommendation posts, photo diaries, evidence-backed explainers, or any multi-image editorial sequence. Produces analysis, card roles, subject-aware composition, saved prompts, real raster images, natural caption copy, evidence provenance when needed, and series-level QA.

日本語の概要は準備中です。原文の説明を表示しています。

How the Strategist works with the user to turn their own trading idea into explicit rules, backtest it honestly on Hyperliquid candle and funding history, and paper-trade it on testnet through the desk lifecycle. Method only - the desk ships no strategies and makes no return claims. Use when the user wants to design, test, compare or paper-trade an idea.

日本語の概要は準備中です。原文の説明を表示しています。

Mines recent papers, blogs, and newsletters for methods worth stealing, with graded evidence. Use when finding recent papers or techniques for RAG, evals, or agents.

日本語の概要は準備中です。原文の説明を表示しています。

Generate Muted Zine Poster v0.1 poetic paper-poster prompts and the matching generated image. Use when the user gives a theme, sentence, object, mood, article idea, photo, or content brief and wants a quiet Japanese/Korean zine-like editorial poster with large negative space, aged paper texture, experimental typography, and a restrained muted palette without high-chroma color blocks. This is the low-saturation sibling of gc-minimal-zine-poster-v0-1.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-layout. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-harden. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-citation. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-data. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-research. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-argument. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Build, revise, audit, or rebut a research manuscript from Harness Research evidence. Use for paper intake, related-work research, claim and citation control, section architecture, LaTeX patching, figure planning, reviewer response, or final manuscript hardening when the workspace contains Harness research artifacts.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-patch. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-intake. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-response. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Internal Harness instruction source for auto-paper-figure. Route through visible Harness aliases instead of invoking directly.

日本語の概要は準備中です。原文の説明を表示しています。

Build, critique, and refine academic posters from a paper, LaTeX project, reference draft image, HTML/CSS source, PPT/PDF outputs, or local figure assets. Use when Codex is asked to create or improve a research poster, convert a poster design to HTML/PDF/PPTX, fix poster layout/typography/overflow/blank-space issues, or preserve paper figures and result semantics in a poster.

日本語の概要は準備中です。原文の説明を表示しています。

Read, study, and answer questions about long books and papers without loading the whole text into one context window, keeping page-anchored notes as a reusable workspace. Use whenever the user asks to read, study, summarize, analyze, review, or answer questions about a long book, textbook, PDF, EPUB, thesis, dissertation, survey paper, or any document of roughly 50+ pages, in any language (Vietnamese "đọc sách", "tóm tắt sách", "phân tích luận án"). Also use when a `{slug}-notes/` workspace from a previous session sits next to a source file and the user asks a follow-up question about that book. Not for short documents (under ~30 pages) that fit in context; read those directly.

日本語の概要は準備中です。原文の説明を表示しています。

Personal document management skill using Paperless-ngx. Use when: (1) Ingesting and filing new documents, (2) Searching for existing documents, (3) Applying tags and correspondents, (4) Managing retention policies, (5) Integrating documents with other personal workflows (tax prep, medical records, insurance claims). Tools: paperless-mcp for all document operations.

日本語の概要は準備中です。原文の説明を表示しています。

Wireframe a screen — text/ASCII by default, or hand-drawn HTML when the user says "sketch", "hand-drawn", "lo-fi HTML", "whiteboard", "graph paper", or "visual wireframe". Text mode produces a buildable ASCII spec Form and Prism can act on. HTML mode produces a single self-contained file with graph-paper background, marker headlines, sticky-note annotations, and hatched chart placeholders — looks like a designer's whiteboard, commits to nothing.

日本語の概要は準備中です。原文の説明を表示しています。