「anchore」の検索結果

Project gene annotations across genomes using TOGA (Kirilenko 2023 whole-genome-alignment chain-based projection with intactness classification), CESAR 2.0 (Sharma & Hiller 2017 codon-aware exon projection), LiftOff (Shumate & Salzberg 2020 reference-based annotation transfer), Liftover (UCSC), GeMoMa (Keilwagen 2019 evidence-based projection), and Comparative Annotation Toolkit (CAT). Use when transferring annotations from a well-annotated reference to query genome(s), classifying gene-loss vs gene-intact across many genomes at scale, building Zoonomia-style comparative annotations across hundreds of mammals or birds (Kirilenko 2023), detecting pseudogenization, projecting alternative isoforms, or selecting between WGA-anchored (TOGA) vs ortholog-based (LiftOff) annotation transfer strategies.

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。

Miro presents itself as the AI-powered visual workspace through a confident, almost playful brand voice — anchored by its signature canary yellow ({colors.brand-yellow}) wordmark over white canvas, broken open by colorful pastel feature tints (rose, teal, coral, orange, mint) that echo the actual sticky-note color palette used on the live whiteboard. Black-pill primary buttons dominate marketing, real Miro-board mockups serve as feature illustrations, and a 4-tier pricing grid leads into a dense comparison table. Roobert PRO carries display headlines; the system supports homepage, pricing, AI Workflows product page, agile vertical, and customer stories surfaces.

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。

An inspired interpretation of HP's design language — a white-paper enterprise-consumer system anchored by HP Electric Blue (`#024ad8`) as the lone signal CTA, near-black ink (`#1a1a1a`) for headlines, geometric Forma-DJR sans throughout, and angular blue-chevron decorations that nod to the HP wordmark's slashes. Cards round at 8–16px, photos sit in soft 16px frames, and dark navy slabs anchor the customer-story and "how can we help" closing bands.

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。

A clean, calendar-software-first interface anchored on white canvas with black primary CTAs and custom Cal Sans display typography. The system reads as friendly modern SaaS — generous whitespace, soft-rounded cards (~12px), product UI fragments shown directly inside cards, and a dark navy footer that visually closes long-scroll pages. Brand voltage comes from the Cal Sans display headline (a custom geometric face) and from product UI artifacts shown in-card rather than from accent colors.

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。

Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark. Triggers on starting new products/features, validating market opportunities, drafting PRD Why sections, or requests like "frame the problem", "define pain points", "write problem statement", "start v0.1", "what problem are we solving". Outputs structured problem tables with CFD evidence IDs.

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。

Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the results", "check the eval code", "实验诚实度".

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。

Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every finding span-anchored to the evidence ledger (claims.json), reviewer≠adjudicator. Emits consistency-audit.findings.json; NEVER computes the verdict. Triggers: "consistency audit", "check the paper against itself", "self-consistency", "内部自洽".

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。

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".

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。

MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP fuzzy-title + boolean · WebSearch · WebFetch) from the paper's own title + contribution spans in the evidence ledger; TWO fresh cross-model codex reviewers (one per axis) LAY OUT the overlap side-by-side against each anchored contribution claim. It NEVER rules 'trivial' or 'duplicate' (that is a human judgment) and absence of a match is NOT evidence of originality. Emits novelty-duplication-advisory.memo.md + an info-only findings mirror; carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Detect-only. Adapted from ARIS novelty-check, reframed from 'is MY idea novel' to 'here is the overlap a reviewer should weigh'. Triggers: "novelty advisory", "duplication check", "prior-work overlap", "is this stapling", "缝合", "查重", "重复发表", "duplicate submission".

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。

Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real paper cited for a claim it never makes — or argues against). A hot zone for machine-generated papers. Decidable at L0 (text + canonical sources). Span-anchored to the evidence ledger (claims.json); the executor gathers canonical facts (DBLP / arXiv / DOI), then one FRESH cross-model thread per cited key proposes findings; reviewer != adjudicator. Emits citation-forensics.findings.json; NEVER computes the verdict. Triggers: "citation forensics", "check the references", "hallucinated citations", "wrong-context citation", "verify references", "引用核对".

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。

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".

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。

Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe paper".

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。

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。

Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation — verdict-bearing at L1 (the LaTeX source; PDF-extracted math is unreliable, so an L0 PDF-only run surfaces info only) — never asserts 'fabricated', only that the step shown does not hold. A fresh cross-model reviewer reads the theorem/proof + an extraction-only obligation scaffold and proposes per-obligation findings, each span-anchored to the evidence ledger (claims.json); reviewer≠adjudicator. Emits proof-derivation-forensics.findings.json; NEVER computes the verdict. dimension=proof, can be critical. Triggers: "proof forensics", "check this proof", "derivation integrity", "audit the math", "证明审计", "推导有没有漏洞".

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。

Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".

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。

Generate hierarchical _FEATURES.md files that describe what a codebase DOES from a user/consumer perspective, anchored to source symbols via tree-sitting. Supports large complex codebases through feature-driven decomposition into sub-feature files. Uses a multi-pass synthesis: orientation → detail → overview rewrite. Use when someone says "what does this do", "document features", "feature inventory", "_FEATURES.md", or needs to understand a codebase's purpose before modifying it. Complements tree-sitting (structural) with semantic (why/what-for) layer.

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。

Turn a short video into a narrated comic strip. Use when the user uploads a video (.mov/.mp4/etc.) and asks to make a comic from it, narrate it, draw it, Attenborough it, storyboard the clip, or otherwise wants a stills-plus-narration comic strip derived from footage. Covers probing and extracting frames, GROUNDING the actual storyline (native Gemini video parse or frame reading), composing narration in a chosen voice, generating comic panels with Gemini image models anchored to the real stills, QA-ing the panels, and compositing a titled strip. Do NOT use for plain video transcoding or trimming (that is processing-video) or for original illustration from a text prompt (that is invoking-gemini).

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。

Designs Amazon-compliant main product images and the 7 secondary image types (Infographic / Multi-angle / Detail Shot / Lifestyle / Variants / What's in Box / Size Reference) — with platform-mandatory main-image rules, conversion-rate-tuned secondary types per product category, and multi-image consistency anchored to the main image URL. Use when the user says "Amazon main image", "亚马逊主图", "product main image", "white background product image", "Amazon listing image", "亚马逊副图", "secondary images", "product carousel images", or any request for the 1:1 product image suite that lives on the Amazon detail page carousel. For A+ Content / detail-page modules (21:9 Hero Banner and 3:2 module layouts), see the `product-shots-detail-page` skill.

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。

Designs Amazon A+ Content (formerly Enhanced Brand Content) — the 8 module suite that appears below the standard product carousel for Brand Registered sellers. Covers Hero Banner (21:9 / 2388×1024), Pain Points / Selling Points / Technology / Data / How-to-Use / Variants (3:2 / 1536×1024), and Endorsement (21:9), with mobile safe-area rule, 30pt text floor, and cross-module consistency anchored to the main image URL. Use when the user says "A+ page", "A+ content", "Amazon A+", "Brand Content", "Enhanced Brand Content", "亚马逊详情页", "A+ 详情页", "21:9 banner", "Hero Banner", "Amazon detail page module", or any request for the brand-registered detail-page module suite. For the 1:1 main image and carousel secondary images, see the `product-shots-main-image` skill.

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。

Design an inquiry sequence anchored in a local ecosystem that embeds science or geography curriculum content. Use when teaching through local living systems like gardens, ponds, or hedgerows.

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。

Use this skill when building, debugging, or answering questions about Liveblocks. Liveblocks gives you the building blocks and infrastructure to enable people and AI to work together inside your app, powering realtime collaboration. Liveblocks features include collaboration, rooms, organizations, workspaces, comments, composer, threads, notifications, multiplayer, conflict resolution, realtime presence, avatar stacks, AI collaborators, AI agents, text editors, Tiptap, BlockNote, Lexical, React Flow, Chat SDK. Common components include AiChat, Thread, InboxNotification, Composer, Toolbar (for Lexical Tiptap), FloatingToolbar, FloatingComposer, FloatingThreads, AnchoredThreads. Common hooks include useThreads, useStorage, useMutation, useOthers, useInboxNotifications, useAiChats. Common issues are related to authentication (ID tokens vs access tokens), permissions, room limits, connection errors, user info.

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。

Audit the reasoning of a document or argument (memo, proposal, investment analysis, board paper, article, the user's own draft): claims, evidence, unstated assumptions, logical gaps, fallacies, and what would falsify it, each anchored to quoted text. Use whenever the user wants reasoning examined, in any language ("audit this argument", "is this analysis sound", "poke holes in this proposal", "review the logic of my draft"; Vietnamese "phản biện giúp tôi", "soi lập luận này", "tài liệu này có lỗ hổng gì", "góp ý bản nháp của tôi"), even when they never say "critical thinking". Also use when the user drops a document and asks whether to trust or act on it, or asks to see their reasoning profile. Not for company-level strategic bets (strategy-board) or learning a topic through dialogue (socratic-questor).

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。