「research」の検索結果

DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded learning notes, summaries, research briefs, scripts, and knowledge-base material. Use when the user asks to 抓取/提取/整理 抖音视频字幕、视频文案、ASR 转写、Qwen3-ASR 中文转写、原始材料归档、学习笔记、analysis plan、note budget、避免返工、复用已有素材、评论洞察、账号分析、赛道/话题研究、竞品拆解、电商/本地生活视频分析、事实核查、自动搜索素材, save Douyin content as Markdown/TXT, or use subtitle/local ASR as the factual spine with logged-in Douyin Web built-in AI / Doubao fallback as visual or quick-reading supplements.

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。

This skill should be used when the user asks about "technical decision", "what to use", "A vs B", "comparison analysis", "library selection", "architecture decision", "which one to use", "tradeoffs", "tech selection", "implementation approach", or needs deep analysis for technical decisions. Provides systematic multi-source research and synthesized recommendations.

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 content creation workflow that orchestrates research, editorial review, and social distribution agents in sequence. Use when the user wants to create, review, and distribute content through a multi-stage pipeline, or says "/content-pipeline".

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。

Plans, researches and writes comparison pages: "[rival] alternatives", "[product] vs [rival]", "[rival A] vs [rival B]" and switching guides. Builds each page from a ledger of sourced, dated facts and ends with an honest verdict on who should choose which product. Use when someone asks for an "alternative page", a "vs page", a "competitor comparison", "comparison landing pages", "why us instead of them", or wants existing comparison pages checked for outdated prices and claims that cannot be backed up.

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。

Research topics and write content like blog posts, articles, and marketing copy. Use when a user asks to write a blog post, create an article, draft marketing copy, write website content, create a newsletter, produce thought leadership content, or write any long-form or short-form copy.

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。

You are an expert in Clay, the data enrichment and outbound sales platform that pulls from 75+ data providers to build rich prospect profiles. You help teams automate lead discovery, enrich contacts with firmographic and technographic data, score leads against ICP criteria, and trigger personalized outreach sequences — replacing manual research with automated, data-driven prospecting.

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。

Optimize mobile app listings for discovery and conversion in Apple App Store and Google Play. Use when tasks involve ASO keyword research, title and subtitle optimization, screenshot and preview video design, A/B testing store listings, review management, localization for international markets, tracking keyword rankings, or improving download conversion rates. Covers both iOS and Android store algorithms and best practices.

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。

Infrastructure and practices for reproducible computational research. Covers environment management, data versioning, code documentation, and sharing protocols that enable others to reproduce your results. Use when ", " mentioned.

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。

Expert in competitive intelligence - systematic gathering, analysis, and application of information about competitors. Covers competitive research, win/loss analysis, competitive positioning, and building competitive advantage. Knows when to compete and when to differentiate. Use when "competitive intelligence, competitor analysis, win loss, battlecard, competitive positioning, market landscape, competitor, " mentioned.

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。

World-class color theory expertise combining the scientific precision of Josef Albers' "Interaction of Color," the systematic thinking of color systems from Pantone and RAL, and the perceptual psychology insights from researchers like Bevil Conway. Color is not just aesthetics - it's communication, emotion, and usability compressed into wavelengths. Great color work is invisible when done right. Users don't notice "nice colors" - they notice when they can't read text, when buttons don't look clickable, when errors don't feel urgent, or when the interface feels "off" without knowing why. Color theory is the science of making the right thing feel obvious. Use when "color theory, color palette, color scheme, color harmony, complementary colors, analogous colors, contrast ratio, dark mode colors, light mode, color tokens, semantic colors, color accessibility, color blindness, color psychology, color system, brand colors, data visualization colors, color, design, accessibility, contrast, dark-mode, theming, tokens, wcag, palette, harmony" mentioned.

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。

Keyword research and opportunity scoring via the DataForSEO Keywords Data and Labs APIs. Returns search volume, CPC, competition, intent classification, related keywords, and long-tail suggestions with a Keyword Score (0-100).

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 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。

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 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。

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。

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。

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。

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。

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。

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。

App Store Optimization (ASO) Skill workflow skill. Use this skill when the user needs Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Astropy workflow skill. Use this skill when the user needs Astropy is the core Python package for astronomy, providing essential functionality for astronomical research and data analysis and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

App Store Optimization (ASO) Skill workflow skill. Use this skill when the user needs Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。