「search run」の検索結果

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。

First-encounter orientation on a repository nobody here has worked in yet. Runs a fixed five-step workflow — venv setup, tarball fetch, tree-sitting structural scan, featuring synthesis, then reasoning over the two — and yields an account of what the repo contains and how it is arranged, optionally written out as _FEATURES.md. Use for "I just cloned this", "what is this repo", "what does this do", "explore this repo", "give me an orientation", "what are the main features", "review what's new in this repo", or before starting work in a codebase you have not seen. This is the divergent what's-here skill. Route elsewhere for: a named symbol, a file's structure or a line range (tree-sitting); all callers of a Python symbol (searching-codebases); teaching a human the codebase through exercises (orienting-codebases); fetching or cloning a repo without analysing it (accessing-github-repos, cloning-project).

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 when a researcher, maintainer, or contributor found or suspects a malicious skill on ClawHub and needs a private reporting workflow: opening a GitHub private vulnerability report, preparing a proposal-only PR, creating `proposals/<GHSA-ID>/clawscan.yml`, running ClawScan against the malicious skill, and explaining what evidence belongs in private versus public channels.

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。

Generates a fully structured SEO content brief for a target keyword and optionally pushes it to a Notion database. Use this skill whenever the user says 'create a content brief', 'brief this keyword', 'run a content brief for', 'generate a brief', 'write a brief for [keyword]', 'content brief on [topic]', or any variation where someone needs a keyword researched and turned into a structured writing assignment with H1, H2 outline, FAQ, internal links, word count target, and writer notes. Also triggers when the user provides a keyword and asks for an SEO brief, editorial brief, or writing spec. Outputs a mandatory structured format that the text parser maps directly to Notion properties. Supports single-keyword and batch (CSV) modes.

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。

Your For You page for content creators. Scrapes tracked competitors across social media platforms, scores what's performing, and turns it into actionable, differentiated content ideas backed by real engagement data. Use this whenever the user wants competitor/creator research, a content feed or "for you" page, trending-topic ideas in their niche, to see what's working on social, to track what creators are posting, or to generate video/post briefs from what's performing — even if they don't say "find ideas." First run walks through setup.

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。

Suede-owned SEO and generative-search audit discipline. Runs a nine-lane evidence-based audit: access, intent, metadata, structure, supported schema, E-E-A-T, clusters, and exact rewrite fixes. Use when a page or site needs a deep standalone SEO/AI-visibility audit with scored lanes. NOT FOR: a fast A-F launch-appeal grade (use suede-visibility-grader); conversion-path rework after the audit (use suede-site-alchemy); getting cited by ChatGPT/Perplexity/AI Overviews (use suede-ai-seo).

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。

Extract structured company lists from directories with Firecrawl. Use for scraping YC, Crunchbase, Product Hunt, G2, startup directories, category directories, or custom company databases into JSON, CSV, CRM-ready lists, or research tables.

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。

Run outcome-focused Firecrawl workflows that produce deliverables such as research reports, literature reviews over published papers, SEO audits, QA reports, lead lists, knowledge bases, website design systems, and other structured web-data artifacts. Use when the user wants Firecrawl to complete a business, marketing, product, or creative workflow rather than merely scrape a page or integrate API calls into code.

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。

Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.

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, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. DO NOT TRIGGER when: Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work is unrelated to Agent Script; or the primary input is a production session or trace ID rather than an agent artifact.

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。

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

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 RAG retrieval for LLM grounding: chunking, BM25+vector hybrid, reranking, GraphRAG. Use when adding embeddings to SQLite FTS5 search or running held-out retrieval eval.

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。

Run metric-driven optimization loops. Use when improving measurable outcomes such as search relevance, clustering quality, build performance, prompt quality, or scored behavior through experiments.

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。

Execute bounded, reproducible experiment rounds.

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。

Convert run artifacts into calibrated interpretation and next decisions.

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 guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks

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。

Quellenbasierte Profile einzelner Wettbewerber aus öffentlichen Informationen erstellen. Nutze diesen Skill, wenn Positionierung, Zielgruppe, Produkt, Preise, Organisation und Belegbehauptungen eines Anbieters zusammengetragen werden sollen, als Kurzbrief, fokussiertes Profil oder vertiefte Recherche. Trennt Tatsache, Anbieterangabe, Schätzung und Hypothese in einem Claim-Ledger, hält Quellen mit Datum fest und beachtet Datenschutz, Datenbankrechte, Urheberrecht und Geschäftsgeheimnisse. Kein Scraping über das Freigegebene hinaus, keine Personendossiers. Für vergleichende Seiten: competitors.

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 a state document (context transfer) that allows any fresh AI instance to resume work without conversation history. Use this skill whenever the user asks to checkpoint, create a state transfer, save state, generate a handoff document, create compaction insurance, or says anything like 'snapshot this', 'create a context transfer', 'checkpoint', 'save state for handoff', 'write a recovery doc', or 'transfer context'. Also trigger when the user mentions compaction concerns, session handoff, multi-session continuity, or wants to preserve the current conversation's state. Works for any conversation type: projects, research, debugging, investigations, design sessions, or long-running chats. This skill produces a structured markdown document optimized for AI cold-start recovery, not human notes.

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。

Jurisdiction comparison for a legal requirement or contract clause. Use when asked "how does this differ by jurisdiction", "compare GDPR and CCPA on this", or "run a state law comparison".

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。

Run a broad SEO audit across technical SEO, on-page SEO, schema, sitemaps, content quality, AI search readiness, and GEO / Audit SEO menyeluruh (Technical, On-Page, Schema, Sitemap, E-E-A-T, GEO)

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。

Bioactivity and small-molecule data-side catalog. Covers ChEMBL search/lookup, MolTrack compound and batch registration, HitTriage / HitDesign / PeptiHit workflows, and Curves dose-response analysis (IC50/EC50 fitting). Open this skill when the user asks about querying ChEMBL, registering or looking up compounds in MolTrack, running a hit-triage campaign, or fitting/inspecting dose-response curves.

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。

Batch download academic paper full-text (PDF/XML) from a list of DOIs. Handles 25 DOI prefixes across 19 publisher families via three layered routes: (1) publisher TDM APIs requiring institutional subscription (Elsevier ScienceDirect, Wiley Online, Springer Nature), (2) Open Access sources (Crossref, Unpaywall, OpenAlex), and (3) a browser-based fallback for paywalled publishers without TDM access (ACS, RSC, IEEE, AIP, IOP, APS, Annual Reviews, T&F, Chinese journals). Browser fallback offers two routes — Route A drives the user's logged-in Chrome via the OpenClaw `browser` tool with `profile="user"` (best for interactive sessions), Route B uses the standalone `auto-paper-harvester` CLI with its built-in Playwright (best for unattended bulk runs). Use when the user wants to harvest, scrape, fetch, or bulk-download papers from a DOI list, savedrecs export, or Excel; or wants to fill missing full-text PDFs for an existing literature collection. Triggers on phrases like "批量下载文献", "下载全文", "harvest papers", "scrape full text", "TDM API", "下载 Elsevier 全文", "Wiley 批量下载", "下载 PDF".

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。

Analyze the causal system-wide impact of a proposed change across behavior, interfaces, state/data, runtime dependencies, tests, documentation, controls, people/processes, and model/prompt/context behavior. Use before planning when lexical reference search is insufficient to establish blast radius and verification obligations.

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。

Runs a deliberative two-model committee of GPT-6 Astra and Claude Opus under a selectable chair, Fable by default, with `/model-committee-astra`, `/model-committee-opus`, and `/model-committee-sol` selecting the others. Use when a consequential decision has several defensible options and two model families should propose, critique, revise, and cross-rank them against a predeclared rubric before converging, as in research design, interpretation, architecture, manuscript strategy, or evaluation design. Not for factual lookups, independent-coder reliability, brainstorming, routine implementation, or final professional judgment.

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。