「info」の検索結果

Label smarter, not more — pick the most informative examples for annotation to maximize model gains per label.

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 tools for AI agents — clean function interfaces, typed schemas, informative errors, idempotency, and tool documentation. Use when giving an agent new capabilities or fixing flaky tool use.

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。

Marketing analytics and data-driven optimization for B2B SaaS campaigns. Use this skill when analyzing marketing performance, optimizing conversion rates, running A/B tests, conducting customer research, creating marketing dashboards, building attribution models, analyzing funnel metrics, or storytelling with data. Also triggers on: marketing ops, performance analytics, CRO, A/B testing, data storytelling, customer insights, tracking plan, event taxonomy, UTM taxonomy, GA4 audit, consent mode, instrumentation contract, sample size calculation, minimum detectable effect, test duration, not enough traffic to A/B test, statistical significance, Bayesian vs frequentist, sample ratio mismatch, experiment feasibility, martech stack, marketing tech stack audit, tool consolidation, build vs buy, vendor evaluation, shadow IT tools, ESP/CRM/platform migration, switching cost, cutover plan, suppression list migration, data portability, customer interviews, survey design, sampling frame, non-response bias, how many people should I interview, thematic saturation, voice of customer, jobs-to-be-done, buyer persona research, is this finding real, data enrichment, which enrichment provider should we buy, waterfall enrichment, contact data quality, match rate, our list data is bad, email verification, catch-all domain, accept-all, bounce rate from bad data, B2B data decay, how often should we re-verify contacts, ZoomInfo vs Apollo vs Clearbit evaluation, cost per usable record, where did this list come from, GDPR Article 14 notice, purchased list compliance, suppression screening, TAM list building, demand planning, marketing plan, how many leads do we need, what pipeline target should marketing carry, funnel model, top-down vs bottom-up plan, plan of record, annual marketing planning, quarterly planning, pipeline coverage we have to create, sales cycle lag, our leads cannot close this quarter, carry-in pipeline, scenario planning, conservative moderate aggressive forecast, stretch target, reforecast, re-forecast triggers, assumption register, capacity ceiling, addressable audience ceiling, marginal cost per lead, blended CPL is wrong, we missed plan and nobody knows why, AI policy for the marketing team, AI governance, AI acceptable use policy, which AI tools are we allowed to use, can I paste customer data into ChatGPT, shadow AI, AI use register, human review of AI output, when can we stop reviewing every AI draft, can the agent send on its own, the AI made a mistake now what, pull back AI autonomy, AI evals, our AI vendor changed the model, AI output went out wrong, prompt injection, can our AI read prospect replies safely, lethal trifecta, the AI leaked internal notes, turn off auto-generated ad assets, auto-applied recommendations, AI literacy training, EU AI Act Article 4, duplicate records in the CRM, dedupe before import, which value wins in a merge, CRM cleanup.

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。

Reviews game audio code for Wwise/FMOD integration safety, custom DSP plugin correctness, and audio middleware usage. Use when the user asks to review a Wwise plugin, check an FMOD DSP effect, audit game audio middleware integration, or asks "is my game audio code safe?". Trigger on phrases like "review my Wwise plugin", "check FMOD DSP effect", "is my game audio code safe", "review my audio middleware integration", or when you see AkPluginInfo, FMOD_DSP_DESCRIPTION, IMetaSoundSource, or Execute/process callbacks in game audio 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。

Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to rule on cases an LLM classifier or rater panel judged, (2) a labeler reports "there is no information to label from" or cells look empty in Excel, (3) excerpt columns cluster at one exact length (e.g. all 1,500 chars — a hard truncation cap). Covers: full rating-basis recovery, Excel 32,767-char cell cap, multi-line CSV mangling, ruling dropdowns, companion text files.

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。

Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.

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。

Create graph-informed implementation plans before writing code. Use before any non-trivial task. Skip for small changes (≤2 files, <20 lines, no hub/bridge).

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。

Apply a formal state machine to issues — assign category (bug/enhancement/question/spike) and state (needs-triage → needs-info → ready-for-agent → ready-for-human → wontfix). Issues marked ready-for-agent become inputs to supergraph:plan. Use when processing a backlog, reviewing new issues, or preparing work for automation.

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 generating or editing diagrams, charts, visual assets, posters, UI mockups, product images, infographics, academic figures, comics, avatars, storyboards, brand boards, or image-edit workflows, especially when exported PNGs need visual QA and bounded self-repair. Prefer deterministic Mermaid/SVG/HTML/canvas sources for text-heavy diagrams; use HTML technical diagrams for browser-ready system blueprints, architecture, deployment topology, agent runtime, memory flow, before-after architecture, workflow, sequence, data-flow, lifecycle, runbook, PII/data-lineage, and state-machine diagrams. Do not use for ordinary UI polish without generated imagery.

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 task needs the judgment of an Environmental Compliance Inspector — reviewing discharge monitoring reports or emissions data against permit limits, classifying a facility's hazardous waste generator status, calculating a penalty for a documented violation, deciding whether an exceedance warrants a Notice of Violation versus informal correction, or scoping a multimedia (air/water/waste) inspection.

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 task needs the judgment of a Clinical Research Coordinator — managing patient recruitment/enrollment against a trial's screen-fail rate, handling a protocol deviation, tracking informed consent and regulatory documentation, or coordinating a multi-visit study schedule against patient retention risk.

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 task needs the judgment of a Chemical Engineer — closing a mass/energy balance around a reactor or separation unit, evaluating scale-up risk from bench to pilot to plant, reviewing a HAZOP finding or LOPA scenario for a covered process, sizing relief for a runaway-reaction or fire case, or checking a process safety information (PSI) package against OSHA 1910.119 before startup.

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 task needs the judgment of a Business Teacher, Postsecondary — grading case analysis on the rigor of business reasoning rather than matching a single "correct" answer, updating stale textbook examples against current market conditions rather than teaching them as still-current, distinguishing taught analytical frameworks from personal business opinion presented as universal fact, and preserving the incomplete-information trade-offs of real business decisions rather than simplifying problems into false certainty.

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 task needs the judgment of an Art Therapist — matching art media to a client's regulation capacity via the Expressive Therapies Continuum, scoring a standardized directive (PPAT, KFD, DAP) with a validated instrument like FEATS as part of assessment, deciding between a directive and open-studio session structure, navigating informed consent and disposition for client-made artwork, or distinguishing an art-as-therapy approach from an art-psychotherapy approach for a given client.

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 task needs the judgment of an animal trainer — designing a behavior-modification plan for a specific problem behavior, choosing a reinforcement schedule and deciding when to raise criteria, structuring session length and frequency to avoid fatigue or frustration plateaus, or setting a handler/public safety protocol around a training animal.

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 task needs the judgment of an Anthropologist/Archeologist working in cultural resource management (CRM) — scoping a Section 106 Phase I identification survey, designing a shovel-test-pit sampling strategy, evaluating National Register of Historic Places eligibility under Criteria A-D, interpreting excavation stratigraphy via a Harris matrix and radiocarbon results, or running the ethnographic field-methods branch (participant observation, informant interviewing) for a cultural-anthropology component of a 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 task needs the judgment of an Application Security Engineer — checking whether an endpoint verifies object-level authorization (not just authentication), running threat modeling at design time rather than deferring security review to the end, triaging a dependency vulnerability by actual reachability rather than CVSS score alone, combining SAST/DAST/SCA tooling to cover their distinct blind spots, or applying context-specific output encoding to untrusted input. Distinct from an information security analyst — this role works inside the SDLC to prevent vulnerabilities before they ship, not detect and respond to intrusions in production.

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。

Track exact provenance for every operation on ENCODE data — tool versions, reference files, scripts, parameters, and timestamps — to enable publication-ready methods writing. Use when the user processes ENCODE files, runs any bioinformatics tool, creates filtered/merged datasets, runs pipelines, performs liftover, uses R/Python/Bash for analysis, or needs to document their analysis chain for reproducibility and publication. Also use when the user says "write me methods" to auto-generate methods sections from the provenance log. This skill implements comprehensive provenance documentation: every tool, every version, every reference file, every parameter, every accession — no shortcuts. Use this skill for ANY processing step, ANY file transformation, ANY analysis operation on ENCODE data.

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。

Assess the scientific integrity and trustworthiness of publications before relying on their findings. Use this skill whenever evaluating a paper for a workflow, citing a study, building an analysis on published methods, or when a user asks about the reliability of a study. Checks for formal retractions, corrections, expressions of concern, and — critically — informal contradictions where subsequent studies failed to reproduce key findings. Integrates with PubMed, bioRxiv, and Consensus to provide a trust assessment. Use this skill for ANY publication evaluation, retraction checking, author reliability assessment, or when a user says "can I trust this paper", "is this study reliable", "has this been refuted", or "check this publication".

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。

Detect documentation drift, stale references, and cross-document inconsistencies in any project. Scans for code-doc drift (API/function changes not reflected in docs), cross-doc drift (conflicting information across documents), and stale references (broken links, deleted files, outdated versions). Use when checking "doc freshness", "stale docs", "documentation drift", "broken links", "outdated documentation", "doc accuracy", "docs out of date", "doc audit", "doc health", or "verify documentation".

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。

Manage Volcengine's AI-native BaaS platform (Supabase edition / AIDAP / 火山引擎 AI 原生 BaaS 平台 Supabase 版) — a Volcengine-operated distribution that differs from official Supabase. Use when the user asks to create, inspect, or manage Volcengine Supabase or AIDAP resources — workspaces, branches, computes, SQL queries, schema changes, Auth, Realtime, Edge Functions, Storage buckets, frontend static-site hosting (Pages), API keys, connection info, or TypeScript type generation — or when a Volcengine deployment selects AIDAP as its database provider. Also trigger on Chinese prompts mentioning "火山引擎 Supabase" or "火山 Supabase". Operations run through the byted-supabase-cli command-line tool (installed via `npm i -g @byted-supabase/cli`; this is NOT the official `supabase` CLI). Do NOT use it for general database discussions, non-Supabase services (RDS MySQL, Redis), or pure client-side coding unrelated to Supabase backend management.

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。

采集科研数字分身的基础信息（研究阶段、学科领域、方法范式、技术能力、科研流程能力）。当用户开始建立科研数字分身、或基础信息尚未填写时使用。

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。

Guidance for Tauri v2 process plugin with controlled process information exposure.

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。

Answer questions about the user's Muse subscription, plan, usage, tokens, reset timing, or available plans and prices, or verify information that references the Muse subscription.

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。