2,505 件 ・ 関連度順
概要と使いどころ
Upload images and files to GitHub PRs, issues, and comments so GitHub hosts them instead of committing binaries to the repository. Use when adding screenshots to a PR or issue body, replacing committed screenshots or raw.githubusercontent.com links with hosted attachments, or when `gh` appears to offer no way to attach a file.
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。
Size the agent-browser Chromium window to fill its current screen, leaving a configurable bottom margin for the desktop panel. Use before any agent-browser automation that needs the full screen visible without elements overlapping or scrolling off (e.g. Xero, dense web apps).
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。
Summarizes raw background check data into structured executive reports with risk categorization (GREEN/YELLOW/RED). Use when processing criminal records, court filings, employment/education verification, sanctions screening, or adverse media for pre-employment screening, executive due diligence, or investment-grade investigations.
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 and Google Play submission automator with Fastlane, screenshot automation, metadata management, and TestFlight/internal testing. Activate on: app store submission, Fastlane, TestFlight, Google Play Console, screenshot automation, metadata management, app review, code signing, provisioning profiles. NOT for: CI/CD pipeline setup (use github-actions-pipeline-builder), app architecture (use react-native-architect), analytics (use mobile-analytics-crash-reporting-expert).
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 to design contextual inputs for an always-on AI agent with episodic memory. Covers what data to feed the agent, how to structure observations and triggers, ambient context capture (screen, audio, calendar), context window budgeting, and retrieval strategies that keep the agent grounded in what's actually happening. Activate on: "what should the agent observe", "context inputs for agent", "ambient context capture", "agent triggers", "agent input design", "screenpipe integration", "context window budget", "what data to feed my agent", "/always-on-agent-inputs". NOT for: memory architecture and storage (use always-on-agent-architecture), application ideas (use always-on-agent-applications), safety concerns (use always-on-agent-safety).
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 a self-contained, visually polished HTML showcase page for a topic or set of artifacts. Supply a mission (topic summary) and optional artifact paths explicitly — the skill never auto-scans the repo. Writes output to assets/showcase/<mission>/. Screenshots are optional (requires Puppeteer). Publishing is local-only by default; publish requests without a configured path fail clearly.
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-first Figma gateway via Figma MCP: analyze designs, implement Figma-to-code for 1–3 screens, extract design tokens, produce a Figma Evidence Packet for planning handoff, screenshot fallback. Advanced operations (Code Connect, canvas writes, design-system/library patterns) are gated references loaded only on explicit intent. Triggers: 'figma', 'design link', 'implement this design', 'design tokens', 'produce a Figma Evidence Packet'.
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 an existing UI for usability, hierarchy, accessibility, and conversion problems. Reviews a live URL, screenshot, or codebase against heuristics and reports prioritized issues with fixes. Use when the user says "audit this UI", "what's wrong with this screen", "UX review", "find the problems", "why is this confusing", or has existing interface to critique. Part of the Product Design set. Can drive a browser for live audits.
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 several distinct UI directions for a screen or flow before committing to one. Produces 2-4 named interface directions with layout logic, component choices, and tradeoffs, optionally with generated mockup images. Use when the user says "ideate the UI", "give me layout options", "design directions for this screen", "explore the interface", or after context/research and before prototyping. Part of the Product Design set.
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 pooled sgRNA libraries for CRISPR knockout, interference (CRISPRi), activation (CRISPRa), Cas12a multiplex, base-editor, and prime-editor screens. Covers on-target scoring (Rule Set 2, Azimuth, DeepSpCas9, CRISPRon), off-target scoring (CFD, MIT), TSS-relative positioning for CRISPRi/a (Horlbeck, Dolcetto, Calabrese), PAM-variant chemistries, control-guide composition, oligo cloning architecture, and library QC. Use when choosing a genome-wide library (GeCKOv2 vs Avana vs Brunello vs TKOv3 vs Inzolia), designing a focused or paralog-focused custom library, picking CRISPRi vs CRISPRa TSS windows, deciding control-guide proportions, or diagnosing library skew and dropout in a freshly cloned pool.
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。
Identifies essential genes from CRISPR-Cas9 fitness screens using BAGEL2 (Kim & Hart 2021 Genome Med), a Bayesian classifier scoring per-gene Bayes Factors via log-likelihood ratios over per-sgRNA fold changes, calibrated against CEGv2 core-essentials (Hart 2017 G3, ~684 genes) and NEGv1 non-essentials (Hart 2014, ~927 genes). Covers the fc + bf + pr workflow, the linear-extrapolation improvement over BAGEL1 truncation, multi-target off-target correction, tumor-suppressor sensitivity (BAGEL2 detects enrichment), and BF calibration (BF >6 ≈ 90% posterior per Hart 2017; ~5% FDR by BAGEL convention). Use when classifying essential vs non-essential genes, calibrating BAGEL2 thresholds against PR curves, identifying tumor suppressors alongside essentials, comparing BAGEL2 hits to MAGeCK / drugZ, or generating publication-quality essentiality calls.
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 guides individualized prostate cancer screening for transgender females receiving estrogen therapy based on personal risk. Trigger phrase: transgender female receiving estrogens.
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。
Applies standard breast-screening guidelines for transgender females who have been assessed as having no known increased risk of breast cancer. Trigger phrases include transgender female and assessed as no increased breast cancer 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。
This skill screens for pregnancy intention in individuals with preexisting diabetes at every reproductive, diabetes, primary care, and urgent care/ER visit when clinically appropriate. Trigger phrases include reproductive planning, preconception care, or pregnancy intention discussion.
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。
Screen a hypercalcemic patient for medication- and supplement-induced causes — thiazides, lithium, vitamin D, vitamin A/retinoids, antiestrogens, theophylline, milk-alkali, SGLT2 inhibitors, immune checkpoint inhibitors, denosumab rebound, teriparatide/abaloparatide, foscarnet, ketogenic diet, aluminium. Trigger when a clinician asks "is this hypercalcemia drug-induced", "thiazide hypercalcemia", "lithium hypercalcemia", "denosumab rebound hypercalcemia", "vitamin D toxicity", "milk-alkali syndrome", "SGLT2 hypercalcemia", or any new hypercalcemia where medication review is needed.
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 recommends using biochemical tests to screen for hypercortisolism to detect recurrence in patients with ACTH-dependent Cushing's syndrome after surgical remission. It is triggered during postoperative follow-up when the HPA axis has recovered, annually, or sooner if clinical signs of hypercortisolism (e.g., weight gain, hypertension, glucose intolerance) or abnormal late-night salivary cortisol/UFC appear.
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。
Identifies patients with a positive aldosterone-to-renin ratio screening who may proceed directly to subtype testing without confirmatory testing based on specific clinical criteria. Triggers include spontaneous hypokalemia, baseline plasma aldosterone concentration >100 pg/mL (CLEIA), renin suppression, or a clinician questioning the need for a confirmatory test after a positive screen.
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。
Interprets the aldosterone-to-renin ratio using active renin concentration (ARC) to screen for primary aldosteronism. Triggered when a clinician has PAC and ARC results and asks 'How do I interpret this ARR using active renin concentration?'
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。
Screen a child with obesity for red flags suggesting monogenic, syndromic, or secondary endocrine causes — distinguishing atypical from typical exogenous obesity. Trigger when a clinician asks whether obesity could be genetic or hormonal, suspects Prader-Willi syndrome, Cushing disease, hypothyroidism, ROHHAD, Bardet-Biedl syndrome, leptin deficiency, or craniopharyngioma, or when a child has early-onset severe obesity, short stature with obesity, hyperphagia, hypotonia, dysmorphic features, or developmental delay with weight gain.
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。
Screen a child aged 13+ with obesity for eligibility for bariatric surgery (laparoscopic sleeve gastrectomy or Roux-en-Y gastric bypass) using the CMAJ 2025 guideline. Trigger when a clinician asks whether a child qualifies for weight loss surgery, bariatric surgery in adolescents, sleeve gastrectomy in a teenager, or when to refer for surgical management of pediatric obesity.
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。
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
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。
Normalize an OpenClaw lead bundle into a conservative lead-screening package with missing-field warnings, manual-review reasons, and customer-intel-ready payloads.
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。
Normalize and screen scattered foreign-trade leads into a conservative, structured lead pool that can flow into customer-intel research. Use when an operator has company names, websites, emails, or contact clues from search results and needs a standardized output with missing-field warnings, review flags, next-step suggestions, and customer-intel-ready JSON.
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.
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。