「its」の検索結果

Run autonomous AI-driven penetration tests on web applications using tools like Shannon, PentAGI, and similar frameworks. Use when tasks involve setting up automated penetration testing pipelines, combining AI agents with security tools (nmap, subfinder, nuclei, sqlmap), building autonomous exploit chains, generating pentest reports with proof-of-concept exploits, or integrating AI pentesting into CI/CD pipelines. Covers the full pentest lifecycle from reconnaissance to reporting using AI orchestration.

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 AI-generated text using rule-based analysis, LLM-as-judge scoring, and optional external APIs. Use when: auditing content for AI authorship, academic integrity checks, editorial review, SEO content 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。

Plans a controlled experiment (A/B test) so its result can be trusted: writes the hypothesis, picks one primary metric and the guardrails, computes sample size and run time, specifies how visitors are assigned and when exposure is logged, and reads out the result with a confidence interval. Use when someone says "set up an A/B test", "split test this page", "how many visitors do I need", "how long should the experiment run", "is this result significant", "can I stop the test early", or wants to test a headline, price, layout or onboarding change against the current version.

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 new commits and generate related test cases.

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。

Full SEO toolkit for Claude Code, powered by the DataForSEO API. Replaces the data layer of an SEO agency: keyword research, competitor analysis, rank tracking, backlink audits, technical site crawls, content gap analysis, and client-ready PDF reports — all with real Google search data, not scraping. Use when the user says "seo", "keyword research", "rank check", "backlinks", "competitor analysis", "site audit", "content gap", "compare domains", or passes a domain / URL / keyword for SEO analysis.

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。

Identify true SEO competitors and quantify the gap, powered by the DataForSEO Labs API. Returns the top 10 competing domains by SERP overlap, with shared and unique keywords, traffic estimates, and a Competitive Score (0-100) showing how dominant the target is in its category.

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 computing orbits, planning maneuvers, propagating trajectories, or analyzing orbital perturbations for spacecraft or celestial bodies. Use when "orbit, trajectory, maneuver, delta-v, Hohmann, Keplerian, perturbation, J2, TLE, orbital elements, semi-major axis, eccentricity, inclination, RAAN, spacecraft propagation, Lambert solver, interplanetary, " 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。

Git is deceptively simple to learn and incredibly hard to master. The difference between a team that ships and a team that fights merge conflicts all day comes down to workflow discipline. Your git history is documentation - make it tell a story future you can understand. This skill covers branching strategies (trunk-based, gitflow, GitHub flow), commit hygiene, merge vs rebase, conflict resolution, and the commands you actually need. Key insight: most git disasters come from not understanding what you're about to do. 2025 lesson: Trunk-based development with short-lived branches has won. Long-lived feature branches are a code smell. If a branch lives more than a few days, something is wrong with your architecture or process. Use when "git workflow, branching strategy, git merge, git rebase, merge conflict, git commit, trunk-based, gitflow, git history, git revert, git reset, git, version-control, workflow, branching, commits, merge, rebase, collaboration" 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 landing page expertise combining conversion rate optimization science, persuasive design psychology, and the craft of pages that turn visitors into customers. Landing pages are where marketing meets reality—the moment of truth where visitors decide. Great landing pages aren't just pretty—they're conversion machines. The best landing page designers understand that every element must earn its place, that friction is the enemy, and that the goal isn't to impress—it's to convert. Speed, clarity, and persuasion in perfect balance. Use when "landing page, conversion page, lead capture, signup page, pricing page, hero section, above the fold, CTA design, conversion rate, page optimization, lead gen page, squeeze page, sales page, landing-pages, conversion, CRO, design, optimization, lead-generation, signups, forms" 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。

Kubernetes is the operating system for the cloud. It schedules containers, handles networking, manages storage, and keeps your apps running. But K8s has a steep learning curve - abstractions on abstractions on abstractions. This skill covers the core concepts (Pods, Deployments, Services), production patterns (health checks, resource limits, HPA), and the gotchas that catch everyone (namespace confusion, service discovery, secret management). 2025 reality: You probably don't need to run your own cluster. Use managed K8s (EKS, GKE, AKS) unless you have a very good reason not to. Focus on writing good manifests, not managing etcd. Use when "kubernetes, k8s, kubectl, deployment manifest, helm chart, kustomize, pod, service yaml, ingress, horizontal pod autoscaler, hpa, kubernetes, k8s, containers, orchestration, devops, cloud-native, helm, kustomize" 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。

The craft of designing icons that communicate instantly across cultures, contexts, and scales. Icon design bridges semiotics, cognitive psychology, and visual craft to create symbols that users understand without thinking. Great icons are invisible in the best way - they convey meaning so naturally that users never pause to decode them. This skill covers icon grid systems, optical alignment, stroke consistency, metaphor selection, scalability across sizes, SVG optimization, and icon set coherence. The best icon designers understand that icons are a visual language - each icon must speak the same dialect while carrying its own distinct meaning. Use when "icon, iconography, symbol, glyph, icon set, icon library, pictogram, svg icon, icon grid, icon pack, feather icons, lucide, phosphor, heroicons, icon system, icon style, icons, iconography, svg, symbols, glyphs, pictograms, ui-icons, icon-set, visual-design, design-system" 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。

Raising money is a means to an end, not the end itself. Great companies can be built with or without venture capital. But if you're raising, you need to understand the game: when to raise, how much, from whom, and at what terms. This skill covers fundraising timing, process, pitch construction, term sheet negotiation, and investor relationship management. It's not about raising as much as possible - it's about raising strategically. Use when "fundraising, raising money, pitch deck, investors, term sheet, valuation, dilution, series A, seed round, pre-seed, runway, cap table, VC, venture capital, fundraising, investors, venture-capital, pitch-deck, term-sheet, valuation, dilution, seed, series-a, cap-table" 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 game UI design expertise combining the clarity of Nintendo's UI philosophy, the immersive diegetic interfaces of Dead Space and Metroid Prime, and the competitive readability principles from esports titles. Game UI is the invisible bridge between player intent and game response. Great game UI serves the player without breaking immersion. It communicates critical information at a glance during intense action, guides new players without patronizing veterans, and adapts gracefully from 4K monitors to handheld screens and from keyboard to touch to controller. The best game UI designers understand that every pixel of screen space is sacred - borrowed from the game world itself. Use when "game ui, game interface, hud design, heads up display, game menu, inventory ui, health bar, stamina bar, game hud, minimap, crosshair, reticle, button prompt, controller ui, gamepad navigation, diegetic interface, in-world ui, quest tracker, damage numbers, cooldown indicator, radial menu, game tooltip, game-ui, hud, game-interface, game-menu, controller-ui, diegetic, game-design, accessibility, console, mobile-games" 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。

Docker makes "works on my machine" a deployment strategy. Package your app with its dependencies, run it anywhere. But Docker's simplicity hides real complexity. A naive Dockerfile can be 10x larger and slower than it needs to be. This skill covers Dockerfile optimization, multi-stage builds, Docker Compose for development, security hardening, and production patterns. Key insight: your Dockerfile is code. Review it, optimize it, version it. 2025 lesson: Containers aren't VMs. The patterns that work for VMs (install everything, big base images) are anti-patterns for containers. Think small, think immutable, think layers. Use when "docker, dockerfile, container, docker compose, docker build, containerize, docker image, multi-stage build, docker network, docker volume, docker, containers, devops, deployment, infrastructure, security, optimization" 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。

When things go wrong - and they will - how you communicate determines whether you lose customers for a day or lose trust forever. Crisis communications isn't about spin or damage control. It's about being human when your company is at its most vulnerable. This skill covers incident response communications, public apologies, data breach notifications, service outages, PR crises, and the aftermath. The goal isn't to look good - it's to be good, and communicate that clearly. Use when "crisis, incident, outage, down, breach, apology, we messed up, customers are angry, PR disaster, viral complaint, status page, postmortem, trust recovery, bad press, crisis, incident, communications, apology, trust, status-page, outage, breach, postmortem, recovery" 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 designing and implementing visceral, satisfying combat systems. Masters hitbox/hurtbox design, frame data, combo systems, enemy archetypes, damage feedback, and the invisible craft that makes players feel powerful. Draws from fighting games, character action games (DMC, Bayonetta), and Souls-like design to create combat that is readable, responsive, and endlessly replayable. Use when "combat system, combat design, hitbox, hurtbox, frame data, hitstop, screen shake, input buffer, coyote time, i-frames, invincibility frames, combo system, attack cancel, recovery frames, punishment window, souls-like combat, action game combat, fighting game, damage feedback, enemy design, boss design, attack telegraph, parry system, stamina system, poise system, weapon feel, game feel combat, melee combat, combat juice, combat, action-game, fighting-game, hitbox, frame-data, game-feel, souls-like, character-action, melee, enemy-design, boss-design, combo, parry, i-frames" 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。

Angular is opinionated and comprehensive - it gives you everything: routing, forms, HTTP, dependency injection, testing. The learning curve is steep, but once you're in, you move fast. The structure it enforces is why enterprises love it. This skill covers Angular 17+, standalone components, signals, the new control flow syntax, and modern Angular patterns. Key insight: Angular's power is in its DI system and RxJS integration. Master those, and everything else follows. 2025 lesson: Standalone components are the future. NgModules aren't going away, but new projects should start standalone. Signals are Angular's answer to fine-grained reactivity - learn them. Use when "angular, angular component, angular service, angular routing, angular forms, rxjs, ngrx, angular signals, standalone component, angular ssr, angular, typescript, frontend, spa, enterprise, rxjs, signals, standalone" 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。

Accessibility isn't a feature - it's a fundamental quality of good software. 1 in 4 adults has a disability. Many more have temporary impairments or situational limitations. Your users include people who can't see, can't hear, can't use a mouse, or can't process information the way you do. This skill covers WCAG guidelines, ARIA patterns, keyboard navigation, screen reader compatibility, and automated testing. Key insight: accessible code is better code. The constraints of accessibility lead to simpler, more semantic, more maintainable implementations. 2025 lesson: Accessibility lawsuits are at an all-time high. "We'll add it later" is both ethically wrong and legally risky. Start accessible, stay accessible. Use when "accessibility, a11y, wcag, aria, screen reader, keyboard navigation, focus trap, alt text, color contrast, skip link, accessible, accessibility, a11y, wcag, aria, screen-reader, keyboard, inclusive, semantic-html" 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 accessibility design expertise combining the inclusive design principles of Microsoft's Inclusive Design team, the technical rigor of the W3C WCAG working group, and the lived experience perspective of disability advocates. Accessibility is not a feature - it's a fundamental quality attribute that makes products usable by everyone. Great accessibility design is invisible to those who don't need it and essential to those who do. It benefits everyone: captions help in noisy environments, keyboard navigation helps power users, high contrast helps in bright sunlight. When you design for the extremes, you improve the experience for all. Accessibility is not a checklist - it's a mindset that asks "who are we excluding?" at every design decision. Use when "accessibility, a11y, wcag, screen reader, keyboard navigation, color contrast, alt text, aria, focus management, skip link, assistive technology, inclusive design, ada compliance, section 508, accessible, voiceover, nvda, jaws, tab order, focus trap, accessibility, a11y, wcag, inclusive-design, screen-reader, keyboard-navigation, color-contrast, aria, focus-management, assistive-technology" 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。

Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers, comparisons, scope, method, baselines, citations, captions, table cells) into claims.json. An OPTIONAL additive cross-model pass ADDS span-anchored semantic claims — method, theorem statements with their assumptions, definitions, proof/derivation steps and equations, scope, baselines, conclusions, the motivation span, and reproducibility-artifact references (the proof, derivation, and structure anchors the family B/D/G auditors need) — it never invents a number, emits a finding, or computes a verdict. Run FIRST, before any audit skill. Triggers: "build the ledger", "extract claims", "prep for integrity audit", "evidence ledger", "建证据账本".

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。

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing-style impressions, never moving the verdict). Triggers: "anti-autoresearch", "integrity audit this paper", "forensic review", "audit a submission", "审一篇投稿的诚信".

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。