Claude Skills by aibot88

Design presentation visuals and slide layouts. Create visual concepts, suggest graphics, and provide design specifications for impactful PowerPoint slides.

Build PowerPoint decks headless with python-pptx. Pairs with excel-author for model-backed decks where every number traces to a workbook cell. Use for pitch decks, IC memos, earnings notes.

Read all unresolved GitHub PR comments from trusted authors and address or resolve them appropriately.

Walk a maintainer through deep code review of open pull requests on the configured `<upstream>` repo (default: read from `<project-config>/project.md → upstream_repo`). The default working list — referred to throughout the docs as **"my reviews"** — is the union of five signals on the authenticated maintainer: PRs where review is requested from them, PRs that touch files they recently modified, PRs whose changed files they own per `CODEOWNERS`, PRs that `@`-mention them, and PRs they already ...

Use this skill to review a PR or diff for security regressions. Do not use it for full-repository audits or legal contract review.

Chiropractic practice marketing, patient communication, content strategy, and healthcare advertising compliance

Guide for authoring comprehensive PRDs with parallel planning support. Use for drafting technical specifications, defining requirements, and synthesizing planner outputs. Use proactively when creating PRDs, architecture designs, or implementation plans. Examples: - user: "Draft a PRD for user auth" → create PRD with purpose, requirements, and scenarios - user: "Analyze these PRD requirements" → verify SHALL/MUST usage and scenario structure - user: "Synthesize planner outputs" → merge the str...

Use before any git commit or PR. Runs format/lint/typecheck/tests, checks for secrets/large files/debug statements, validates commit message. Triggers готов к commit, проверь перед commit, можно ли пушить, ready to merge.

9-point pre-deploy gate — compilation, linting, tests, migrations, API spec, debug artifacts, env config, bundle size, secrets

Verifica que no haya credenciales, secrets o archivos sensibles antes de pushear a GitHub. Busca API keys hardcodeadas, .env con valores reales, y valida .gitignore.

Safety check before executing destructive or irreversible commands. Catches dangerous shell commands, risky git operations, secret exposure, and high-blast-radius actions before they run. Activates automatically when Claude is about to execute shell commands that match known risk patterns. Trigger phrases: "check before running", "is this command safe", "safety check", "pre-execution review".

Before opening a pull request, run the project's check suite, scan the diff for things reviewers can't easily catch (debug code, secrets, missing tests), and draft a PR body.

Skill do używania biblioteki preboot-core. Użyj tego skilla zawsze gdy użytkownik chce cache z TTL, rate limiting, synchronizację dostępu po kluczu, transakcje programowe, hashowanie parametrów, walidację beanów, konfigurację Jacksona, lub pracuje z infrastrukturą współbieżności. Obejmuje: TTLMap, AccessSynchronizer, RateLimiter, TransactionWrapper, HashUtils, BeanValidator, JsonMapperFactory, JacksonCustomizerAutoConfiguration. Triggeruje się na: TTL cache, rate limiter, token bucket, key-ba...

Skill do używania biblioteki preboot-query. Użyj tego skilla zawsze gdy użytkownik chce implementować dynamiczne filtrowanie, sortowanie, paginację, repozytorium z wyszukiwaniem, REST API z filtrowaniem, projekcje, eksport danych, lub pracuje z Spring Data JDBC i potrzebuje dynamicznych zapytań. Obejmuje: FilterableRepository, FilterableUuidRepository, FilterCriteria, SearchParams, SearchRequest, FilterableController, CrudFilterableController, UuidFilterableController, CrudUuidFilterableContr...

Use when the user is trying to predict how a dominance-seeking leader will sort people in their orbit — who gets kept, who gets rehabilitated after a rift, who gets quietly dropped, who gets actively attacked. The sort logic is not moral or loyalty-based; it is constituency-based, and this skill makes that logic explicit so the user can forecast decisions and, if they are themselves in the orbit, move their own standing. Triggers on phrases like "why did the leader drop X and keep Y despite Y...

Audit manufacturing predictive maintenance systems for OPC-UA/MQTT sensor data pipelines, time-series storage retention, ML model lifecycle (training-serving skew, drift detection, retraining triggers), MTBF/MTTF/MTTR reliability calculations, Weibull survival analysis, RUL prediction accuracy, alert threshold tuning and false positive management, CMMS/ERP integration, spare parts demand forecasting, and OT/IT security segmentation.

Describe an agent in `agent_spec.yaml`, run deterministic prompt-injection analysis, generate mitigations, and validate defenses before rollout.

Reference document describing six pre-flight checks (clean git state, not detached HEAD, gh auth, issue exists and OPEN, remote reachable, duplicate-branch warning) as pure bash exit codes with no LLM calls. Reference only (policy document; consumed by `/flow:start` Phase 0).

Prüft die Einhaltung der Preisangabenverordnung 2022 (PAngV) bei Gesamtpreisen, Grundpreisen, Streichpreisen und Versandkosten, insbesondere die 30-Tage-Niedrigstpreisregel bei Preisreduzierungen. Lädt bei Fragen zu Preisauszeichnung, Rabattaktionen, Sale-Kennzeichnung und Grundpreisangabe.

Tracks the latest preprints and emerging research topics related to your topic across bioRxiv, medRxiv, and arXiv. Use when a user wants to discover what is being published right now before it reaches journals, monitor competitor directions, spot new methodology trends, or get an early-warning scan of a research area. Triggers on phrases like "what's new in X", "latest preprints on Y", "emerging topics in Z", "monitor bioRxiv for", or "what are people working on in this field".

Complete PrestaShop module development workflow using modern architecture and best practices. Use when: creating new PrestaShop modules, updating legacy modules to modern code, implementing hooks and actions, setting up module configuration pages, adding front office features, handling database operations, implementing security measures, managing translations, or modernizing existing PrestaShop modules from legacy patterns to current standards.

Use actionlint when an agent needs to inspect GitHub Actions workflow files before a push or pull request lands. The skill checks syntax, expressions, action inputs, runner labels, cron patterns, and a few security footguns so the agent can stop bad workflow changes before CI burns time.

Stálý průvodce prezentační platformou v `c:\github\presentations`. Pomáhá autorům (mluvčím + organizátorům) navigovat celý ekosystém — od založení nového eventu, přes import externích slidů (Google Slides PDF, Keynote, PowerPoint, PNG screenshoty), tvorbu/úpravu mega-deck prezentací, až po správu live mode, Q&A scope, speaker auth a brand konzistence. Skill je BRAND-AGNOSTIC — zná víc design themes (zatím jen UICZ Uměláinteligence.cz, další půjdou přidat jako `themes/<jméno>/`). Při aktivaci ...

Use when the user wants to pressure-test a product, internal-tool, or OSS concept against Amazon's Working Backwards PRFAQ gauntlet before committing to a spec. Triggers on: \"work backwards\", \"write a PRFAQ\", \"press release first\", \"is this idea worth building\", \"pressure-test this concept\", \"filter this before brainstorm\", \"is this a real product\". Also catches solution-first pitches (\"I want to build X that does Y\") and technology-first pitches (\"use AI to...\") that need c...

Generate strategy documents from completed Primr research. Use when the user wants AI, CX, security, or data strategy deliverables from an existing report.

Three orthogonal analytical operations (WHERE/WHEN/WHY) + cross-operation synthesis. Each operation attacks the problem from a fundamentally different angle. The disagreements between the three ARE the valuable output. Works on any domain — code, business, strategy, design, text.

Discover all possible analysis domains for an artifact. Finds obvious and non-obvious angles — architecture, security, but also marketing positioning, user psychology, regulatory implications, teaching value. Use before prism-scan or prism-full to explore what's worth investigating.

Full Prism: multi-pass structural analysis with mandatory adversarial self-correction. Designs custom analytical passes, executes them with chaining, then attacks its own findings before synthesizing. Use for maximum depth on important code or artifacts.

Data minimization, purpose limitation, DPIA, vendor mapping.

Use to assess Privacy by Design compliance and GDPR/data protection alignment for a feature or system.

Privacy engineering patterns — PII classification and inventory, GDPR consent flows, data minimization, right-to-erasure implementation, pseudonymization/encryption, privacy-by-design architecture, and DPIA checklist.

EU 사용자 대상 서비스용 Privacy Notice·Terms of Service·Consent Modal·Cookie Banner 자동 생성. GDPR (Regulation 2016/679) + ePrivacy Directive + Consumer Rights Directive 2011/83 + Digital Services Act + Digital Content Directive + Unfair Terms Directive 반영. 영문 인터뷰로 진행.

Prevent email addresses and personal data from entering the codebase. Use when user asks to "prevent emails", "remove personal data", "privacy check", "no email", or when writing/ editing any code, config, or documentation files.

Checkt of je omgaat met persoonsgegevens volgens de AVG/GDPR-regels.

Generates comprehensive privacy policies by scanning websites for data collection signals including cookies, forms, payment processors, and third-party scripts. Use when launching a website or app that collects user data and needs GDPR/CCPA compliance. Trigger with "/privacy-generator" or "create a privacy policy for my website".

한국+EU 병기 처리방침·이용약관 자동 생성. 한국 본사가 EU 사용자까지 대상으로 서비스할 때 사용. 한국어(PIPA)·영문(GDPR) 두 세트 문서를 동시 생성하고, Footer에 언어·관할 전환 링크 자동 삽입.

한국 서비스용 처리방침·이용약관·회원가입 동의 모달·쿠키 배너 자동 생성. 개인정보보호법 §30, 2025.4.21 작성지침, 2026.3 개정법, 공정위 전자상거래 표준약관 10023호 반영. Next.js 13~16 프로젝트 대상.

PrivacyInfo.xcprivacy generator en validator. Run bij elke dependency change en pre-submit.

Privacy manifest (PrivacyInfo.xcprivacy) implementation including required reason APIs, tracking domains, third-party SDK declarations, and App Tracking Transparency. Use when preparing apps for App Store privacy requirements.

Reuse one system init payload shape across trusted and remote transports, but redact tool, MCP, and plugin metadata when the bridge path would leak local integrations or filesystem paths.

Routing privacy per il segreto professionale italiano (segreto professionale, Art. 622 CP, Art. 9 D.Lgs. 96/2001) con rilevamento pattern in italiano e inglese per proteggere le comunicazioni legali confidenziali.

처리방침·이용약관 자동 생성 진입점. 호출 즉시 4개 하위 스킬(privacy-kr·privacy-eu·privacy-us·privacy-global)을 번호 메뉴로 제시하고, 번호 입력 즉시 해당 스킬 인터뷰로 직행한다.

미국 CCPA/CPRA + 주요 주법(VCDPA·CPA·CTDPA·UCPA·ICDPA·KCDPA·RIDPA) 기반 Privacy Policy 자동 생성. 2026.1.1 CPPA 갱신 규정, Sensitive Personal Information, Do Not Sell/Share, ADMT 공개, GPC 브라우저 신호 대응. 캘리포니아 거주자 서비스·100K records 초과 서비스 대상.

Integrates Privy authentication, embedded wallets, and agent payment protocols into web and agentic apps. Covers React SDK (PrivyProvider, hooks, wagmi), Node.js SDK, smart wallets (ERC-4337), x402 and MPP machine payments, Tempo chain, and agentic wallets with policies. Use when setting up Privy auth, creating embedded or agentic wallets, adding x402 or MPP payments, integrating with Tempo, configuring wallet policies, or connecting Privy to MCP/Agent Auth flows.

Use when analyzing randomized algorithms, probabilistic analysis, indicator random variables, hiring and secretary problems, random permutations, balls-and-bins, birthday paradox, streaks, or average-case versus expected-time reasoning.

Test agent systems for graph-discovered tool-chain vulnerabilities, silent side effects, and multi-phase trust exploits before deployment.

Den Laufzeitzustand eines benannten Feature-Flags in einem CLI-Binary prüfen. Behandelt das vierzweigige Evidenzprotokoll (Binary-Strings, Live-Aufruf, On-Disk-Zustand, Plattform-Cache), die vier Zustands- klassen (LIVE / DARK / INDETERMINATE / UNKNOWN), die Unterscheidung Gate vs. Event, den Umgang mit Konjunktions-Gates sowie Skill- Substitutionsszenarien, in denen ein Flag DARK erscheint, die Fähigkeit aber auf anderem Wege bereitgestellt wird. Einzusetzen, wenn geprüft werden soll, ob ein...

Assess a Kubernetes cluster from the attacker viewpoint when an agent needs exposure-focused findings instead of a general cluster scanner listing.

Run a focused exposure probe against a Kubernetes environment before deeper pentest work or remediation planning starts.

Run automated red-team and failure scans against an LLM or RAG app before users find the breakage.