All authors
Claude Skills by PapeMati98
github.com/PapeMati9877 skills0 installs0 views
- Agent CliExecute lean TODO tasks through native CLI models with independent product review and targeted repairs; no procedural contract chain for new work.Votes: 0GitHub stars: 4
- Agent FleetExecute lean TODO tasks through native CLI models with independent product review and targeted repairs; no procedural contract chain for new work.Votes: 0GitHub stars: 4
- Agent LoopExecute lean TODO tasks through native CLI models with independent product review and targeted repairs; no procedural contract chain for new work.Votes: 0GitHub stars: 4
- Model RadarMaintain model capability and quota evidence for lean task selection.Votes: 0GitHub stars: 4
- Agent CliExecute lean TODO tasks through native CLI models with independent product review and targeted repairs; no procedural contract chain for new work.Votes: 0GitHub stars: 4
- Agent FleetExecute lean TODO tasks through native CLI models with independent product review and targeted repairs; no procedural contract chain for new work.Votes: 0GitHub stars: 4
- Agent LoopExecute lean TODO tasks through native CLI models with independent product review and targeted repairs; no procedural contract chain for new work.Votes: 0GitHub stars: 4
- Model RadarKeep model selection for local AI coding CLIs current and evidence-based. Use automatically with agent-fleet, before consequential model routing, when the user asks which model is newest or strongest, when a provider changes its catalog or subscription entitlement, or when either the seven-day model-market audit or weekly Arena benchmark snapshot is stale. Checks local freshness first, refreshes provider facts from primary sources, and maintains an exact-alias snapshot of official Arena leade...Votes: 0GitHub stars: 4
- Accept SystemApply proportionate product acceptance within the current TODO: executable checks, actual role-based user paths, changed behavior and regressions, without a separate acceptance contract.Votes: 0GitHub stars: 4
- Agent GraphExecute a short TODO as a real parallel dependency graph with native CLI makers, independent reviewers, targeted repairs and a small resumable state. No planning or acceptance contracts for new tasks.Votes: 0GitHub stars: 4
- Ai Infrastructure AuditAudytuje read-only infrastrukturę AI: agentów, skille, MCP, RAG, pamięć, endpointy modeli, izolację wykonania i łańcuch dostaw. Użyj przy przeglądzie architektury agentowej, integracji z zewnętrznymi narzędziami AI albo przed wdrożeniem komponentu, który może wykonywać polecenia lub przetwarzać dane nieufne.Votes: 0GitHub stars: 4
- Anti BureaucracyAudytuje koszt i wartosc wymogow procesu przy tworzeniu lub rozbudowie skilli oraz w cotygodniowym przegladzie stacku i ostatnich 7 dni sesji. Wykrywa duplikaty, kolizje, kaskady obowiazkow i powrot dawnych ceremonii. Uzyj przy zmianie reguly procesu, triggera, bramki lub zaleznosci; nie przy kazdym zwyklym zadaniu.Votes: 0GitHub stars: 4
- Audio Bed GenGenerate instrumental background music beds, short stingers, loops, and mix-ready audio assets through OpenRouter music models such as google/lyria-3-pro-preview. Use when Codex needs narration-safe background music for product demos, AI videos, presentations, explainers, intro/outro clips, or final audio mixing with ElevenLabs voice-over. Do not use to imitate copyrighted songs, artists, or generate deceptive audio.Votes: 0GitHub stars: 4
- Avatar GenGenerate audio-driven talking avatar and lip-sync videos from a still image or source video using dedicated avatar/lip-sync APIs such as Hedra. Use when Codex needs a speaking presenter, animated character, talking-head avatar, DOG TOR style narrator, or image-to-video lip-sync synced to pre-recorded audio. Prefer this over general video generation for talking avatars. Never use to impersonate real people deceptively or to create fake evidence.Votes: 0GitHub stars: 4
- Business CapabilitiesStructure cross-functional business decisions and briefs with one primary business lens and at most one supporting lens across strategy, finance, people, operations, revenue/customer experience, and marketing/content. Not for SOP/runbook/RACI authoring, reusable marketing context, channel execution, media generation, regulated advice, or external actions.Votes: 0GitHub stars: 4
- Clone ThreadPrzenosi kontekst projektu i modulu miedzy Claude, Codex, ZCode i Antigravity przez lokalny rejestr watkow oraz PROJECT_KNOWLEDGE.md. Uzyj przy /clone-thread, $clone-thread lub zapisie decyzji wlasciciela i rozwiazanych problemow.Votes: 0GitHub stars: 4
- Cloud Org OperatorDobiera właściwą organizację i konto dla Azure, Microsoft Graph, Microsoft 365/SharePoint, GCP oraz Google Workspace, a następnie tworzy fail-closed plan preflight dla CLI i MCP bez logowania i mutacji. Użyj przed każdą pracą chmurową, zwłaszcza gdy wiele firm ma osobne tenanty, witryny, konektory, subskrypcje, projekty lub konfiguracje.Votes: 0GitHub stars: 4
- Cloudflare OperatorOperate Cloudflare DNS, proxy and TLS, Tunnel and Access, Workers and Pages, WAF, rate limits, cache and redirects. Use for scoped Cloudflare administration, deployment troubleshooting, access checks and usage diagnosis; distinguish account/zone/environment and preserve rollback before changes.Votes: 0GitHub stars: 4
- Codex Security CliDEPRECATED. Ten skill zostal zastapiony przez `simulate-attack`. Wspolne skille powinny byc migrowane do nowego skilla; skan chmurowy oficjalnym Codex Security CLI nie jest czescia tej warstwy. Nie instaluj juz tego skilla. Niezbedny runtime pozostaje zarchiwizowany w `references/runtime-manifest.json` i w `scripts/` tylko na potrzeby audytu historycznego.Votes: 0GitHub stars: 4
- Create DotsTworzy lub konfiguruje DOTS tylko na wyrazne polecenie stworzenia DOTS albo $create-dots. Nie uruchamia sie podczas zwyklych sesji ani statusow.Votes: 0GitHub stars: 4
- Creating Mermaid DiagramsGenerate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using the LOCAL mmdc CLI. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, class diagram, ER diagram, state machine, architecture, visualize, git graph, schemat, diagram, architektura. PROACTIVELY USE when explaining ANY system with 3+ components, API flows, authentication sequences, class hierarchies, database schemas, or state machines. Supports 11+ diagram types with fully automatic layout.Votes: 0GitHub stars: 4
- Data GovernanceInclude applicable ownership, access, quality, compatibility and recovery checks for persistent data, schemas, ETL or migrations in the existing TODO; preserve real consent and privacy decisions without a separate governance contract.Votes: 0GitHub stars: 4
- Delivery AuditAsynchronously audits completed top-level delivery tasks using one fixed native CLI Graph. Use for the automatic post-delivery metadata handoff and when maintaining this audit skill; never audit an audit, subtask, status check, or metadata-only episode.Votes: 0GitHub stars: 4
- Design Code ArchitectureProjektuje lub recenzuje architekturę kodu przez model domeny, granice modułów, publiczne kontrakty i małe pionowe kroki wdrożenia. Użyj przed większą funkcją, przebudową odpowiedzialności, podziałem monolitu albo gdy zmiana przecina wiele modułów.Votes: 0GitHub stars: 4
- EmailCzytaj wskazane skonfigurowane skrzynki przez lokalny konektor POP3/IMAP/Gmail/Microsoft Graph, przygotowuj lokalne szkice i wysylaj wylacznie za jawna zgoda wlasciciela. Lokalny ekstraktor Tone of Voice.Votes: 0GitHub stars: 4
- FundraisingBuduje albo naprawia pitch decki, memoranda inwestycyjne i one-pagery do pozyskania finansowania na podstawie zweryfikowanych dowodow, spojnych liczb i jawnych decyzji wlasciciela. Uzyj przy tworzeniu materialow inwestorskich; nie uzywaj do wysylki, kontaktu z inwestorami ani porad prawnych, podatkowych lub inwestycyjnych.Votes: 0GitHub stars: 4
- Google Ads StrategyRun Google Search Ads end-to-end: keyword mining, account structure, ad copy, negative keyword architecture, and performance analysis. Covers the full loop from setup to ongoing optimization for B2B SaaS and app makers. Use when the user wants to plan, launch, or optimize Google Search campaigns, or understand how the platform works before spending. Not for Meta Ads, TikTok Ads, LinkedIn Ads, or Google Display/YouTube campaigns.Votes: 0GitHub stars: 4
- Growth ExperimentsDesign and evaluate bounded growth experiments, tracking plans, CRO and attribution with guardrails. Use for hypotheses and analysis; do not change budgets, campaigns or production traffic automatically.Votes: 0GitHub stars: 4
- Hermes DelegationDelegate bounded synchronous or asynchronous work to Robert, the Hermes Agent running on AI Lab Server, through the native Hermes CLI over SSH. Use for approved mailbox/calendar access, public-web research, long-running server work, safe call-summary or ticket-triage drafts, server-local coding, or an explicitly approved final action. Enforces contract hashing, mode/target/skill allowlists, result evidence, and exact Mateusz approval for private data, terminal inspection, code writes, messagi...Votes: 0GitHub stars: 4
- Home AssistantControl Mateusz Home Assistant from explicit owner requests through Hermes and Agent Office. Use for lights, home status and temperature reads; prefer existing native HA tools, with a portable client for bounded light actions and verified readback. Availability inference is advisory.Votes: 0GitHub stars: 4
- Html VideoRender frame-accurate deterministic MP4 videos from HTML/CSS/SVG compositions using headless Chrome and FFmpeg, with strict network isolation, local asset pinning, seek-order determinism, contact-sheet evidence, and ffprobe validation.Votes: 0GitHub stars: 4
- Idea MakerProponuje nowe skille lub rozszerzenia na podstawie powtarzalnych dowodow, podczas cyklu co 14 dni albo jawnego przegladu pomyslow. Nie sluzy do implementacji, instalacji, synchronizacji ani wdrazania skilli i nie uruchamia sie przy kazdym zadaniu.Votes: 0GitHub stars: 4
- M365 Workspace OperatorInspect or manage Microsoft 365 workspaces: Teams, SharePoint sites/lists, Planner, Microsoft Graph and Entra applications/consent. Use for M365 integration diagnostics, resource discovery, permission planning and explicitly authorized operations, including a configured managed MCP connector. Reuse cloud-org-operator for tenant/account selection. Do not activate for unrelated web coding or ordinary email reading.Votes: 0GitHub stars: 4
- Market Strategy ResearchProwadzi research-only badania strategii rynkowych i tradingowych: jakość danych, jednoznaczne reguły, koszty wykonania, walk-forward, OOS, final holdout, ogony i reżimy. Użyj przy backtestach, sygnałach, portfelach i modelach rynkowych; nigdy do składania zleceń ani autonomicznego handlu.Votes: 0GitHub stars: 4
- Marketing ContextBuild or audit a product marketing context from evidence: ICP, JTBD, positioning, proof and customer language. Use for strategy and messaging decisions; do not publish or launch campaigns.Votes: 0GitHub stars: 4
- Meta Ads StrategyRun Facebook and Instagram ads end-to-end: Meta ads strategy, ad creative, copy, campaign structure, targeting, budgeting, ROAS tracking, and Pixel setup. Includes a built-in ad brief workflow. Use when the user wants to plan, create, launch, or optimize Meta ads, or when they need to understand how the platform works before spending money. Not for Google Ads, TikTok Ads, LinkedIn Ads, or general marketing strategy outside Meta.Votes: 0GitHub stars: 4
- Ml Architecture SelectionUzyj przed budowa modelu ML/DL. Dobiera najmniejsza sensowna strategie przez baseline ladder, 2-4 konkurujace hipotezy, eksperymenty falsyfikujace, split OOS, koszt i stop-rule.Votes: 0GitHub stars: 4
- Ml ReconRead-only rekonesans modeli i datasetow lokalnie oraz w Hugging Face/web, z przypieciem rewizji, licencji, proweniencji, formatu, VRAM i ryzyk; dzialania hf-act wymagaja osobnego kontraktu.Votes: 0GitHub stars: 4
- Model AuditUtrzymuje aktualna charakterystyke modeli AI dostepnych w lokalnych CLI. Uzyj przy jawnym audycie rynku albo potrzebnym odswiezeniu faktow o nieznanym lub zmienionym modelu/CLI. Zwykly dobor wykonawcy nie uruchamia pelnego audytu rynku tylko z powodu wieku raportu.Votes: 0GitHub stars: 4
- Model CouncilConsult independent model lineages through existing CLI subscriptions and Agent Office for valuable uncertainty, ML hypotheses, architecture disputes or brainstorming. Prefer two relevant subscription/local consultants; paid OpenRouter consultants need explicit incremental benefit and a bounded budget. JEV can advise whether consultation is useful. Historical API panels keep their pinned protocol.Votes: 0GitHub stars: 4
- New TaskOrient a new application task and choose a minimal TODO, a small maker/reviewer pair, or a real dependency graph; preserve product checks and existing approvals without contract ceremonies.Votes: 0GitHub stars: 4
- New TrainingUzyj na poczatku KAZDEGO treningu lub fine-tuningu. Zawiera campaign contract, lokalnie-pierwszy wybor compute, baseline, resume proof, OOS, telemetryke i niezalezna bramke promocji przed kolejnym runem lub wdrozeniem.Votes: 0GitHub stars: 4
- Ngrok OperatorOperate ngrok AI Gateway, HTTP/TCP/TLS tunnels, endpoints and webhooks. Use for sharing localhost, remote UAT connectivity, provider routing configuration, BYOK, access policies, request failures, usage and cleanup. Keeps API billing separate from Agent Fleet subscriptions and requires scoped approval for public exposure.Votes: 0GitHub stars: 4
- Office LoopContinue a goal-bound team task through Agent Office: consult a Director for concrete Fleet TODO batches, deliver and review them, then continue on real progress. Use for sustained multi-session delivery or explicit Office Loop requests; ordinary answers and single fixes do not need this loop.Votes: 0GitHub stars: 4
- Operate ChromeDefault agent browser for logged-in web services in Codex, Claude and Antigravity: use the assigned Fleet Chrome Relay profile (chrome_* tools) or DOTS tools; fail closed when unavailable, never the owner's private Chrome.Votes: 0GitHub stars: 4
- Operations PlaybookTurn a bounded operational need into a usable SOP, runbook, RACI or process map with controls, evidence, recovery and handoffs. Draft and review only; do not execute production actions automatically.Votes: 0GitHub stars: 4
- Pl Tax ComplianceSpecjalista od polskich wymogów FORMALNYCH w podatkach i księgowości (faktury, korekty, KSeF/FA(3), JPK, ewidencje). Przed werdyktem sprawdza aktualność przepisów w źródłach pierwotnych; aktualizuje kanoniczną bazę wiedzy, gdy zapis jest dozwolony i wykonalny. Użyj, gdy trzeba ustalić, jakie elementy MUSZĄ, a jakie MOGĄ znaleźć się na dokumencie podatkowo-księgowym wg aktualnego prawa PL.Votes: 0GitHub stars: 4
- Plan DeliveryPlan every new task as a short TODO with requirements, dependencies, maker/reviewer pairs and product checks. A strong current parent plans once; no planning contract or review-of-plan ceremony.Votes: 0GitHub stars: 4
- Rag EngineeringDesign, audit and evaluate provider-neutral retrieval-augmented generation pipelines from ingest through answer quality, latency and drift. Use for planning and local evaluation; do not upload, deploy or publish automatically.Votes: 0GitHub stars: 4
- Remote Computer UseRun browser E2E or bounded Windows desktop UAT on an explicitly configured isolated Windows VM through SSH, with explicit capability contracts, an interactive-session broker, allowlisted apps, evidence, timeout recovery, and transactional deployment. Use when tests or computer interaction should run off the local PC.Votes: 0GitHub stars: 4