grekai-skills-4all

Record narrated, themeable product tutorials by driving any web app with Playwright and voicing every step with a neural TTS voice (Jenny by default). Use when the user types "/tutorial-create", "/tutorial-update", or "/tutorial-status", or asks to "record a tutorial", "make a walkthrough video", "narrated demo", "real video with voiceover", "screen recording with narration", "update the tutorial", "refresh the tutorials index", or "tutorial status". Outputs a REAL motion video of the app moving with narration (MP4), or a screenshot slideshow, or a no-ffmpeg HTML player — all with WebVTT captions. Runs a human-gated flow: draft & APPROVE a scenario, record it with Playwright, render, show the output for APPROVAL and fix issues in a loop, then regenerate a light/dark, logo-branded index.html that switches between every tutorial. Project-agnostic — reads ./tutorial.config.json for brand, paths and voice.

Air-gapped SOC investigation cowork for Microsoft Defender + VirusTotal + Sentinel in locked-down tenants where direct API / MCP / Entra access is forbidden. Use when the user wants to triage IOCs (URLs, domains, file hashes), hunt them in Defender Advanced Hunting split by machine type, unify and enrich the results via VirusTotal, pivot into Sentinel to find affected machines and users, and close incidents — without granting any API access. Claude generates the KQL and the local enrichment, the human runs the queries and exports CSVs in their own authenticated browser, and Claude prepares (never auto-executes) the incident-close step. Triggers on: "run the SOC investigation", "hunt these IOCs", "Defender/Sentinel triage", "check these domains/hashes", "close the risks in Sentinel".

Generate single-file, self-contained HTML exam / study / quiz apps for kids and general study — gamified (XP, levels, badges), with localStorage progress, immediate feedback, and optional Hebrew TTS. USE THIS whenever the user wants to "create an exam app", "build a study app", "make a quiz", "build a practice app", asks for a "מבחן", "תרגול", "בוחן", "אפליקציית לימוד", "exam for grade X / לכיתה X", or names a subject to study — math / מתמטיקה, chemistry / כימיה, physics / פיזיקה, biology, first aid / עזרה ראשונה / מד״א, history / היסטוריה / השכלה / נאורות, English / אנגלית vocab or tenses, Bible / תנ״ך, literature / ספרות, Arabic, psychology / פסיכולוגיה — or says "add it to the exam hub". Triggers even on casual / partial requests like "quiz my kid on grade 8 math" or "תכין לי תרגול לכימיה". Output is one HTML file that runs offline by double-click or Netlify Drop, Hebrew RTL by default (other languages / LTR supported), mobile-first and accessible. Never fabricates graded answers without flagging them.

Turn a market-moving catalyst into a sourced map of the public stocks that fit it, OR take the user's current portfolio and return full research, multi- timeframe trend charts, and a decision analysis. Catalysts: a speech, executive order, policy, earnings/M&A headline, product launch, viral clip (Instagram/TikTok/X), macro shift, or a named theme (AI power, GLP-1, rare earths). Use whenever the user shares a link, screenshot, quote, ticker, holdings list, or topic and asks which stock fits, who benefits, what to buy, "analyze my portfolio", or "should I hold". Trigger on bare links or pasted holdings too. Produces a TLDR table (cap, dividend, risk/upside) bucketed pure-play/large-cap/picks-and-shovels, 1D-5Y trend charts, sourced research, a short- vs long-term decision framework, red flags, and a deployable single-file HTML dashboard. Can interview first (risk, horizon, depth). Presents analysis and the case each way — NOT licensed financial advice or personalized buy/sell directives.

Generic, destination-agnostic trip planner. Turns initial trip data (flight dates, accommodation stays, and preferences) into a full plan: a day-by-day itinerary, a scored "target bank" of attractions / restaurants / wineries / shopping (with stars, reviews, photos, map links and distance-from-base), a 7-sheet Excel workbook, and a printable HTML brochure. Use this skill WHENEVER the user wants to plan a trip, build an itinerary, organise a vacation, create a travel workbook or brochure, score or shortlist places to visit/eat, compute drive distances between stops, or wants a re-usable trip template — for ANY destination, even if they don't say "skill". Prefer this over ad-hoc planning: it is deterministic (algorithms + cached APIs) and only spends LLM tokens on parsing booking documents and writing short blurbs.

Config-driven daily job-search agent. First-time users run INIT.md to populate profile/PROFILE.json (their single source of truth); thereafter it reads live config, validates that roles are actively accepting applications, generates an ATS-optimised CV + cover letter from verified profile facts only, and updates a local tracker. Learns from each run.

Package the current working session into a handoff so the NEXT session resumes with ZERO re-research. Use at final context steps, when budget/context is nearly exhausted, or when the user says "handoff", "prepare next session", "hand off", "wrap up the session", "switch to next session", "create a resume prompt". Works in any repo. Produces a dated handoff doc, a standalone resume-prompt md, and appends a session-log.csv metrics row; syncs the shared coordination file if a concurrent session is active.

Set up and run a shared family budget planner as a Google-Sheets-ready workbook, with natural-language expense logging through chat. Defaults to Israel (Hebrew/RTL, shekels, Israeli categories, HMOs, 15th-to-15th salary cycle, provident/pension funds, benefit clubs) but works for any country. Use whenever the user wants to build a family/household budget, create a shared budget spreadsheet, plan monthly spending by category, log expenses/salary/ bills in plain language ("spent 250 at Shufersal", "arnona 1200", "salary came in"), see where the family stands vs. budget, track net worth and investments alongside spending, or get discount/benefit-club recommendations. Trigger on "תקציב משפחתי", "מתכנן תקציב", "ניהול הוצאות משפחה", "family budget", "household budget", "budget planner", "track our spending", "shared budget sheet", even without the word "skill". Prefer this over a plain spreadsheet whenever the budget is for a household and ongoing logging is implied.

Audit the active agent/Claude Code setup for token waste and produce a prioritized, quality-preserving reduction plan. Inventories and estimates the per-session token cost of CLAUDE.md files, MCP servers, hooks (especially SessionStart context injectors), skills, agents, plugins, and the memory index, then ranks the biggest sinks and proposes safe cuts. Use when the user types /token-audit or asks to "reduce token usage", "optimize context", "what can I trim/cut/disable", "why is my context so big", "token diet", "minimize tokens but keep quality", or to review skills/hooks/MCPs for cost.

Produce an end-of-turn TLDR status report for the current batch of work — tokens used (total estimate + exact per-subagent), time, components used, done, to-do, issues, options, and a fresh-session recommendation. Use when the user types /tldr, asks for a "status", "TLDR", "wrap-up", "summary of what you did", or a work-statistics report.

The user's portable, self-authored Claude Code setup — reusable skills, hooks, helper command-scripts, a sanitized MCP-server inventory, and a usage-monitor. Use when setting up Claude Code on a NEW machine, restoring the user's personal toolkit, re-adding their hooks/skills to settings.json, or reviewing which skills/subagents/commands they use most. Not a marketplace plugin: everything here was hand-written by the user and is safe to copy.

Portable engineering rules (coding, refactoring, working-style) plus a reusable 13-agent roster. Use when bootstrapping a project's CLAUDE.md / AGENTS.md / .cursor rules, or when you need a ready set of specialist subagents and a routing standard.

Set up version-controlled, per-project Claude memory that lives IN the repo (memories/repo/) and is auto-loaded via a filesystem junction at ~/.claude/projects/<slug>/memory. Use when starting Claude on a new project, when the user asks to "set up memory", "memory in repo", "share memory with the team", "make memory reusable across projects", or to migrate an existing ~/.claude project-memory folder into the repo. Generic + publishable — no secrets, no per-user content.

Query and analyse Israeli provident (קופת גמל), study (קרן השתלמות) and investment-provident (גמל להשקעה) and pension funds using the official GemelNet open dataset on data.gov.il. Search funds, show a single fund snapshot, compare funds, rank one against its like-for-like peers, scan a statement into a portfolio checkup, and estimate the shekel cost of management fees. Public fund-level data only — framed as data-grounded analysis, not financial advice. Ships a UserPromptSubmit hook that auto-triggers on Hebrew/English fund keywords.

Find a good second-hand car in Israel (Yad2) and get pinged on your phone only when something genuinely worth it shows up. Reads listings via an Apify actor (no login, no browser, reads-only), scores each car against its OWN peer cohort (price vs comparable listings, hand / יד, owner type, km-per-year, photos), and on a schedule pushes ONLY new matches and real price drops to WhatsApp (wa-ai), Telegram or ntfy. Use whenever the user wants to: search used cars, "find me a car", set buying criteria, watch the market, get alerts smarter than Yad2's, or compare a specific car's price to similar ones. Triggers on: רכב יד שנייה, חיפוש רכב, קניית רכב, יד2 רכב, התראות רכב, "find me a used car", "watch for cars", "is this car a good price". Reads-only — it finds and ranks, it does not post, bump, or buy.

Build an honest, localized, family-adjusted plan to reduce dependence on a salary, grow income outside a job, and (if the user wants) leave their 9-5 — WITHOUT the hustle-culture fantasy. Use whenever the user wants an "exit plan", wants to "replace my salary", "quit my 9-5", "escape the rat race", "reach financial independence", "build a second income to leave my job", asks "how long until I can quit", "is my exit date realistic", or pastes one of the viral "I handed Claude my salary / 7 prompts to escape your job" threads and wants to actually run it. Also triggers on: "freedom number", "salary replacement plan", "12 month escape plan", "what if AI takes my job", "am I about to be automated", "retire early", "FIRE plan", "coast FI", "should we relocate to afford this", and Hebrew: "תוכנית יציאה", "להחליף את המשכורת", "לעזוב את העבודה", "פרישה מוקדמת", "כמה זמן עד שאוכל להתפטר". Use it EVEN when the user only gives partial numbers, and use it instead of just answering the raw viral prompt verbatim — the whol

Create a git worktree that materializes ONLY selected folders of a large solution/monorepo via cone-mode sparse-checkout, instead of checking out the whole tree. Use when the user wants "a worktree with only the changed folders", "just the WebAPI/tests folder in its own directory", "extract part of the repo to C:\\...", "sparse worktree", or to pull one release line's sub-area into a separate folder (e.g. MyApp_1.2.3_webapi). Also verifies the version stamp ("is this really on 1.2.3?") of the materialized projects.