AI & ML

hack23 Skill

Hack23 organization architecture documentation standards, C4 model requirements, future state planning

chocholous Bundle

Find and analyze scholarly research across the major open academic databases — search and rank papers by field-normalized impact, run a literature review, trace citation graphs, find similar / foundational / breakout papers, map a field's institutions and funders, compare institutions, build a citation-safe RAG corpus, check whether a preprint is safe to cite, mine biomedical entities and datasets, grade clinical evidence, and look up or disambiguate researchers. Covers all fields via OpenAlex, Semantic Scholar, arXiv, Crossref, PubMed, Europe PMC, CORE, DBLP, and ORCID. Use when someone wants academic papers, peer-reviewed studies, a literature or systematic review, an evidence summary, the most-cited or seminal papers, research trends, a research-funding or institution landscape, or a researcher profile — e.g. "find papers on...", "what does the research say about...", "summarize the literature on...", "who's winning this field".

chocholous Bundle

App-store intelligence and ASO research across the Apple App Store, Google Play, and the Shopify App Store. Pull app details, exact ratings and ratings histograms, customer reviews, and keyword/category rankings, then compare an app against its competitors. Use when the user asks to scrape App Store or Google Play data, track app reviews or ratings over time, do ASO / app-store keyword rank research, monitor competitor apps, mine app reviews for sentiment or feature requests, or research the Shopify app ecosystem. Requires the Apify CLI or the Apify MCP server.

chocholous Bundle

Pull Street View and 360 panoramas for a place by name with a google maps street view api built on the Apify Google Maps Photos API Actor (johnvc/google-maps-photos-api). The official Street View Static endpoint wants a latitude, longitude and heading and returns one rendered tile; this returns a listing of the panoramas actually attached to a business, addressed by its name or its Google Maps URL, as rows with the full-size image url, a thumbnail, gallery position and a stable photo id. Set the category to street_view for panoramas or videos for clips. Use when the user wants a street view api, google street view images for a business, 360 photos of a location, exterior or frontage imagery for site surveys, real estate, insurance or field-service work, without geocoding first. Pay per image returned, MCP-ready for Claude and other AI agents.

chocholous Bundle

Build your own fare history for google flights tracking with the Apify Google Flights Deals API Actor (johnvc/google-flights-deals-api). Run it on a schedule against one or several home airports and every row arrives with the fare, what that route typically costs, the gap between them, exact dates, airline and a booking link, so successive runs accumulate into a price record you own and can query. This is the data layer under a price-alert product, not the alerting itself. The Actor takes a snapshot and keeps no history and sends no notifications, so the repeated observation is yours to store and the notify rule is yours to write, and a baseline in every row means that rule can be below typical instead of a threshold you guessed. Use when the user wants flight price tracking, airfare monitoring, fare data with a reference price, or the source feed behind flight price alerts. Pay per deal returned, MCP-ready for Claude and other AI agents.

chocholous Bundle

Search the Yandex Images vertical and get full-size image URLs as structured JSON with the Apify Yandex Search Scraper Actor (johnvc/Scrape-Yandex). A yandex image search api for agents and pipelines. One text query returns image results with the original full-size image URL, hosting page link, thumbnail, and source, filtered by image type, color, orientation, file type, exact size, site, and recency. Use when the user wants a yandex image search api or yandex images api, wants to search Yandex Images programmatically, collect image datasets with full-size URLs, source images from Russian-language sites, or filter image results by color, size, or license-friendly site. Pay-per-page billing, MCP-ready for Claude and other AI agents.

chocholous Bundle

Discover Instagram brand–creator partnerships by chaining Apify Actors. Use when the user asks who collabs with a brand, which brands a creator has done paid posts for, wants to audit an influencer's branded-content history, or wants to scope a brand's sponsorship roster. **Triggers:** - "who collabs with [brand] on Instagram?" - "what brands has [creator] done sponsored posts for?" - "find paid partnerships / branded content for [handle]" - "audit [influencer]'s brand deals" - "show me [brand]'s influencer roster" Works in either direction — brand → creators or creator → brands — and detects direction from the data, so don't ask the user to declare it. Requires Apify MCP tools.

chocholous Bundle

Analyze LinkedIn post engagement with the Apify LinkedIn Posts API Actor (johnvc/linkedin-posts-api). Collect a profile's posts or a list of post URLs, then measure reactions, comments, and shares alongside author reach (followers, headline) to see what performs. Use when the user wants to analyze LinkedIn post engagement, measure engagement rate, find a creator's or a competitor's top-performing posts, benchmark engagement across profiles, track post engagement over time, or build a LinkedIn engagement report. Returns one row per post with numLikes, numComments, numShares, datePosted, and a ready-made engagement view. Pay-per-post billing, MCP-ready for Claude and other AI agents.

chocholous Skill

Monitor known public web pages for meaningful content changes with persistent snapshots and structured diffs. Use when the user asks to "monitor a website", "track a pricing page", "watch competitor pages", "detect page changes", "track recruitment or job page changes", "monitor FDD or filing pages", "compare a page with its previous version", or create a recurring known-URL watchlist. Returns hashes, added and removed text, categorized business signals, and explicit baseline, unchanged, changed, blocked, or failed status. Requires an Apify account and CLI or MCP access.

chocholous Skill

Build real-estate agent and listing lead lists from Zillow - property details plus the listing agent's email, cell phone, brokerage and license number - and fall through to web enrichment only for the rows Zillow leaves empty. Use when the user says things like "get real estate agent emails", "scrape Zillow listings", "find realtor contacts in a ZIP code", "build a list of listing agents", "Zillow lead generation", "pull homes for sale with agent contact", "recently sold comps", or "who is the listing agent". The agent's phone is in the listing row every time and the email about 4 times in 5, so this skill leads with what the property scrape already returned and only pays for contact-enrichment on the remainder - instead of routing every lead through a Google Maps email scraper, which costs more and matches the wrong business.

chocholous Bundle

Bulk google maps photo download with the Apify Google Maps Photos API Actor (johnvc/google-maps-photos-api). Name a place, paste a Google Maps URL, or search a category and city, and get one row per photo with the full-size image url, a thumbnail, its gallery position, and a stable photo id you can de-duplicate on across runs. One run sweeps up to 20 places, so a whole neighbourhood of businesses comes back in a single pass instead of one right-click at a time. Filter to a gallery section when you only want menus, interiors, or owner uploads. Use when the user wants to download google maps photos, bulk place images, a google maps images api, place photos api access, or imagery for a directory, listings site, or dataset. Pay per photo returned, MCP-ready for Claude and other AI agents.

chocholous Bundle

Build TypeScript Apify orchestrator Actors — coordinate a sequence of sub-Actors (optionally with an LLM step) using the apify-orchestrator library. Use when creating a new orchestrator Actor, chaining Apify Actors together, adding an OpenRouter LLM step between Actors, or scaffolding parent-Actor workflows that call other Actors.

chocholous Bundle

Build LLM training data from YouTube transcripts in bulk with the Apify Actor johnvc/YoutubeTranscripts. Feed it an array of video URLs and get one clean row per video, with non_timestamped transcript text ready for tokenization, timestamped snippets, language_code, and provenance metadata (title, channel_name, upload_date, view_count) for dataset documentation. Filter by language or translate every transcript into one target language for a consistent corpus. Use when the user wants LLM training data from videos, a fine-tuning or RAG corpus from YouTube, bulk YouTube transcripts for machine learning, or a text dataset from spoken video content without running speech-to-text. Pay-per-video billing, MCP-ready for Claude and other AI agents.

ferroxlabs Skill

Generate DMCA takedown notice, counter-notice, and designated-agent registration walkthrough - 17 USC §512(c)(3) elements, dmca.copyright.gov registration, repeat-infringer policy template. Templates only - not legal advice. Have an attorney review high-stakes notices.

davie521 Skill

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.

davie521 Skill

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

davie521 Skill

Challenge an implementation approach or design choice via Codex (read-only `codex exec` through the codex-run wrapper). Read-only, asks "is this the right path?" — not "are there bugs?". Trigger when the user says "质疑这个方案" / "这个设计靠不靠谱" / "challenge this design" / "design review" / "second-guess this approach" / "考虑过 X 吗" / "is this the right approach" / "stress-test the design" / "punch holes in this". Returns assumptions / failure modes / alternatives — NOT a bug list, NOT a severity matrix. Division of labor with grill-with-docs — user wants to be interactively grilled question-by-question → dev-workflow:grill-with-docs; user wants a fully-formed proposal attacked by an external model in one pass → this skill.

davie521 Bundle

Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use ONLY for two scenarios — (1) the user needs to compare multiple structurally different UI approaches side by side before picking one, or (2) the user needs to manually step through a state machine / data model that is hard to reason about on paper. For building a real page or polished UI, use ui-ux-pro-max / hallmark instead — this skill produces throwaway code.

davie521 Skill

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

davie521 Skill

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use when the user wants to write, extend, or debug an MCP server — implementing tools/resources/prompts, choosing a transport, upgrading the SDK, or fixing registration/transport issues. Use Context7 or official MCP docs for latest API.

davie521 Skill

Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types. Use when migrating a project to Swift 6.2 concurrency, adopting @concurrent or MainActor-default inference, or resolving data-race safety compiler errors ("sending X risks causing data races").

davie521 Bundle

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan, get grilled on their design, mentions "grill me", or wants to challenge a plan against their project's language and documented decisions.

davie521 Skill

Cost discipline for LLM pipelines — parse structured text with regex first and escalate only flagged items to an LLM, route the cheapest sufficient model tier by task size, track budget, retry narrowly, cache prompts. Use when building LLM pipelines, controlling API costs, or choosing between regex and LLM for parsing structured text (构建 LLM 管道、控制 API 成本、解析结构化文本选方案时).

davie521 Skill

Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.

iblai Skill

Discover agents and learning content in an ibl.ai organization via the platform API — faceted, paginated search over agents and the catalog (courses, programs, pathways, skills), personalized (RAG) recommendations, global/personalized agent search, and seller-facing sellable-items search; plus admin management of the recommendation prompts. Use to find, browse, or get recommended agents/content (mostly read-only; recommendation-prompt endpoints write).

iblai Skill

Set an ibl.ai agent's LLM provider and model via the platform API — list available provider/model cards and write the selection through the agent settings endpoint. Use when changing which model an agent runs on.

iblai Bundle

MCP connectors for ibl.ai agents, end to end — register MCP servers (featured multi-tenant sharing, enable/disable, OAuth service linkage), manage credential connections with the auth_type × scope matrix (org / agent / per-user), wire servers onto an agent, run the OAuth connected-service lifecycle, handle per-user in-chat OAuth (the oauth_required / oauth_connection_resolved chat events), and debug MCP auth failures (401s, missing OAuth prompts, agents ignoring servers). Use when wiring an agent to external MCP servers and tools, or designing/troubleshooting MCP auth.

iblai Skill

Run inference against an ibl.ai deployment through its OpenAI-compatible API — same request/response shape as OpenAI's /v1/chat/completions, routed to any configured provider/model (e.g. openai/gpt-5). List models, then POST OpenAI-format messages for a single completion or a streamed SSE response, with Api-Token auth. Use to generate completions or tool calls directly, without the agent-chat MCP server or agent wiring.

iblai Skill

Set up live chat with a deployed ibl.ai agent by wiring the hosted iblai-api-agent-chat MCP server into the project (.mcp.json / claude mcp add) using the .env Api-Token and a chosen agent's unique id. Use to enable runtime conversations with an agent. The actual chatting then happens through the MCP server's tools.

iblai Skill

Enable or disable an ibl.ai agent's tools via the platform API — list toggleable tools, read currently enabled tool slugs, and write the enabled set (saved through the agent settings endpoint). Use when controlling which tools an agent can use.

iblai Skill

Manage an ibl.ai organization's LLM spend caps via the platform API — admin-imposed maximum LLM cost at three scopes (tenant-wide, one agent, or one user on one agent), each with a rolling interval (day/week/month/year), a hard-block or alert-only enforcement mode, and near-limit alert thresholds. Read the current fill/zone for a user's applicable caps (learner-safe, dollars hidden). Use when setting a budget ceiling on an org/agent/user, listing configured caps, checking how close a user is to their limit, or removing a cap. Spend counters are reconciled from ClickHouse and are read-only.

iblai Skill

Read an ibl.ai agent's audit log via the platform API — a who-changed-what trail filterable by action, actor email, and date range. Read-only. Use when investigating configuration changes to an agent.

iblai Skill

Manage an ibl.ai agent's skills via the platform API — browse the org skill catalog, assign/unassign skills to an agent, and create/edit/delete catalog skills. Requires a connected sandbox. Use when giving an agent reusable skill instructions.

iblai Skill

Manage an organization's account-level integrations via the platform API — third-party LLM provider keys, Data Source credentials, and Platform API tokens. Use when connecting an ibl.ai organization to external model providers, data sources, or issuing API keys.

iblai Bundle

Create a new ibl.ai agent from a template via the platform API — set name, display name, description, system prompt, and LLM provider; returns the new agent's unique id. Use when creating an agent from scratch, then configure it with the other /iblai-api-agent-* skills.

iblai Bundle

Manage an ibl.ai agent's memories via the platform API — list and filter agent (mentor) memories (by category, user, email, date), curate global (cross-agent) memories, curate shared agent knowledge injected into every user's chat, add/edit/delete memories, manage memory categories, and toggle capture/recall settings. Use when inspecting or curating what an agent remembers.