AI & ML

celigo Skill

Manage Celigo on-premise agents -- lightweight software you install on a host inside your own network that opens a secure OUTBOUND tunnel to integrator.io, letting the platform reach private systems (on-prem databases, file shares, internal apps) without opening inbound firewall ports. An on-premise agent is a connectivity resource on the `/agents` page -- not a stack (compute) and not an AI agent (LLM processing). Use when connecting to a system behind a firewall, installing or pairing an agent, rotating its access token, or diagnosing agent-offline flow failures.

laguagu Skill

Write or update a HANDOFF.md so a fresh agent can continue this work. Use when the user says "handoff", "compact this", "context is full", or "/clear and continue".

laguagu Bundle

Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, streaming apps, or structured output with the ai package. Covers ToolLoopAgent, useChat, generateText, streamText, tool approval, smoothStream, provider tools, MCP integration, and Output patterns.

laguagu Bundle

Creates new skills, modifies and improves existing skills, and measures skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

laguagu Skill

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance (LCP/CLS/INP), or verify visual output with real runtime data. Complements Playwright — use this for live debugging and performance work, Playwright for stable E2E test suites.

laguagu Bundle

PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector indexing, hybrid FTS/BM25 + RRF, ParadeDB, reranking, halfvec, multilingual search, query translation, and domain evals. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW, IVFFlat, ParadeDB, pg_search, reranking, iterative_scan, filtered HNSW, halfvec, websearch_to_tsquery, unaccent, multilingual FTS, pg_trgm, trigram, fuzzy search, ILIKE, autocomplete, typo tolerance, fuzzystrmatch, Hit@K, MRR, retrieval evals, cross-lingual retrieval, non-English corpus, per-language indexing, query translation For general Postgres schema, index, RLS or query tuning unrelated to retrieval, use supabase-postgres-best-practices instead.

trpc Bundle

Configure the tRPC client link chain: httpLink, httpBatchLink, httpBatchStreamLink, splitLink, loggerLink, wsLink, createWSClient, httpSubscriptionLink, unstable_localLink, retryLink. Choose the right terminating link. Route subscriptions via splitLink. Build custom links for SOA routing. Link options: url, headers, transformer, maxURLLength, maxItems, connectionParams, EventSource ponyfill.

trpc Skill

Configure SuperJSON transformer on both server initTRPC.create({ transformer: superjson }) and every client terminating link (httpBatchLink, httpLink, wsLink, httpSubscriptionLink) to support Date, Map, Set, BigInt over the wire. Transformer must match on both sides. In v11, transformer goes on individual links, not the client constructor.

trpc Skill

Create a vanilla tRPC client with createTRPCClient<AppRouter>(), configure link chain with httpBatchLink/httpLink, dynamic headers for auth, transformer on links (not client constructor). Infer types with inferRouterInputs and inferRouterOutputs. AbortController signal support. TRPCClientError typing.

geoffjay Bundle

Regenerates documentation files (agents.md, agent-skills.md, plugins.md, usage.md) from marketplace data using Jinja templates. Use when plugins are added, updated, or removed to keep documentation in sync.

software-mansion-labs Bundle

Fishjam platform fundamentals — domain model and auth shared by all SDKs. Covers glossary (room, peer, track, agent, streamer, viewer), the four room types (conference / audio_only / livestream / audio_only_livestream), two-tier auth (management vs peer tokens), Sandbox vs production, WebSocket-vs-webhook notifications and the 18-event taxonomy, REST endpoint list, and the end-to-end auth/join flow. Read this first for any Fishjam task. Trigger on: 'Fishjam', 'fishjam.io', 'fishjam.swmansion.com', 'fishjam dashboard', 'management token', 'peer token', 'sandbox API', 'useSandbox', 'room manager', 'livestream room', 'audio-only room', 'conference room', 'Fishjam ID', 'room types', 'auth flow', 'webhook', 'webhookUrl', 'FishjamWSNotifier', 'FishjamNotifier', 'notifier vs webhook', 'ServerMessage', 'peerAdded', 'peerConnected', 'roomCreated', 'refreshPeerToken', 'rest endpoint', 'OpenAPI', 'llms.txt'.

software-mansion-labs Bundle

Python server SDK for Fishjam — backends that create rooms, mint peer tokens, receive server notifications, and run voice agents. Use when writing a Python backend (FastAPI, Flask, Starlette, aiohttp) that talks to Fishjam, decorates a notification handler, decodes a Fishjam webhook, or builds an AI voice agent in Python. Trigger on: 'fishjam-server-sdk', 'pip install fishjam-server-sdk', 'from fishjam import', 'fishjam.FishjamClient', 'FishjamNotifier', 'on_server_notification', 'receive_binary', 'fishjam Agent', 'AgentSession', 'PeerOptions', 'RoomOptions', 'AgentOptions', 'AgentOutputOptions', 'OutgoingAudioTrackOptions', 'create_room', 'create_peer', 'create_agent', 'create_vapi_agent', 'create_livestream_streamer_token', 'create_moq_token', 'subscribe_peer', 'fastapi fishjam', 'flask fishjam', 'fishjam python', 'gemini fishjam python'. Python 3.10+. The REST client is synchronous; notifier and agent are async.

srinitude Bundle

Use when packaging source input for a standing goal.

srinitude Bundle

Use when a workflow or capability must become a new agent skill, when an existing skill must be updated or standardized without losing its purpose, when a user-level or project-level variant is needed, or when a skill needs validation, evaluation, scaffolding, scripts, tests, or a Mise task graph.

srinitude Bundle

Use when the user asks to enhance, improve, refine, rewrite, strengthen, or validate a prompt, or says "make this prompt better". Returns a clearer, more specific, better structured version of the prompt without executing it, picking validation checks from the prompt's own context. Contexts include coding, research, writing, image or video generation, agentic tasks, data work, and system prompts. Flags ambiguity, contradictions, missing constraints, missing success criteria, format gaps, and leaked secrets. Do not use when the user wants the prompt's task performed.

srinitude Bundle

Use when a claim depends on an agent taking a real action.

srinitude Bundle

Use when one exact callable tool and a user-authored behavior configuration must become a tool-specific Agent Skill, or when that behavior must be integrated into one exact existing Agent Skill. Supports established or owned MCP, native, and custom tool contracts; stops on ambiguous identity, behavior, authority, source, or update target.

asmartbear Skill

Reference for creating, editing, or updating Claude Code SKILL.md files — including any change to a skill's YAML frontmatter, description, invocation rules, or body. Covers all YAML frontmatter fields (description, when_to_use, disable-model-invocation, user-invocable, allowed-tools, disallowed-tools, context, agent, effort, paths, shell, etc.), authoring best practices, and string substitutions. Load BEFORE writing or modifying any file in .claude/skills/, not only when creating a new one. For agent .md files, see doc-agents.

asmartbear Skill

Scores whether a business idea can become a viable business, walking the path from 'The Problem' to 'Viable Business Model': one specific target market is Fermi-scored on seven multiplying criteria (Plausible, Self-Aware, Lucrative, Liquid, Eager ×2, Enduring), every optimistic number is challenged unless evidence backs it, and when the verdict is bad, narrower niches are re-scored side by side. Load when the user asks whether their startup or product idea is viable, whether a market really exists for what they want to build, why a product that solves a real problem isn't selling, which of several target markets to pursue, whether to persevere or give up on a product, or says 'score my idea.' Do NOT load for general devil's-advocate stress-testing of plans or pitches without the viability question, for building a full ideal-customer profile, for writing customer-interview questions, or for execution problems like funnel optimization, hiring, or fundraising.

bilalmk Bundle

Advanced SQLModel patterns and comprehensive database migrations with Alembic. Use when creating SQLModel models, defining relationships (one-to-many, many-to-many, self-referential), setting up database migrations, optimizing queries, solving N+1 problems, implementing inheritance patterns, working with composite keys, creating indexes, performing data migrations, or troubleshooting Alembic issues. Triggers include "SQLModel", "Alembic migration", "database model", "relationship", "foreign key", "migration", "N+1 query", "query optimization", "database schema", or questions about ORM patterns.

bilalmk Bundle

Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.

bilalmk Bundle

Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.

bilalmk Bundle

Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.

bilalmk Bundle

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

bilalmk Bundle

Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction. NOT when only fetching static content (use curl/wget instead).

bilalmk Bundle

Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.

dig1t Skill

Use when a task hits Roblox platform behavior rather than project logic — a placed model's rotation comes out flipped 180 degrees, CFrame/Euler math (Angles vs fromEulerAnglesYXZ, left-handed basis), a client tag handler finds nil children, StreamingEnabled quirks, DataStore session locks, ProcessReceipt / PurchaseGranted / NotProcessedYet / double-grant questions, DevProduct vs GamePass vs Subscription, Luau strict-mode narrowing errors, session-vs-persistent currency theory, or "look it up in brain".

dig1t Skill

Use when a claim needs proof, not a retry — a placed model faces the wrong way (CFrame/basis/Euler math), client and server disagree on an orientation, an economy or difficulty number needs a derived prediction before tuning, a ProcessReceipt path might double-grant or drop on crash, seeded generation should be identical across restarts but isn't, or a player-keyed table goes nil after a yield. Also for pre-tuning predictions (change-control rule 4 evidence) and "prove it, don't just try it" requests.

lightdash Skill

Guide for AI agents running in the isolated agent-harness environment. Use when you need to discover your agent ID, find your ports, manage your stack with agent-cli.sh, run verification, or understand the multi-agent development setup.

machina-sports Skill

Gateway to the Machina Sports premium platform — packaged agent workflows ("templates"), licensed real-time data, betting odds, and zero-latency live streams. This skill is prompt-only: it shells out to the separate `machina-cli` binary and routes the agent to a per-project Machina MCP server. Use when: the user asks for live odds, real-time telemetry, zero-latency match states, sub-second tick streams, packaged sports workflows (e.g., "Build a Bundesliga podcast bot", "Create a Polymarket arbitrage engine"), or when the open-source sports-skills are rate-limited or insufficient for the task. Don't use when: the user wants snapshot data from public APIs — use the sport-specific skill (nfl-data, polymarket, markets, …). Don't use to fetch data through raw HTTP — use the Machina MCP server, not a `requests` call.

machina-sports Skill

Premium FIFA World Cup 2026 market & match intelligence — a hosted, read-only layer that fuses official match truth (fixtures, standings, squads, injuries, player performance) with live prediction markets (Kalshi + Polymarket: prices, order books, price history, movers, cross-venue edges) and AI-grounded context (prematch briefs, move explanations, fan/social pulse). Every entity carries a canonical machina URN cross-walked across api-football, sportradar, opta, entain and ESPN, so a market resolves to a fixture resolves to two teams. This skill is prompt-only and premium: it routes the agent to the hosted World Cup Intelligence project (a per-project Machina MCP server) via `machina-cli`. It runs no code locally and ships no API keys. Use when: the user wants World Cup 2026 odds + match context together, asks "what moved and why", wants a grounded market brief or fan-sentiment read on a fixture, or needs one stable id that joins markets ↔ fixtures ↔ teams across providers. Don't use when: the user wants free

sumsub Bundle

Manage Sumsub `clientWebhooks` (event subscriptions for applicantReviewed / applicantPending / kytTxn / etc.) — reads via `/resources/api/clientWebhooks`, writes via `/resources/api/agent/clientWebhooks`. **Sandbox only** — production webhooks must be created by a human directly in the Sumsub dashboard. TRIGGER when the user asks to "list / retrieve / show webhooks", "create / add / register a webhook", or "update / edit / change a webhook target / event list / secret / signature algorithm" against their sandbox tenant. SKIP for production webhook setup (refer the user to the dashboard), for unrelated webhook surfaces (Stripe / videoIdent / Fireblocks / NFC / partner-specific receive paths under `/resources/webhooks/...`), for testing one-off delivery (use the `inspectionCallbacks/testWebhook` endpoint directly), and for KYT-only webhook routing (that's managed in the Sumsub dashboard's KYT section). The public API does not expose delete or per-webhook delivery stats — for those, refer the user to the Sumsub

sumsub Bundle

Create or update a Sumsub Proof-of-Address (POA) preset. POST `/resources/api/agent/poaStepSettings` to create new, PATCH same path to update (id in body), GET `/resources/api/agent/poaStepSettings/{id}` to read one back. TRIGGER when the user asks to "create / add / build / configure / update / edit a POA preset" or "PoA step settings", configure which proof-of-address document types are accepted (utility bills, bank statements, tax bills, etc.), set validity periods per provider type, enable POI-as-POA (accept identity doc as proof of address), tune the cross-validator (name/address fuzzy match between POI and POA), or add per-country POA overrides. SKIP for attaching a preset to a level (set `poaStepSettingsId` on the level instead, via `sumsub-create-level`), or for non-POA presets (cross-check presets, permission presets, etc.).

sumsub Bundle

Verify that the locally installed Sumsub agent-skills package is compatible with the published version before doing any Sumsub work. TRIGGER at the start of any task that touches Sumsub — Sumsub Dev MCP tools (mcp__Sumsub_Dev__*), KYC/AML workflows, applicants, checks, transactions, verification levels, verification links, questionnaires, fraud network, VASP lists, or anything Sumsub-related — so the user is warned before a stale skills package produces wrong results. Also use this skill when the user explicitly asks "are my Sumsub skills up to date / current", "is there a newer version of the Sumsub skills", or similar. Skip the actual update (the user runs `npx skills add sumsub/agent-skills --all` themselves) and skip any other Sumsub API or entity task — those have their own skills.

sumsub Bundle

Create or update a Sumsub KYC questionnaire definition. POST `/resources/api/agent/questionnaires` to create new (fails 409 if id exists), PATCH same path to update (fails 404 if id is unknown), GET `/resources/api/agent/questionnaires/{id}` to read one back. TRIGGER when the user asks to "create / add / build / update / edit a Sumsub questionnaire", or supplies a list of questions / sections meant for a Sumsub applicant flow, or references a questionnaire id / definition to be POSTed or PATCHed. SKIP for other Sumsub entities (levels, workflows, applicants), questionnaire data (answers) submission, or non-Sumsub form builders.

sumsub Bundle

Create or update a Sumsub cross-check preset (name/address comparison rules between POI and POA documents) via `POST/PATCH /resources/api/agent/crossCheckPresets` and `GET /resources/api/agent/crossCheckPresets/{id}`. TRIGGER **ONLY** when the user EXPLICITLY asks to override how cross-checks compare names or addresses — e.g. "switch name match to strict", "allow fuzzy address match", "ignore middle-name mismatch", "create a custom cross-check preset". SKIP by default — Sumsub ships sensible defaults tuned for the best conversion and approval rate, so most clients should NOT create a custom preset. SKIP for level creation (the default cross-check preset auto-applies to every level), for general KYC config, or any request that doesn't specifically name "cross-check rules", "name comparison", or "address comparison".