AI & ML

octo-patch Bundle

Unified AI News Tracking Specification - covers Product/Model/Benchmark/Funding types with tracking scope, source standards, timeliness checks, scoring criteria, and record format

awrshift Skill

Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique this', or similar. Three review styles: Devil's Advocate (single critique), Boardroom Debate (parallel multi-reviewer validation), Round-Table (multi-round brainstorm for choosing between paths). Not for factual lookups — use WebSearch for those.

awrshift Skill

End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one — synthesize where they agree vs diverge, apply the cheap-safe fixes immediately, record a measurable plan for the rest, and CHALLENGE reviewer claims you disagree with (never blind-accept). Use at the close of a substantive coding or design session, when the user says "session review", "review my session", "stress-test this session", or types /session-review. Skip for trivial one-off edits.

kingmadellc Bundle

Complete Kalshi trading command interface — portfolio P&L, live market scanning with edge scoring, trade execution, and risk management through your OpenClaw agent. Built-in safety: $25 max trade, 100 contract cap, $50 daily loss cutoff. Scan 600+ markets, query positions, execute trades with configurable blocklists and retry logic. Part of the OpenClaw Prediction Market Trading Stack — pairs with Kalshalyst for intelligent execution and feeds portfolio data to Market Morning Brief.

citedy Bundle

Stateful MCP-first producer for branded AI UGC shorts. Generates scripts, reuses brand/avatar memory, renders vertical talking-head videos, and optionally publishes to Instagram Reels and YouTube Shorts.

tambo-ai Skill

Manages AI SDK model configurations - updates packages, identifies missing models, adds new models with research, and updates documentation

airtable Skill

Lists bases, reads and writes records, manages tables and fields, filters and searches data in Airtable via the `airtable-mcp` CLI. Use when the task involves Airtable data or the user mentions airtable-mcp, bases, tables, records, or fields.

airtable Skill

Builds Airtable filters parameters for the MCP tools that list or display records — field-type-aware comparison operators, choice and collaborator IDs, date ranges, and nested AND/OR logic. Use when the user wants to find, filter, narrow down, or search Airtable records by field values, even when they don't explicitly say "filter."

airtable Skill

Explains what Airtable is and how data is structured — bases, tables, fields, records, views, automations, and interfaces. Use when you need context about the Airtable data model.

airtable Skill

Provides a clickable Airtable link whenever the agent has touched user-visible Airtable content. Use after every MCP call that creates, updates, lists, searches, or returns records, schema, or interface pages — bases, tables, fields, records, or pages. Hand off the most-specific URL the agent's tool calls have proven access to — prefer single-record URLs over table URLs, table URLs over base URLs, and interface page URLs when the user's access is restricted to pages. Format as a markdown link with a descriptive label. Construct URLs only from IDs the tools actually returned — never synthesize IDs to round out a URL. Compose this skill from any workflow skill that affects Airtable content.

wenyuchiou Bundle

Use when a consequential decision has genuinely competing positions that need bounded adversarial review before a human decision.

wenyuchiou Bundle

Use when a user asks to inspect coordination memory, propose a durable decision or resolution, review pending memory proposals, or apply an explicitly approved proposal as a new append-only event.

wenyuchiou Bundle

Use when a goal needs multiple bounded agent roles, parallel or dependent task packets, explicit scope partitions, and a provider-neutral DAG. Not for research-domain routing that owns .research, .paper, Zotero, Obsidian, or NotebookLM workflows; use research-hub-multi-ai for those.

wenyuchiou Skill

Use when an agent task needs bounded context packets, checkpoint-aware compaction, a fresh-session primer, or policy-controlled child results without loading raw logs into the primary session.

wenyuchiou Bundle

Use when reconciled multi-agent output needs an evidence-based PASS, CONDITIONAL PASS, or FAIL record before authorized delivery.

wenyuchiou Skill

Use when one agent must iteratively plan, act, evaluate evidence, and revise under a readable policy until acceptance, checkpoint, stop, or human escalation.

wenyuchiou Bundle

Use when multiple agent results must be checked for missing evidence, scope drift, contradictions, and merge conflicts before an acceptance decision.

airbytehq Bundle

Wires up an Airbyte connector for use in a PydanticAI or Claude SDK agent, or any other framework via agent_tool. Generates auth config, connector initialization, and tool_utils- or agent_tool-decorated tool functions. Use when adding a connector to an agent or setting up a new agent with a connector.

airbytehq Bundle

Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK. Scaffolds project structure, wires up connectors, composes tools, and creates a run loop. Use when building an agent with multiple connectors or scaffolding a new agent project.

superlines Skill

Comprehensive AI search visibility analysis using Superlines data. Use when auditing brand visibility across AI engines, analyzing competitor presence, or building GEO strategies based on real AI search data. Requires Superlines MCP server connection.

chaitanyame Bundle

Guide for creating effective Agent Skills during Spec Kit planning. Use when users want to create a new skill, update an existing skill, or when running /speckit.specify to create tech-stack-specific skills. Extends Copilot's capabilities with specialized knowledge, workflows, or tool integrations.

chaitanyame Bundle

Autonomous coding patterns for unattended feature implementation using Ralph loop runner. Use when running Ralph autonomous loop, implementing features without supervision, handling long-running agent sessions, or when context mentions Ralph, autonomous, unattended, or batch implementation.

builtby-win Bundle

Add tasks to beads repositories with smart project inference

builtby-win Bundle

Use when substantial implementation work should run through tmux with one orchestrator agent and one or more implementer agents, especially when the user says gaud, gaud-mode, god, godmode, or god-mode and wants milestone-based check-backs instead of one long unsupervised run.

builtby-win Bundle

Use when the user wants to read, search, create, update, move, complete, cancel, or delete Things 3 items from an agent or terminal workflow, especially when they mention Things, Things 3, Things3, things-cli, Things URLs, AppleScript, tags, projects, areas, deadlines, checklists, or task CRUD on macOS.

ryze-ai-adgent Skill

Measure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they cite — from actual GA4 referral data, not prompt sampling. Use when asked "AI visibility", "GEO/AEO check", "do LLMs cite us", "traffic from ChatGPT", or "how do we show up in AI search".

voxpelli Skill

Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-*.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for read-only sprint summaries — use the sprint-review agent for that.

mahmutka Bundle

Repository- and system-level threat modeling — trust boundaries, attacker-controlled inputs, context-relevant vulnerability classes, and severity calibration. Produces a reusable threat model that grounds later security review.

stackonehq Bundle

Behavioral guidance for Claude Code when StackOne Defender is running as a PostToolUse hook. Defender flags tool results that may contain prompt injection. Treat its flags as a quiet review hint — do a quick check for genuine injection, then continue working. Do not interrupt the user unless you confirm a real attack.

firebase Skill

How to write pytest tests for modules in this workspace. Load whenever you are about to write or extend tests.

firebase Skill

Conventions for clean, idiomatic Python. Load whenever you read, edit, or write Python source files.

anshumanbh Bundle

Identify agentic AI security threats based on OWASP Top 10 for Agentic Applications 2026. Use when analyzing AI agents, LLM-powered applications, chatbots, auto-reply systems, tool-using AI, browser automation, sandbox execution, or any application that uses AI/LLM APIs (Anthropic, OpenAI, Claude, GPT) to process user input and take actions.

shaunandrews Skill

Audit skills across agent runtimes, resolve canonical copies, and plan safe consolidation without overwriting divergent repositories.

saknarinz Skill

ปรับปรุงโค้ดให้ดีขึ้นโดยไม่เปลี่ยน behavior

cortalabs Skill

How to use Scribe MCP tools correctly — logging, docs, topology, bugs, file reading, search

cortalabs Skill

Install and connect Scribe MCP — pip install, one-command Postgres bootstrap, host/plugin projection, and first-bind verification