quad-fact-check
Claude + Gemini + Codex 4-way cross-fact-check. Four parties—Opus itself, Gemini Flash, Gemini Pro, and Codex (gpt-5.3-codex)—independently check → extract points of contention → discuss → output a consensus report.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,530 results
cap-llm-plugin
Use when building AI/LLM features inside a SAP CAP application: the CAP LLM Plugin (@sap/cds-plugin-llm or @sap-ai-sdk), RAG (Retrieval-Augmented Generation),…
create-tools
Create Databricks resources that agents connect to as tools. Use when: (1) User needs to create a Genie space, vector search index, UC function, or UC…
long-running-server
Enable long-running background task support with LongRunningAgentServer. Use when: (1) Agent tasks may exceed HTTP timeout (~120s), (2) User wants…
asyncio_patterns
Async concurrency patterns for running agents in parallel within the KYC pipeline
decision_explainer
The English introduction is being prepared.
agent-factory
Meta-skill that orchestrates the full agent creation pipeline. Composes: trend-discovery → api-research → lucid-agents-sdk → railway-deploy. Use when creating…
repo-standards-review
Review a pull request or a branch against the repository's standards — skill frontmatter and body, docs and bilingual pairs, Agent Notes, and scripts — and…
the-council
Facilitate structured deliberation with multiple specialist subagents to reach consensus on complex decisions.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
jolly
End-to-end playbook for setting up a Saleor Cloud storefront with Jolly — teaches the customer's own agent to drive the official CLIs (Vercel,…
multi-llm-convergence
Drive any artifact to convergence by alternating two genuinely different LLM reviewers — a Codex reviewer and an independent Claude review subagent — applying…
auto-optimize-prompt
Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering…
compress-prompt
Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to…
rlm-subagent
Master skill for parallel subagent-driven execution with automatic fallback to single-agent sequential mode. Use when implementing plans with multiple…
prompt-enhance
[Skill Management] Use when enhancing, compressing, or expanding prompts, docs, or skills with attention anchoring [INTELLIGENT ROUTING]. Flag:…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web…
audit-agents
Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.
breadcrumbs
Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what…
using-superpowers
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage,…
mcp-review
Review fallow's MCP server for tool contract clarity, output stability, and agent usability. Use when changes touch crates/mcp or AI-agent integration surfaces.
agent-builder-pydantic-ai
Build conversational AI agents using Pydantic AI + OpenRouter. Use when creating type-safe Python agents with tool calling, validation, and streaming.
chatgpt-ask
Use when the user wants to ask ChatGPT a question through Frevana using the user's logged-in Chrome Extension session.
agent-harness-orchestration
Coordinate multiple coding agents in shared repos with task packets, worktree or branch isolation, path ownership, verification loops, and PR or CI…