#SkillRepo stars
- 865Call Cross Call Consistency CheckerCALLE-AI/awesome-phone-call-agentsOffline experimental CALL-E helper that compares amounts, dates, and times stated by the agent across two finished calls to the same destination and grades each fact kind CONSISTENT, CONTRADICTED, or ONLY_STATED, plus a consistency-guarded goal template. It is not proof either call lied, a record of truth, or authorization for another call.116
- 866Call Human Escalation Request AuditorCALLE-AI/awesome-phone-call-agentsOffline experimental CALL-E transcript helper that detects callee requests for a human agent (transfer intent plus human role, or bare manager/supervisor demands) and grades the agent response window HONORED, DEFLECTED, IGNORED, or FALSE_HUMAN_CLAIM, plus an escalation-honesty goal template. It is not proof a transfer happened, intent detection, or authorization to act.116
- 867Call Negotiation CoachCALLE-AI/awesome-phone-call-agentsPre-call strategy engine and post-call debrief for negotiation calls. Implements BATNA/ZOPA/Dual Concern Model + DISC-matched tactics.116
- 868Call Repair Sequence AuditorCALLE-AI/awesome-phone-call-agentsOffline experimental CALL-E transcript helper that detects callee-initiated repair sequences (huh, can you repeat, did you say X), localizes and profiles the trouble-source agent turn, classifies how the agent handled each repair, and crafts chunked redial goals. It does not measure comprehension conclusively, calibrate a per-minute rate, or authorize another call.116
- 869Call Semantic Barge in AnalyzerCALLE-AI/awesome-phone-call-agentsPost-call cooperation skill. Classifies callee turns in a CALL-E transcript as backchannels ("mm-hmm", "right, okay"), frustration barge-ins ("wait", "hold on", "slow down"), or substantive answers - disambiguating answers from backchannels via the preceding agent question - and computes pacing metrics including backchannel density and whether the agent shortened its turns after the first interruption. Returns a cooperation profile (ENGAGED_COOPERATIVE / NEUTRAL / FRUSTRATED_INTERRUPTING / DISENGAGED) with a pacing recommendation and a ready-to-use pacing goal for the next plan_call. Heuristic116
- 870Call Sycophancy GuardCALLE-AI/awesome-phone-call-agentsOffline experimental CALL-E transcript helper that detects pushback against goal-grounded facts and classifies the agent's response (HOLDS, CAPITULATES, VERIFIES, UNADDRESSED), flags capitulated values that tainted the final confirmation, and crafts anti-capitulation goals. It is not a measure of the agent's intent, proof the callee was wrong, or authorization to act on the call's outcome.116
- 871Dialtone HandshakeCALLE-AI/awesome-phone-call-agentsUse when an AI phone call agent (outbound caller or inbound voicebot) needs to recognise that the other end of the call is also an AI, switch to a compressed machine mode, and label call results by who actually attested them (human, phone system, or AI agent).116
- 872Dollar Consent First CallbackCALLE-AI/awesome-phone-call-agentsPlace one consent-first CALL-E callback after a local safety gate has already blocked an extreme-risk developer action, so a known project owner can say stop or request normal review without granting the agent destructive permission.116
- 873Exception ResolverCALLE-AI/awesome-phone-call-agentsResolve operational exceptions by gathering missing information through an authorized CALL-E phone conversation and returning a structured result for human approval. Use when an AI agent encounters a supported operational exception that cannot be resolved from available system data and requires information from an authorized person.116
- 874Find Skillsalexdcd/Mafia-Claude-SkillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.70
- 875Google Form CallbackCALLE-AI/awesome-phone-call-agentsTurn Google Form lead or callback responses into safe one-off AI-agent phone calls with template-driven goals, scheduled runs, and result writeback.116
- 876Ground Truth GateCALLE-AI/awesome-phone-call-agentsUse when an agent holds some evidence for a physical-world claim but the evidence is broader, narrower, or older than the exact question asked, and it must first decide whether a phone call is warranted at all. Triages the claim, answers provisionally, and gates the fact behind one disclosed CALL-E call to the party whose word is binding. When the decision to call has already been made, use verify-by-phone instead.116
- 877Hifi Hotel NegotiatorCALLE-AI/awesome-phone-call-agentsAutonomous voice AI agent skill for hotel procurement, direct-booking rate negotiation, and reservation confirmation over the phone using CALL-E.116
- 878Manage Skillsumutbozdag/agent-skills-managerDiscover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)44
- 879Outcome Completion AgentCALLE-AI/awesome-phone-call-agentsOwn one goal across as many CALL-E calls as it takes, when who to call next depends on what the last call said — read every call as structured evidence, reject offers that break the user's stated limits, follow referrals to parties the user never supplied, and gate the single call that commits the user.116
- 880QuotehunterCALLE-AI/awesome-phone-call-agentsAutonomous voice AI agent skill that dispatches parallel phone calls to local service providers via CALL-E, negotiates competitive trade quotes, extracts structured pricing and availability schemas, and generates comparison dossiers for human closing.116
- 881Servexa Phone Call AgentsCALLE-AI/awesome-phone-call-agentsUse when working on SERVEXA phone-call workflows, CALL-E integration, customer-care call prompts, human-directed call templates, structured call outcomes, transcripts, webhook persistence, follow-ups, or call-report review. Covers the repository's implemented flow and its safety boundaries.116
- 882Supply Chain Supplier StatusCALLE-AI/awesome-phone-call-agentsOutbound phone agent powered by CALL-E that calls suppliers to check fulfillment status on purchase orders, negotiates revised dates, captures delay root causes, and generates structured procurement intelligence.116
- 883A2a ProtocolTerminalSkills/skillsBuilds Agent2Agent (A2A) servers and clients, the open protocol (originally from Google, now under the Linux Foundation) that lets AI agents from different frameworks call each other. Use when the user wants to create an A2A-compliant agent, build an Agent Card, implement task management, connect agents across frameworks, set up agent discovery, handle streaming responses, implement push notifications, or orchestrate multi-agent workflows. Trigger words: a2a, agent to agent, agent2agent, a2a protocol, a2a server, a2a client, agent card, agent interoperability, agent collaboration, multi-agent,213
- 884Add AgentBerriAI/litellm-skillsCreate a new AI agent on a live LiteLLM proxy. Asks for agent name, the underlying model, and optional MCP server access, then calls POST /v1/agents.109
- 885Add MCPBerriAI/litellm-skillsRegister a new MCP server on a live LiteLLM proxy. Asks for the server name, transport type, URL, and optional auth, then calls POST /v1/mcp/server.109
- 886Add ModelBerriAI/litellm-skillsAdd a new model to a live LiteLLM proxy. Walks the user through picking a provider, entering the deployment name and credentials, calls POST /model/new, then test-calls the model to confirm it routes correctly. Use when the user wants to add, register, deploy, or configure a new model on a LiteLLM proxy instance.109
- 887Add TeamBerriAI/litellm-skillsCreate a new team on a live LiteLLM proxy. Asks for team name, budget, and allowed models, then calls POST /team/new and shows the result. Use when the user wants to create a new team, set up team budgets, or configure model access for a team on the proxy.109
- 888Ag2TerminalSkills/skillsAG2 (formerly AutoGen) is an open-source Python framework for building AI agents and multi-agent systems that use tools, human approval and structured conversations. Use it when you need agents that call functions, collaborate in a group chat, execute code, or when you are migrating AutoGen or pyautogen code to AG2 v1 or ag2-classic.213
- 889Agent SandboxTerminalSkills/skillsRun AI agent code safely in isolated sandboxes with resource limits, audit trails, and kill switches. Use when someone asks to "sandbox my agent", "run agent code safely", "add guardrails to AI agent", "isolate agent execution", "audit agent actions", "prevent agent from deleting files", "restrict agent permissions", or "add safety controls to AI coding agent". Covers Docker isolation, filesystem restrictions, network policies, resource locking, and comprehensive audit logging.213
- 890Agent Swarm OrchestrationTerminalSkills/skillsCoordinate multiple AI agents working together on complex tasks — routing, handoffs, consensus, memory sharing, and quality gates. Use when tasks involve building multi-agent systems, coordinating specialist agents in a pipeline, implementing agent-to-agent communication, designing swarm architectures, setting up agent orchestration frameworks, or building autonomous agent teams with supervision and quality control. Covers hierarchical, mesh, and pipeline topologies.213
- 891Agent Workflow PackagerTerminalSkills/skillsTurns a workflow a team keeps repeating with a coding agent (a pasted prompt, runbook, review checklist or AGENTS.md section) into a spec-valid Agent Skill folder with SKILL.md, triggers, approval gates and a done check. Use when asked to "turn this into a skill", "package our release checklist as a skill" or "convert this runbook to SKILL.md".213
- 892AgentscopeTerminalSkills/skillsBuild and trace AI agents in Python with AgentScope, an open-source agent framework with a ReAct loop, tools, middleware, team pipelines and OpenTelemetry tracing. Use when building production agents that need observability, debugging an agent's model and tool calls, capping token spend per reply, or coordinating a leader with specialist agents.213
- 893AI Eval CITerminalSkills/skillsRun AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions integration.213
- 894AI GuardrailsTerminalSkills/skillsAdds safety guardrails to LLM applications in Python: prompt injection checks, a canary token for system-prompt leaks, OpenAI moderation, PII redaction, Pydantic output validation, rate and token limits, and grounding checks for RAG answers. Use when adding safety layers to a chatbot, detecting prompt injection, filtering harmful content, validating LLM output against a schema, or building a moderation pipeline.213
- 895AI ScientistTerminalSkills/skillsThe AI Scientist-v2 is Sakana AI's open-source research agent that turns a topic description into research ideas, runs machine-learning experiments with an agentic tree search, and writes a LaTeX paper with citations. Use when someone wants to automate ML research, generate and test hypotheses, run "AI Scientist" or "AI-Scientist-v2", or study automated scientific discovery.213
- 896AI SDKTerminalSkills/skillsThe Vercel AI SDK is a TypeScript toolkit for calling LLMs from Node.js, Next.js, Nuxt, SvelteKit and edge runtimes through one API. It covers text generation, streaming, structured output with Zod, tool calling, agents (ToolLoopAgent) and chat UIs with useChat. Use when asked to "add AI to my Next.js app", "stream a chat response", "get typed JSON from an LLM", "switch between OpenAI, Anthropic and Gemini", or "build a tool-calling agent".213
- 897AiderTerminalSkills/skillsAider is an open-source terminal AI pair programmer that edits files in your git repository with an LLM and commits each change. Use when a user asks to run Aider, let an AI refactor or fix code from the command line, script Aider with --message, auto-run lint and tests after edits, or point Aider at Claude, GPT, Gemini, DeepSeek or a local model.213
- 898AirllmTerminalSkills/skillsAirLLM runs very large open language models on a small GPU (or a CPU) by loading the model one layer at a time from disk instead of holding it all in memory, at the price of slow generation. Use when the user wants to run a 70B or larger Hugging Face model locally with 4-12 GB of VRAM, asks how to fit a model that does not fit in GPU memory, or says "airllm", "layer-by-layer inference", "run Llama 70B on a small GPU", "offline batch answers from a big model".213
- 899Anthropic SDKTerminalSkills/skillsThe Anthropic SDK (Python `anthropic`, TypeScript `@anthropic-ai/sdk`) calls Claude models through the Messages API. Use when a user asks to add Claude to an app, build a chatbot, stream Claude responses, give Claude tools (function calling), send images or PDFs, turn on adaptive thinking, count tokens, or pick a current Claude model id. Covers client setup, streaming, tool use, vision, thinking and effort, and current model ids and breaking changes.213
- 900Anthropics Official PackPeiiii/skildAll official Claude skills from anthropics/skills.117
- 901Anything LLMTerminalSkills/skillsAll-in-one private AI app that chats with your own documents in workspaces, using any local or hosted LLM, a built-in vector database and a developer REST API. Use when someone asks to "run AnythingLLM in Docker", "chat with my PDFs privately", "create a workspace and upload documents through the API", "generate an AnythingLLM API key", or "connect AnythingLLM to Ollama".213
- 902Architectural DimensionsTerminalSkills/skillsReference for architectural dimensions, proportions, and building codes for AI-generated 3D/2D models. Use when: generating floor plans, creating 3D buildings, validating architectural designs, ensuring correct human-scale proportions in models.213
- 903ArizeTerminalSkills/skillsArize is an AI observability platform, and Phoenix is its open-source tracing and evaluation tool for LLM applications. Use this skill when the user wants to trace OpenAI or LangChain calls, run a local Phoenix server, score RAG answers for faithfulness, debug slow or wrong LLM responses, or send OpenTelemetry traces to Arize for production monitoring.213
- 904AstrbotTerminalSkills/skillsAstrBot is a self-hosted AI chatbot platform that connects one LLM assistant to messaging apps such as Discord, Slack, Telegram, LINE and Mattermost, with a web panel for providers, platforms and plugins. Use this skill to install it with uv or Docker, keep the panel on localhost, set the admin password, reset it, script settings with `astrbot conf`, manage plugins, or point it at a local Ollama model. Trigger phrases: "self-hosted chatbot for Discord and Slack", "deploy AstrBot", "AstrBot dashboard password", "run an LLM bot without writing code".213
- 905BoltTerminalSkills/skillsBolt (bolt.new, by StackBlitz) is an AI app builder that turns a text prompt into a working web or mobile app, with built-in database, hosting and domains. Use when asked to prototype an app from a prompt in Bolt, write better Bolt prompts, plan with Plan Mode, spend fewer tokens, connect GitHub, Supabase, Stripe or Netlify, publish a Bolt project, or run the open-source bolt.diy instead.213
- 906BraintrustTerminalSkills/skillsBraintrust is a hosted platform for evaluating and tracing LLM applications: it runs a task over a dataset, scores the outputs, stores each run as an experiment and logs production traces. Use when a user asks to write or run a Braintrust eval, score LLM outputs with autoevals, compare prompt or model versions as experiments, run evals in CI and fail on regressions, trace OpenAI or Anthropic calls with Braintrust, manage evaluation datasets, or use the bt CLI.213
- 907Browser UseTerminalSkills/skillsBrowser Use is an open-source Python library that lets an LLM agent drive a real browser to navigate sites, fill forms, click and extract data from a plain-English task. Use when the user wants an AI agent to automate a website, scrape pages that need clicking or login, return structured data from the web, add browser tools to a coding agent, or run browser agents locally or in the cloud.213
- 908Bug Hunt SwarmTerminalSkills/skillsFinds the cause of a hard bug by running several read-only subagents in parallel, each attacking it from a different angle (change history, code path, data and state, environment, reproduction), then checking their evidence, ranking the hypotheses and naming the one experiment that would confirm the leader. It diagnoses and does not fix. Use when someone says "hunt this bug with multiple agents", "swarm on this regression", "investigate in parallel", "find the root cause", or when a failure is intermittent, crosses components, or has resisted a first look.213
- 909CerebrasTerminalSkills/skillsCerebras Inference is a hosted LLM API that runs open models on Cerebras wafer-scale chips at thousands of tokens per second, through an OpenAI-compatible endpoint. Use when a user wants the lowest-latency chat, code completion or agent loop, asks how to call the Cerebras API or SDK, needs streaming, tool calling, strict JSON schema output or reasoning control, or hits a "model not found" error from a retired Cerebras model ID.213
- 910ChromadbTerminalSkills/skillsAssists with storing, searching, and managing vector embeddings using ChromaDB. Use when building RAG pipelines, semantic search engines, or recommendation systems. Trigger words: chromadb, chroma, vector database, embeddings, semantic search, similarity search, vector store, rag.213
- 911Claude CodeTerminalSkills/skillsClaude Code is Anthropic's AI coding agent for the terminal, IDEs, desktop and web: it reads a codebase, edits files, runs commands and tests, and iterates. Use when a user asks to install or set up Claude Code, write CLAUDE.md or rules, set permissions, add MCP servers, create hooks, or run claude -p in scripts and CI.213
- 912Claude Computer UseTerminalSkills/skillsClaude computer use is an Anthropic API tool that lets Claude see a desktop through screenshots and operate it with mouse and keyboard. Use when automating GUI workflows, browser automation without CSS selectors, desktop app testing, or any task that requires seeing and interacting with a graphical interface.213