Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with any LLM.

judge

Blind evaluation pattern. Agent spawns an independent judge to evaluate an idea, plan, strategy, statement, or implementation. The judge sees the repo but not the conversation. Verdict goes to a shared markdown file.

Survey Mcp Server

MCP server for conducting dynamic, conversational surveys with structured data collection.

Io.Github.TonySimonovsky/Claude Code Conversation Search Mcp

Search Claude Code conversation history with natural language queries across all projects

resume-builder

Generate professional resumes that conform to the Reactive Resume schema. Use when the user wants to create, build, or generate a resume through conversational AI, or asks about resume structure, sections, or content. This skill guides the agent to ask clarifying questions, avoid hallucination, and produce valid JSON output for https://rxresu.me.

mengram-memory

Long-term memory with 3 types (facts, events, workflows). Remember user preferences, past conversations, and learned procedures across sessions. Use when recalling what the user said before, saving important info, getting user context, or tracking completed workflows.

cashew

Persistent thought-graph memory for OpenClaw agents. Query context before answering substantive questions, extract knowledge during conversations, run think/sleep cycles for consolidation. Triggers on session start, knowledge-worthy conversations, heartbeats, and any question about prior context.

AI Brain Starter — Interactive Setup

You are setting up a new user's AI-powered second brain. This is an interactive, conversational setup, not a script dump. Go step by step, wait for their answers, and adapt to what they have.

Bootstrap — Personalized Onboarding

A conversational onboarding skill. Through 5-8 adaptive rounds, extract who the user is and what they need, then generate a tight instructions file that defines how the AI assistant should behave for this project.

architecture-refiner

Facilitate a structured conversation to define architecture principles for a repository. Supports multiple architecture styles: clean architecture (default), hexagonal / ports & adapters, modular monolith, or custom. Produces a formal architecture document that the corresponding atom will use. Use when setting up a new project, defining architecture standards, or when the user says 'setup architecture', 'define layers', 'architecture principles', 'help me define my architecture', 'hexagonal architecture', 'modular monolith', 'ports and adapters', or 'define my architecture style'.

elevenlabs:sdk-migration

Migrate to the next major version of @elevenlabs/client, @elevenlabs/react, and @elevenlabs/react-native. Use when updating code that uses Conversation, Input, Output, useConversation, ElevenLabsProvider, ConversationProvider, or related APIs from these packages. Also trigger when users mention upgrading ElevenLabs packages, fixing breaking changes after an npm update, moving to the latest ElevenLabs SDK, or encountering type errors or runtime errors after updating @elevenlabs/* dependencies.

gcal-api-research

Expert research tool for Google Calendar API implementations. PROACTIVELY use when (1) reviewing PRs adding calendar features, (2) planning new event/attendee/recurring event functionality, (3) investigating calendar API issues, (4) validating timezone handling or batch operations. Specializes in recurring events, timezone conversions, multi-calendar support, and edge case identification.

sinch-authentication

Configures Sinch API credentials and authentication. Use when setting up OAuth2, Basic auth, application signing, API keys, or SDK credentials for any Sinch product including Conversation API, Voice, Verification, Numbers, Fax, and Mailgun. Also use when troubleshooting 401 Unauthorized, 403 Forbidden, invalid signature, or credential errors against any Sinch API.

Adam Framework

Persistent memory tools for Claude Desktop. Search your vault or Obsidian notes mid-conversation.

gh-issue-bug

Generate a structured bug report for GitHub issues based on conversation context about bugs, errors, or broken functionality

Obris

Stop re-explaining yourself to AI. Save knowledge once, use it in every conversation.

Bbox Mcp Server

Bounding box(bbox) GIS tool: coords conversion, EPSG, WKT, GeoJSON, H3, Overpass, POI, map viz

update-hwpx-differences

Updates the HWPX-Markdown differences documentation when a new conversion issue is found or a new handling method is implemented. Use this skill when fixing HWPX parsing issues, adding new format handling, or discovering incompatibilities between HWPX and Markdown.

Conversation JSON 转 Markdown（中文）

将用户提供的聊天导出 JSON 转换为多个 Markdown 文件，并统一为问答结构。

claude-memory

Access the persistent memory database (PostgreSQL `claude_memory`) for long-term context across Claude Code sessions. Triggers on "what do I know about", "memory lookup", "recall", "memory db", "what did we decide about", "similar conversations", "lookup context", "/memory". Provides semantic search, SQL queries and the ability to add new insights.

forge-onboard

Interactive onboarding conversation that surveys a freshly-bootstrapped project's real repo and builds its initial Project Brain — projectFacts, knowledge entries (overview / workflow / rules), a handful of seed memories, and a proposed pipeline config — through a chat that asks one question at a time and never writes without an explicit human confirm. Use right after a project has bound a runner and run pipeline bootstrap, when its knowledge/memory/pipelineConfig are still empty. Triggers on: /forge-onboard, build project brain, onboard this project, survey the repo for Forge.

tsk-add

Queue a single task based on the current conversation using tsk add

strava-sync

Downloads and syncs training data from Strava using the Strava MCP server. This is ONE option for importing training data - athletes can also use manual logs, other platforms (Garmin, Apple Health), or provide data conversationally. Use this skill specifically when the athlete wants to sync from Strava or when the running-coach indicates Strava as the chosen data source. Stores activities in the training-log folder as markdown summaries, including lap details for workout runs.

agtx

Use when planning features, decomposing work into tasks, creating or managing tasks on a kanban board, coordinating parallel coding agent sessions across git worktrees, or when the user wants to sweep/push conversation results to the agtx board. Also use when asked about agtx setup, MCP configuration, or task workflow.

ads-creative-development

How to produce ad creative that converts at performance scale. Hook patterns, format selection, video pacing, variation systems, sequential testing methodology, fatigue detection, brand-voice alignment without conversion dilution, and platform-specific creative norms. Triggers on ad creative, ad design, hook patterns, ad video pacing, creative testing, ad variations, creative refresh, creative fatigue, refresh ad creative, video ads for Meta, TikTok creative, LinkedIn ad creative, ad asset library. Also triggers when a team is producing creative at scale, planning a creative test cycle, or auditing why creative is not converting.

Mcp Units

An MCP server that provides some common units conversions for cooking

beeper

Search and read messages from Beeper Desktop API (WhatsApp, Signal, Telegram, etc.). Triggers: "check my messages", "search messages", "who messaged me", "find conversations", "unread messages", "beeper", "chat history".

chat-history

Search, inspect, and export Claude Code and Cursor conversation history. Use when the user asks about past conversations, wants to find a previous session, needs to search chat history, wants a summary of what they worked on, or asks to resume a session. Also use when the user says "what did I work on", "find that conversation where I...", "show me my recent sessions", or "search my history for...".

context-monitor

Monitor conversation context and prevent MAX mode by warning at token thresholds and generating handoff summaries. Use when context approaches 100K/150K/180K tokens or when working with high-cost files.

add-domain

Add a new knowledge domain to your existing system. Derives domain-specific configuration through conversation, generates domain folders, templates, and vocabulary while preserving and connecting to your existing architecture.

codoc:share

Share a file for collaborative editing with a human via browser. Use when the user wants to collaboratively edit a markdown file, get feedback, or have a conversation within a document.

ab-test-store-listing

When the user wants to A/B test App Store product page elements to improve conversion rate. Also use when the user mentions "A/B test", "product page optimization", "test my screenshots", "test my icon", "conversion rate optimization", "CPP", or "custom product pages". For screenshot design, see screenshot-optimization. For metadata optimization, see metadata-optimization.

conversation-log

Technical conversation log with factual accuracy and precision tailored specifically for DEVELOPER and ENGINEER profiles. Provides systematic guidance for capturing decisions, outcomes, and next steps. Use when user asks to create technical conversation logs for reviews, architecture discussions, or implementation sessions.

agents

Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience.

Anki Mcp

MCP server for integrating with Anki flashcards through conversational AI

design-dialogue

Guides structured design conversations for complex engineering tasks

Io.Github.Huoshuiai42/Huoshui Pdf Converter

An MCP server that provides PDF file conversion

Mcp

Build and publish websites through AI conversation.

building-streamlit-chat-ui

Building chat interfaces in Streamlit. Use when creating conversational UIs, chatbots, or AI assistants. Covers st.chat_message, st.chat_input, message history, and streaming responses.

agent-estimation

Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead of human time. Use when asked to estimate, scope, plan, or evaluate how long a coding task will take. Prevents the common failure mode where agents anchor to human developer timelines and massively overestimate. Outputs a structured breakdown with round counts, risk factors, and a final wallclock conversion.

claude-agent-sdk-python

Build and test Python applications using the Claude Agent SDK. Use when creating agent applications, custom MCP tools, permission handlers, lifecycle hooks, or multi-turn conversations. Covers query(), ClaudeSDKClient, @tool decorator, create_sdk_mcp_server(), hooks, permissions, and independent app testing patterns.

Antigravity CLI (`agy`)

Google's agentic coding CLI. Runs Gemini 3 (Pro/Flash) by default, with internal access to Claude Sonnet/Opus 4.5/4.6 and GPT-OSS models. Pairs a chat REPL with planning, scheduling, and autonomous "goal" workflows that write `implementation_plan.md` + `task.md` to a per-conversation brain directory

background-watch-hook

Use `vibe watch` to run a background waiter that returns to the same conversation later. Best for reviews, CI, files, logs, and other wait-now-continue-later workflows.

sidecar

Spawn conversations with other LLMs (Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Qwen, Grok, Mistral, etc.) and fold results back into your context. TRIGGER when: user asks to talk to, chat with, use, call, or spawn another LLM or model; user mentions Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Claude (as a sidecar target), Qwen, Grok, Mistral, or any non-current model by name; user asks to get a second opinion from another model; user wants parallel exploration with a different model; user says "sidecar", "fork", or "fold". CRITICAL RULES: (1) ALWAYS launch sidecar CLI commands with Bash tool's run_in_background: true. Never run sidecar start/resume/continue in the foreground. (2) The fold summary returns on stdout when the user clicks Fold in the GUI or the headless agent finishes. Use TaskOutput to read it when the background task completes. (3) Use --prompt for the start command (NOT --briefing). --briefing is only for subagent spawn. (4) NEVER use o3 or o3-pro unless the user explicitly asks for it by name. These models are extremely expensive ($10-60+ per request). If the user asks for o3, warn them about the cost before proceeding. Default to gemini for most tasks. (5) When the user asks to query MULTIPLE LLMs simultaneously (e.g., "ask Gemini AND ChatGPT", "compare Gemini vs GPT"), ALWAYS use --no-ui (headless) for all of them unless the user explicitly requests interactive. Opening multiple Electron windows at once is disruptive. Launch them all in parallel with run_in_background: true.

ChartPane

Renders interactive Chart.js charts and dashboards inline in AI conversations.

ab-test-generator

Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version is better", "optimize conversions", "test my email subject line", "compare approaches".

migrate-to-vinext

Migrates Next.js projects to vinext (Vite-based Next.js reimplementation). Load when asked to migrate, convert, or switch from Next.js to vinext. Handles compatibility scanning, package replacement, Vite config generation, ESM conversion, and deployment setup (Cloudflare Workers natively, other platforms via Nitro).

analytics-setup

When the user needs to set up product analytics, event tracking, or says 'set up analytics,' 'add tracking,' 'GA4,' 'Mixpanel,' 'PostHog,' 'Amplitude,' 'what events should we track,' 'conversion tracking,' 'funnel tracking,' or is launching a product and needs to instrument it for data collection.

moltnet

Use Moltnet through the local moltnet CLI. Read conversation context before speaking and send only when you choose to.

Eval: speckit-extension

The regression net for the `speckit-extension` (the spec-kit-side half of SpecKit Companion). It verifies the assumptions behind each feature against a **real spec the user created**, combining a deterministic file checker with a conversational cross-check of what the user actually did this session.