KeePassXC cursor.kdbx — natywny keyring per OS, keepass-db.path bez fallbacków, agent instaluje brakujące narzędzia.

Extract cross-session patterns from git history, PRs, and handoffs, then recommend artifacts (skill/rule/hook/agent) based on frequency thresholds. Use when consolidating recurring patterns into durable artifacts. For single-session reflection, use `reflect` instead.

Diagnoses LLM output failures including hallucinations, constraint violations, format errors, and reasoning issues. Provides root cause classification, prompt fixes, tool improvements, and new test cases. Use for "debugging AI", "fixing prompts", "quality issues", or "output errors".

Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"

Analyze messages exchanged per project across all Claude Code sessions. Generates monthly and yearly markdown reports with per-project/branch breakdowns. Use when the user asks about "message count", "messages per project", "how many messages", "message report", "logbook messages", or wants usage statistics.

Analyze time spent per project across all Claude Code sessions. Generates monthly and yearly markdown reports with per-project/branch breakdowns. Use when the user asks about "time spent", "hours per project", "session time", "time report", "logbook time", or wants to know how long they spent coding.

Use Claude's 1M-token context window effectively — when to use it, how to structure inputs for recall, how to price it, and how to combine with prompt caching to keep it affordable. Use this skill when building apps that feed large codebases, long documents, or entire conversation histories to Claude, or when weighing 1M context vs RAG. Activate when: 1M context, long context, big context window, context vs RAG, Claude 1 million tokens, context-beta header.

Use when creating, releasing, or maintaining a Claude Code Plugin Marketplace - covers marketplace.json schema, version management, release checklists, changelog conventions, and validation to prevent sync drift between plugin.json and marketplace.json

Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations

Model Context Protocol (MCP) integration specialist. Use when creating MCP server configurations, implementing MCP integrations, or optimizing MCP performance. Specializes in MCP server architecture and integration patterns.

Use MCP Resources correctly — the read-only, URI-addressable data primitive — and know when to pick resources, tools, or prompts. Covers templated URIs, subscriptions, and common mistakes. Use this skill when designing MCP servers that expose data, deciding between tool vs resource, or implementing resource subscriptions for live data. Activate when: MCP resource, resource template, resource vs tool, subscribe resource, MCP URI schema.

On-demand audit of MCP usage. Reads .aura/security/mcp-audit.jsonl, surfaces blocked calls, rate-limit hits, suspicious input patterns. Companion to mcp-call-gate hook (which produces the audit log).

Analyze session friction trends, success rates, and satisfaction patterns across sessions using Claude Code facets data. Read-only query tool for on-demand trend analysis.

Generates comprehensive code and thorough analysis using OpenAI Codex sub-agents — handles large-scale code generation, exhaustive edge case coverage, and detailed boilerplate scaffolding. Use when the user wants comprehensive output, large code generation, thorough analysis, or 'give me everything' solutions.

Use when "deploying ML models", "MLOps", "model serving", "feature stores", "model monitoring", or asking about "PyTorch deployment", "TensorFlow production", "RAG systems", "LLM integration", "ML infrastructure"

Guide to writing ai-cli mode files. Use when creating modes for non-interactive Claude Code sessions — preconfigured agent runs with locked-in system prompts, model selection, and prompt wrappers.

Fetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently displays all LLM calls.

Synthesize outputs from multiple AI models into a comprehensive, verified assessment. Use when: (1) User pastes feedback/analysis from multiple LLMs (Claude, GPT, Gemini, etc.) about code or a project, (2) User wants to consolidate model outputs into a single reliable document, (3) User needs conflicting model claims resolved against actual source code. This skill verifies model claims against the codebase, resolves contradictions with evidence, and produces a more reliable assessment than any single model.

Cross-validate decisions using multiple AI models (Codex, Gemini, Grok). Use when "get a second opinion", evaluating approaches, or high-stakes decisions.

Spawn nested sub-agents (agents that spawn sub-agents, up to depth=5) via Claude Code's native Task tool — for context-managed deep delegation

Cross-AI personal knowledge graph memory (Nowledge Mem). Stores memories from this tool, Claude Code, Cursor, browser capture, imported documents, and more. Use when: (1) the user asks about prior work, decisions, preferences, people, dates, plans, or todos, (2) the user references something discussed before or says "remind me" / "what did we decide" / "what was I working on", (3) the conversation produces a decision, preference, plan, or learning worth keeping, (4) the user wants to browse recent activity or explore how ideas connect, (5) the user asks about a past conversation or wants to find a specific thread.

Send messages, system events, and agent notifications through the openclaw CLI. Use when an agent needs to notify a user (Telegram, Slack, Discord), trigger another agent, broadcast updates, send system events, or coordinate agent-to-agent communication via swarmmail. Covers all three messaging layers - external channels, agent invocation, and internal swarmmail.

Optimize prompts for better AI performance. Use when user says "improve this prompt for better results", "optimize this prompt to reduce tokens", "apply prompt engineering best practices to this", "make this prompt more effective", "help me refine this system prompt", or "tune this prompt for the AI model I'm using".

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

This skill should be used when the user asks to "add background processing", "cache this data", "run this async", "handle concurrent requests", "manage state across requests", "process jobs from a queue", "this GenServer is slow", or mentions GenServer, Supervisor, Agent, Task, Registry, DynamicSupervisor, handle_call, handle_cast, supervision trees, fault tolerance, "let it crash", or choosing between Broadway and Oban.

This skill should be used when the user asks to "add background processing", "cache this data", "run this async", "handle concurrent requests", "manage state across requests", "process jobs from a queue", "this GenServer is slow", or mentions GenServer, Supervisor, Agent, Task, Registry, DynamicSupervisor, handle_call, handle_cast, supervision trees, fault tolerance, "let it crash", or choosing between Broadway and Oban.

Reduce CLI output noise before it reaches LLM context. Use when setting up repos, troubleshooting context overflow from build/test/git output, or when Bash tool output exceeds limits. Covers RTK (zero-config baseline) and tokf (per-project customization). Either or both may be installed — the skill adapts gracefully when one is absent.

Use when facing 2+ independent tasks that can be worked on without shared state. Dispatch one agent per problem domain for concurrent investigation.

Orchestrate parallel agent execution with git worktrees

Query pi agent session logs as JSON Lines using Nushell pipelines. Use when debugging agent sessions, analyzing tool calls, or tracking file access in session history.

Use this skill when the user asks to create, review, improve, trim, audit, or standardize an AGENTS.md file, or to derive agent instructions from a codebase. Produces compact, repo-specific, LLM-optimized AGENTS.md files and, when useful, companion authoring guidance such as AGENTS_MD_GUIDELINE.md.

Create, validate, and publish Claude Code plugins and marketplaces. Use this skill when building plugins with commands, agents, hooks, MCP servers, or skills.

Internal workflow for post-plan materialization — creates MCP items from the approved plan and dispatches implementation. Triggered automatically after plan approval when MCP tracking is active.

AI agent for Predexon Prediction Market Agent 1.5 via Teneo Protocol. Use this skill when the user needs Predexon Prediction Market Agent 1.5 via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.

AI agent for Predexon Prediction Market Trading 1.5 via Teneo Protocol. Use this skill when the user needs Predexon Prediction Market Trading 1.5 via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.

Generate AI-powered presentations locally using Presenton. Use when: (1) User asks to create a presentation or slideshow, (2) User wants to convert a document or prompt into slides, (3) User needs PPTX/PDF export with AI-generated content.

Expert prompt optimization for LLMs and AI systems. Use when building AI features, improving agent performance, crafting system prompts, or optimizing LLM interactions. Masters prompt patterns and techniques.

Display QAVR (Q-Value Augmented Vector Retrieval) system status including mode, interaction counts, top memories by Q-value, and configuration.

Run a bounded quality audit across a repo or control plane, split the scan into 3-5 evidence lanes, consolidate overlapping findings, and remediate the highest-leverage issues with one main-agent owner. Use when a user wants a broad hygiene pass, drift audit, regression triage, control-plane review, or a parallel analysis followed by direct remediation.

Build RAG systems: document chunking, embedding generation, vector storage, retrieval strategies, and answer generation.

How to use the Readwise MCP tools — access highlights, documents, and your entire reading library via MCP

# Release Claude Code Plugin

Plans resource allocation and agent assignments to tasks. Use when you need to allocate agents to tasks, balance workload, or plan resource usage. Considers task dependencies, agent capabilities, and workload distribution.

Creates minimal, effective AGENTS.md files using progressive disclosure. Triggers on "create agents.md", "refactor agents.md", "review my agents.md", "claude.md", or questions about agent configuration files. Also triggers proactively when a project is missing AGENTS.md.

Run citation-bearing deep research with deep-research-client across OpenAI, Perplexity, Edison/Falcon, Cyberian, and site-specific providers such as OpenScientist. Use when a user asks for research reports, literature reviews, source-backed synthesis, or provider/model trade-off guidance.

Use for Salesforce Agentforce work — Agents (Topics, Actions), prompt templates, Atlas reasoning engine, Trust Layer integration, agent testing.

Use for Salesforce Einstein work — Discovery, Predictions, Next Best Action, Einstein Bots (legacy → migrating to Agentforce), prompt builder, model management.

Analyzes current conversation context to recommend the best skills and subagents for the task at hand. Use proactively when unsure which tool, skill, or agent to use.

Guide to creating CLI tools and scripts that augment Claude Code. Use when building bin/ executables, automation scripts, hook handlers, or tooling that abstracts repeated agent workflows.

Manage encrypted local credentials for agent tooling with the `secrets` CLI: add, rotate, list, enable, disable, and inspect service integrations without exposing secret values in agent output.

Capture current session state and generate a handoff prompt for seamless continuation in a new session. Use when context window is filling up, before ending a long session, or when explicitly requested.

This skill should be used when the user asks to "export session log", "convert session to json", "export conversation", "save session", "sessionlog export", "export this session", or wants to export the current Claude Code session as a standard LLM conversation JSON file and human-readable TXT transcript.

Sets the local clone path of the christian289/dotnet-with-claudecode repository so the WpfDevPackMcp server can read WPF knowledge topics from disk. Use when the WpfDevPackMcp server reports the repo path is not configured, when first setting up wpf-dev-pack on a machine, or when moving the local clone. Writes ~/.wpf-dev-pack-mcp/config.json.

Guides users through setting up the ClickHouse MCP server connection bundled with this plugin. Use when the user first installs the plugin or has trouble connecting to ClickHouse.

Use when setting up context management for Claude Code - configures conversation search, context summarization, session export, and project memory patterns for long-running development

Guide for setup Serena MCP server for semantic code retrieval and editing capabilities

Decide when Zoom MCP is the right fit and produce a safe setup plan for Claude. Use when planning AI workflows over Zoom data, deciding between MCP and REST, or defining a hybrid MCP architecture.

Guide the user through creating a new Claude Code skill — SKILL.md format, frontmatter, progressive disclosure, when to use reference files, common pitfalls.

6-phase interactive interview that generates the agent's identity (SOUL.md), user profile (USER.md), access control (ACCESS_POLICY.md), and operational cadence (HEARTBEAT.md). Re-runnable anytime to update any section.

Use when facing 2+ independent problems (different test files, unrelated bugs, separate subsystems) that can be investigated in parallel without shared state — covers the dispatch decision, the actual Claude Code parallelism mechanism, prompt construction, and integration after agents return

Use when saving workflow state to Serena MCP memory at research, planning, execution, or completion stages - enables resuming work later with /cc:resume command

Delegate work to sub-agents via the Task/Agent tool — parallel research, isolated context windows, specialized expertise. Covers when sub-agents help vs hurt, prompt shape, and result handling. Use this skill when building agents that need to research in parallel, process independent work items, or isolate context-heavy sub-tasks. Activate when: sub-agents, Task tool, Agent tool, parallel agents, agent delegation, spawn agent, multi-agent.

Orchestrate parallel agent teams using Claude Code's experimental Agent Teams feature

Pull today's OpenClaw session activity into the current daily note. Use when the user asks to "sync today", "pull in today's activity", "sync openclaw", or wants to enrich the daily note with Telegram/agent session context.

Use BEFORE delegating any complex task to a subagent. Contains the routing table that maps task patterns to the correct specialized agent. MUST be consulted before using the Task tool for delegation decisions. Trigger keywords - "delegate", "subagent", "agent", "research", "implement", "investigate", "debug", "architect".

Current Ethereum development tools, frameworks, libraries, RPCs, and block explorers. What actually works today for building on Ethereum. Includes tool discovery for AI agents — MCPs, abi.ninja, Foundry, Scaffold-ETH 2, Hardhat, and more. Use when setting up a dev environment, choosing tools, or when an agent needs to discover what's available.

Ultimate Bug Scanner - Pre-commit static analysis for AI coding workflows. 18 detection categories, 8 languages, 4-layer analysis engine. The AI agent's quality gate.

AI-powered blockchain monitoring agent with real-time monitoring of Uniswap V2, V3, and V4 most known pools. Track swaps, monitor specific liquidity pools by address, and receive intelligent insights

Agent Teams delegate mode with Command-as-Active-Lead monitoring loop -- TeammateIdle routes tasks, TaskCompleted validates and advances state, commands create dynamic tasks via signal flags

Scaffold a new Claude Workflow script — deterministic multi-agent orchestration. Triggers: "build a workflow", "create a workflow", "scaffold workflow", "author a workflow".

Author a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/*.js orchestration script (agent/parallel/pipeline fan-out)

Enhance a plan with dynamic skill/agent discovery and targeted research

# QA Validation Agent

Control Adobe Audition from the shell via Flue - ExtendScript bridges without an MCP server.

Control Autodesk desktop apps - 3ds Max and friends - from the shell via Flue, without an MCP server.

This skill should be used when the user asks to "buy NFT", "purchase NFT", "OpenSea", "NFT collection", "view my NFTs", "NFT holdings", "mint NFT", "NFT listings", or any NFT-related operation. Provides guidance on browsing, purchasing, and managing NFTs.

This skill should be used when the user asks about "my balance", "portfolio", "token holdings", "check balance", "how much do I have", "wallet balance", "what tokens do I own", "show my holdings", or any balance/portfolio query. Provides guidance on checking balances across chains.

Control Blender from the shell via Flue - a Python bridge to bpy without an MCP server.

This skill should be used when the user asks to "send a Discord notification", "notify Discord", "post to Discord", "send a message to Discord webhook", "alert Discord channel", or when another agent, hook, or skill needs to deliver a notification to a Discord channel via webhook. Provides the complete workflow for reading webhook configuration, formatting messages (plain text or Embed), and sending via HTTP POST.

Control SideFX Houdini from the shell via Flue - a Python bridge to hou without an MCP server.

Control Adobe Illustrator from the shell via Flue - ExtendScript bridges without an MCP server.

Control Adobe InDesign from the shell via Flue - ExtendScript bridges without an MCP server.

Control Adobe Photoshop from the shell via Flue - ExtendScript bridges without an MCP server.

Control Adobe Premiere Pro from the shell via Flue - ExtendScript bridges without an MCP server.

AI agent for Aave V3 Liquidation Watcher via Teneo Protocol. Use this skill when the user needs Aave V3 Liquidation Watcher via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.

Build or rebuild the ADR index + dependency graph by running scripts/import.mjs (handles v3-style and plugin-style ADR formats; one Bash call vs hundreds of MCP round-trips)

Audit installed Bankr skills before you run them — scan SKILL.md and companion scripts for shell injection, secret exfiltration, path traversal, prompt-override payloads, destructive commands, and 2026-era obfuscation (zero-width Unicode, bidi override, base64-decode pipes, webhook SSRF hosts). Designed to integrate with Bankr Safety Scores. Silent on no-op runs; surfaces only NEW or RESOLVED findings vs prior scans. Triggers: "audit this skill", "is this skill safe to install", "security scan my skills", "check skill X for injection".

Curated bundle for building, testing, and coordinating AI agent systems. Includes multi-agent orchestration, agent testing, cross-agent handoff, MCP server building, and prompt engineering. Use when developing AI agent workflows or multi-agent systems.

The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.

Persist and retrieve repository-specific knowledge using AGENTS.md files. Use when you want to save important information about a codebase (build commands, code style, workflows) for future sessions.

Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model evaluations.

Search, list, and resume AI agent sessions across Claude Code, Codex CLI, and Gemini CLI. Use when the user asks to find a past conversation, search session history, resume a previous session, list recent agent activity, or check what was discussed in a prior session. Also use when asked to "find that conversation where I...", "resume my last codex session", "what did I work on yesterday", or "search my claude history for X".

Team composition knowledge for Claude Code Agent Teams - when to suggest teams, optimal sizing, spawn prompt patterns

Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 230 rules.

Intelligent auto-continuation skill for Claude Code sessions. Use when working on extended tasks requiring minimal interruption, continuous development workflows, or Ralph Loop style iterations.