agent-skills

The ultimate network troubleshooting skill — a CCIE/RHCE-level reference and decision engine for diagnosing ANY network, connectivity, bandwidth, latency, DNS, TLS, or security problem. Covers packet-level sensors (NetWatch, RustNet, tshark, ngrep, Pktmon), all capture architectures (SPAN/RSPAN/ERSPAN, transparent Linux bridge, L3 gateway, host-based, one-armed SPAN), Windows AND Linux sensor builds, and Cisco native telemetry (SNMP/NETCONF/gNMI/CLI/pyATS). Includes a decision framework that picks the best tool + architecture per symptom, multi-platform command references, and 20+ worked incident scenarios with implementation details, commands, and scripts. Use whenever something is slow, down, dropping, flapping, unreachable, mis-behaving on the wire, or you need to plan/scale a monitoring sensor fleet.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Create AiderDesk agent profiles via interactive Q&A.

Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values

Comprehensive Agentspan durable workflow orchestration skill for creating, running, scheduling, monitoring, and debugging AI agent workflows using the Agentspan Python SDK and CLI. Covers agents, tools, multi-agent strategies, guardrails, memory, streaming, human-in-the-loop, testing, and production deployment.

Submit software to antivirus vendors to prevent false positive detections. Use when releasing new software that triggers AV warnings, submitting binaries for whitelisting, or checking VirusTotal detection status.

AI browser automation agent — navigate websites, fill forms, extract data, click elements, search the web, take screenshots, download files, and automate any browser task using natural language. Uses anthropic/claude-sonnet-4.6 via OpenRouter with Playwright Chromium. Use when asked to browse websites, scrape data, fill web forms, automate repetitive browser tasks, search and extract information from web pages, or interact with any web application programmatically.

Enterprise-grade autonomous penetration testing framework for comprehensive web application and API security assessment using CLI tools, specializing in authorization bypass, injection attacks, business logic flaws, and security reporting

Enterprise-grade penetration testing framework using curl + mitmproxy + playwright + python stack for comprehensive web application and API security assessment with traffic interception, browser automation, automated exploitation, WAF bypass, CVSS scoring, and compliance reporting

Comprehensive Cisco Catalyst 8000 SD-WAN engineering skill. Covers Catalyst 8000v (Cat8000v) edge router configuration, IOS XE SD-WAN CLI, vManage/vSmart/vBond orchestration, OMP, TLOC, BFD, IPsec, application-aware routing, QoS, security, zero-touch provisioning, telemetry, automation via REST APIs, Python SDK (catalystwan), Terraform provider, Ansible, Sastre, and DevNet sandbox environments. Use when configuring, troubleshooting, or designing Cisco Catalyst SD-WAN networks.

Comprehensive Cisco IOS XR network engineering skill. Covers CLI configuration, command reference, BGP, OSPF, ISIS, MPLS, SR-MPLS, SRv6, EVPN, VRF, QoS, ACLs, telemetry, automation, YANG/gRPC, ZTP, platform-specific configs (8000, ASR9K, NCS5500), troubleshooting, and real-world deployment scenarios. Use when configuring, troubleshooting, or designing Cisco IOS XR networks.

Sign Windows executables (.exe, .dll, .msi) and macOS applications (.app) with code signing certificates. Use when signing binaries for distribution, setting up code signing workflows, or verifying signatures.

Comprehensive Dagu workflow orchestration skill for creating, managing, and automating workflows with Dagu - a compact portable workflow engine. Covers all step types, scheduling patterns, error handling, and deployment strategies.

Elite data analyst with advanced statistical expertise for comprehensive data quality assessment, exploratory analysis, hypothesis testing, time series forecasting, clustering, causal inference, and business intelligence across finance, healthcare, retail, marketing, and operations domains

Universal database CLI supporting 30+ databases (SQLite, PostgreSQL, MySQL, SQL Server, Oracle, MongoDB, ClickHouse, DuckDB and more). Execute SELECT/DDL/DML, list tables, export schema, backup/restore tables, and run parameterized SQL. Use when the user asks to query, inspect, or modify a database, run SQL, list tables/columns, export data, or compare query results. Sub-skills: dbcli-query, dbcli-tables, dbcli-exec, dbcli-db-ddl, dbcli-export, dbcli-export-schema, dbcli-compare, dbcli-view, dbcli-index, dbcli-procedure, dbcli-interactive.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Helps 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.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Plays Gandalf, a Capture The Flag prompt security game by Lakera. Extracts guarded secret passwords from AI defenders across 8 levels of increasing difficulty. Competes on a public agent leaderboard. Triggers: "play Gandalf", "play CTF", "play the password game", "prompt challenge", "agent CTF", "test prompt hacking skills".

GOAD (Game of Active Directory) lab environment — AWS-based Active Directory pentest lab with 1 Ubuntu jumpbox and 5 Windows Server VMs (2 forests, 3 domains). Provides SSH/WinRM access, Ansible playbooks, server configs, and credentials for AD security testing, lateral movement practice, and Kerberos attacks.

Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.

CLI email client for IMAP and SMTP. Use when reading, searching, composing, sending, or managing email via terminal. Covers account setup, envelope listing, message reading, sending raw RFC 5322 messages, folder management, attachments, flags, and multi-account configuration.

Control interactive terminal applications like vim, git rebase -i, git add -i, git add -p, apt, rclone config, sudo, w3m, and TUI apps. Can also supervise another CLI LLM (cursor-agent, codex, etc.) - approve or reject its actions by pressing y/n at confirmation prompts. Use when you need to interact with applications that require keyboard input, show prompts, menus, or have full-screen interfaces. Also use when commands fail or hang with errors like "Input is not a terminal" or "Output is not a terminal". Better than application specific hacks such as GIT_SEQUENCE_EDITOR or bypassing interactivity through file use.

Comprehensive toolkit for AI agents to read, analyze, and extract information from large files without overflowing context windows. Use when working with files too large to read entirely, analyzing codebases, extracting specific sections from logs, processing large datasets, or when semantic search is needed. Covers chunked reading, semantic grep, structured extraction, and intelligent file navigation strategies.

Run any task iteratively until completion using Ralph Wiggum methodology. Executes tasks in a persistent loop where the AI receives the same prompt repeatedly, seeing its previous work in files and git history, enabling self-correction and incremental progress until a completion signal is detected. Use when tasks require multiple iterations, complex multi-step work that benefits from self-correction, tasks with verifiable success criteria (tests, builds, linters), long-running autonomous work, or iterative refinement tasks like getting tests to pass.

Nylas CLI for unified email, calendar, and contacts via IMAP/SMTP, Google, and Microsoft 365. Use when reading, searching, composing, sending, or managing email from terminal, scheduling calendar events, managing contacts, extracting OTP codes, running MCP server for AI agents, or using the interactive TUI.

Remote system administration and shell execution through the OpenCode AI Server REST API for Windows, macOS, and Linux systems with full shell access, file operations, and process management

Comprehensive OpenCode documentation covering installation, configuration, providers, tools, agents, MCP servers, skills, plugins, SDK, and all features. Use this skill when you need to understand how to use, configure, or extend OpenCode.

Use the `orca` CLI to drive a running Orca editor — manage Orca worktrees; create, read, and run shell commands in Orca-managed terminals; and automate Orca's built-in browser (snapshot/click/fill/screenshot/tabs). Use this instead of raw `git worktree`, ad hoc shell PTYs, or Playwright whenever the task touches Orca state. Coding agents inside an Orca worktree should also use it to keep the worktree comment fresh at meaningful checkpoints. Boundary with `orchestration`: if the recipient of a terminal write is another AI agent (Claude Code, Gemini, Codex, a worker), use `orchestration` — it is the only correct way to send messages, nudges, replies, or task hand-offs to agents. orca-cli writes are for non-agent terminals (shells, build/test commands); reading or `wait`ing on any terminal — including agent terminals — stays in orca-cli.

Use `orca orchestration` when coordinating multiple AI agents through Orca: pass context, instructions, questions, findings, reviews, handoffs, or structured results between agents; delegate subtasks; dispatch work; track task DAGs; wait for worker_done/escalation; or run coordinator loops and decision gates. This is the right skill for semantic agent-to-agent communication. Boundary with `orca-cli`: do not use orchestration for ordinary terminal control, shell commands, browser automation, worktree management, or reading/waiting on terminals; use `orca-cli` for those. Triggers include "tell the other agent", "ask <agent>", "hand off to", "pass this to <agent>", "delegate to <agent>", "have <agent> do X", "let <agent> know", "share with the other AI", "coordinate agents", "what did <agent> find", "check orchestration inbox", "reply to <agent>", "dispatch task", "orchestrate agents", "multi-agent", "task DAG", "worker_done", "escalation", "decision gate", and "coordinator loop".

Comprehensive PaddleOCR document intelligence skill covering OCR text extraction, table detection and QA, layout analysis, document-level reasoning, structured extraction (forms, invoices, IDs, receipts), seal/stamp recognition, handwriting, formulas, multilingual OCR, and PaddleOCR-VL multimodal tasks. Use when extracting text from images or PDFs, parsing tables, understanding document structure, extracting key-value pairs, running document QA, processing financial documents, or doing any image-to-structured-data task.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Enterprise-grade Windows remote management skill using PyWinRM for connecting to any Windows server with WinRM enabled. Provides advanced system administration, monitoring, Active Directory management, and automation capabilities.

Comprehensive ReactorPro documentation covering installation, features, agent mode, configuration, skills, MCP servers, and all capabilities. Use this skill when answering questions about ReactorPro features, configuration, troubleshooting, or best practices.

Enterprise-grade Robotic Process Automation framework for web automation without APIs - a UiPath alternative using Playwright, Python, mitmproxy, and open-source RPA tools for browser automation, data extraction, form filling, workflow orchestration, scheduled task execution, desktop automation, document processing, and enterprise observability

Comprehensive secure code analysis and vulnerability review using Semgrep, Gitleaks, Trivy, CodeQL, and Horusec in a layered defense approach. Covers secret detection, pattern-based SAST, dependency CVEs, IaC misconfigs, container scanning, deep taint analysis, and multi-engine sweeps. Use when performing security scans, vulnerability assessments, code security reviews, secret detection, dependency audits, or CI/CD security gate setup.