DrOlu

@drolu source repo

85 skills
0 followers
8 hours ago last updated

▌
Hyperframes · drolu bundle
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill.

0
installs
▌
Creatorskill · drolu
Create or update Pi prompt templates and Agent skills from a short user brief. Produces minimal, well-structured SKILL.md or prompt files that follow Agent Skills best practices.

0
installs
▌
DOCX · drolu bundle
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

0
installs
▌
Excel · drolu bundle
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

0
installs
▌
Supacode CLI · drolu
Control Supacode from the terminal. Use when running Supacode CLI commands, managing worktrees, tabs, and surfaces programmatically, or when inside a Supacode terminal session.

0
installs
▌
Doc Coauthoring · drolu
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.

0
installs
▌
Web Artifacts Builder · drolu bundle
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

0
installs
▌
PDF · drolu bundle
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.

0
installs
▌
Rpa · drolu bundle
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

0
installs
▌
Goad · drolu
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.

0
installs
▌
Loop · drolu bundle
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.

0
installs
▌
Vapt · drolu bundle
Comprehensive vulnerability assessment and penetration testing skill leveraging Secator, NetExec, Metasploit, and raw Python for advanced exploitation chaining across Linux, Windows, Unix, macOS systems, network devices (switches, routers, firewalls), protocols, webapps and APIs (REST, GraphQL, gRPC). Uses OSSTMM and OWASP standards. Supports blackbox, greybox, and whitebox pentests with false-positive resistance, verified exploit confirmation, detailed step-by-step remediation, and full documentation. Use when performing security assessments, penetration tests, vulnerability scans, exploit validation, network enumeration, or security auditing.

0
installs
▌
Dbcli · drolu bundle
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.

0
installs
▌
Nylas · drolu bundle
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.

0
installs
▌
Casper · drolu bundle
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

0
installs
▌
Netops · drolu bundle
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.

0
installs
▌
Ciscoxr · drolu bundle
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.

0
installs
▌
Pywinrm · drolu bundle
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.

0
installs
▌
Synapse · drolu bundle
Complete implementation guide for Synapse protocol — build multi-agent systems on NATS using CLI or code (TypeScript, Python, Go). Covers all 6 primitives, real-world patterns, security (cryptographic ACL, NKeys, JWT), cross-org topology, and production deployment.

0
installs
▌
Hallmark · drolu bundle
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.

0
installs
▌
Himalaya · drolu bundle
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.

0
installs
▌
Neuralos · drolu bundle
Install, configure, run, administer, and manage the standalone neuralOS backend (neuralos / rterm-backend / gybackend) AND the rterm-cli command client, completely headlessly on macOS, Linux, and Windows. neuralOS is the headless AI-native backend for RTerm — the RTerm desktop app stays RTerm; neuralOS is the standalone backend daemon. Use when an agent needs to set up RTerm-as-a-service — install/update the daemon and CLI (together or individually), configure the data dir and gateway, run it as a service, manage saved connections/automation/schedules, and drive it over its WebSocket JSON-RPC gateway. Pair with the rterm-gateway skill for the RPC method reference and client examples.

0
installs
▌
Orca CLI · drolu
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.

0
installs
▌
Temporal · drolu bundle
Expert Temporal workflow specialist for creating, running, scheduling, monitoring, and debugging durable workflows using Python and uv. Covers activities, workers, signals, queries, sagas, child workflows, testing, and production deployment patterns.

0
installs
▌
Workflow · drolu
Create, run, schedule, monitor, and debug Temporal workflows using Python and uv. Expert in activities, workers, signals, queries, saga patterns, child workflows, retry policies, and CLI operations.

0
installs
▌
Agentspan · drolu bundle
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.

0
installs
▌
Casperpro · drolu bundle
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

0
installs
▌
Paddleocr · drolu bundle
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.

0
installs
▌
Rterm Ops · drolu bundle
Install, start, and fully operate neuralOS / rterm-backend (gybackend daemon) and rterm-cli from any agent harness (CyberAgent/Pi, Claude Code, Codex, OpenCode, Hermes, Cursor, …). Use when a task needs SSH, WinRM, PSRP, serial, fleet commands, playbooks, Windows/AD, Cisco, or the RTerm agent over the WebSocket gateway. Also use when rterm ping fails or neuralos is missing. Configure the daemon (model, API key, model profile, agent-settings slot, gateway access, command policy) via settings:get / settings:set.

0
installs
▌
Interminai · drolu bundle
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.

0
installs
▌
Powerpoint · drolu bundle
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

0
installs
▌
Rmagent Ao · drolu bundle
The Agent Observatory — find and trace every AI agent, agent harness and model server on a box, with zero install, from outside. The agent-plane sibling of rmagent-so. A four-probe census (process, network, filesystem, packages) discovers all agents including shadow ones the SDK vendors cannot see; per-agent questions pull config, models, recent activity from their own disk artifacts; local model servers (Ollama, LM Studio, vLLM) are queried through their own APIs. Works over SSH (Linux/macOS) and WinRM (Windows). Use when you need to know what agents are running on an estate, what they are calling, what changed, or to trace one agent's activity — the OpenLLMetry question answered by asking the box instead of embedding an SDK. Pull-based, capped, holes instead of dumps. Not a lake.

0
installs
▌
Rmagent At · drolu bundle
The App Tracing skill — resident, on-device application tracing using Windows' built-in ETW (Event Tracing for Windows). Enterprise-scale ring buffers (512 MB default, tunable) that start at boot and live in kernel memory: circular, bounded, old events overwritten — no lake, no agent install, no SDK. Captures .NET EventSource, HTTP.sys, IIS, kernel network (every TCP connection with PID), and process lifecycle (create/exit with full command line) — all providers already on every Windows box. Pull questions read the ring on demand: apptrace (events), appslow (slow requests), apperrors (errors/warnings), appnet (connections), appproc (process lifecycle). The AutoLogger setup is a MOP-level persistent change, reversible via teardown. Use for application-level observability on Windows boxes you administer, with the same pull-only, capped, holes-not-dumps constitution as the rest of the observatory.

0
installs
▌
Rmagent Fr · drolu bundle
The Flight Recorder — follow one work id (a ticket, a payment, an incident) across the estate without a span warehouse. The tracing half of the RMAgent security observatory: a Security Trace Context (STC) carries case, principal, window, depth, ticket and trigger through every hop; the trajectory records the reasoning chain as an append-only DAG; the hop index remembers whether a principal has appeared before; the causal graph computes blast radius from kilobytes; OTel spans land in Grafana/Jaeger next to application traces. Use when a payment is slow, an incident needs a timeline, or security and reliability must read the same tape. Pull-based, capped, case-filed — not a lake.

0
installs
▌
Rmagent So · drolu bundle
The Security Observatory — the witness-question half of the RMAgent security observatory. Pull-based, allowlisted named questions over WinRM :5985 tracking Administrator and SYSTEM: attest (with blind_check — can this witness actually see?), sketch, edges, explain, netedges, pslogs, kernring, attackmap, flowstats, deepwindow. Cross-witness correlation joins the answers (cross-host-account, lateral-hop, shared-logonid); baseline drift flags new admins and witness blindness as critical. Use for identity-led compromise, lateral movement, living-off-the-land, silent hosts, and honest root-cause on Windows boxes you administer. Watch-only, capped at 32 KB, holes instead of dumps — no lake, no agent install.

0
installs
▌
Browser Use · drolu bundle
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.

0
installs
▌
Find Skills · drolu
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.

0
installs
▌
Gandalf Ctf · drolu
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".

0
installs
▌
Rmagent Iso · drolu bundle
Last-resort payments wire adapter — reconstruct one STAN/RRN from passive ISO 8583 SPAN rings ONLY after rmagent-pay cannot join hop diaries. Circular decoded JSONL, not a PCAP lake. PAN masked. Hunt never runs tshark.

0
installs
▌
Rmagent Pay · drolu bundle
The payments Flight Recorder — reconstruct one ATM/POS/FEP transaction across Postilion and Finacle from each hop's own logs (STAN/RRN), without modifying the switch or CBA. Pull-based, capped, STAN/RRN-grained, holes instead of a packet lake. Use when a withdrawal is slow, a debit-without-dispense dispute needs hop localization, or channel/switch/core teams cannot agree which segment failed. Answers delay_on: finacle-posting | postilion-ingress | never-reached-core. PCI mask on the device. Demo runs on fixtures with no bank hosts.

0
installs
▌
Secure Scan · drolu bundle
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.

0
installs
▌
Agentsecrets · drolu bundle
Zero-knowledge secrets infrastructure — AI agents manage the complete credential lifecycle without ever seeing values

0
installs
▌
Catalyst8000 · drolu bundle
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.

0
installs
▌
Code Signing · drolu bundle
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.

0
installs
▌
Opencode API · drolu
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

0
installs
▌
Opencode Doc · drolu bundle
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.

0
installs
▌
Rmagent Core · drolu bundle
Shared lake-less engine for every rmagent-* skill — grain ALLOWED maps, case paths under ~/.rmagent, and the thin loader other skills import so they do not vendor a second lib.py. Not a witness. Load rmagent-so / linux / at to ask boxes.

0
installs
▌
Rterm Plugin · drolu bundle
Develop, test, and deploy custom RTerm plugins — drop a folder into plugins/ with a plugin.json manifest + a register(ctx) entry module, and RTerm auto-integrates it (agent tools, event-driven triggers, dashboard panels). Use when an agent needs to create a new plugin, scaffold a plugin template, test plugin loading, or deploy a plugin to an rterm-backend instance. Includes the manifest schema, PluginContext API, templates, and ready-made examples.

0
installs
▌
Agent Browser · drolu
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.

0
installs
▌
Agent Creator · drolu bundle
Create AiderDesk agent profiles via interactive Q&A.

0
installs
▌
Data Analysis · drolu
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

0
installs
▌
Orchestration · drolu
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".

0
installs
▌
Rmagent Linux · drolu bundle
Pull-based remote-witness habit for Linux and macOS hosts — the Linux sibling of rmagent-windows. Same philosophy: pull-only, allowlisted questions, no agent install, watch-only (Phase 0), capped answers, holes instead of dumps. Five questions (attest, sketch, edges, explain, attackmap) over SSH reading journald/auth.log/ss/systemd/cron. Use when the estate grows beyond Windows so the security observatory is actually multi-plane. macOS paths documented as experimental.

0
installs
▌
Rterm Backend · drolu bundle
Install, configure, run, administer, and manage the standalone RTerm backend (rterm-backend / gybackend) completely headlessly on macOS, Linux, and Windows. Use when an agent needs to set up RTerm-as-a-service — install the daemon, configure its data dir and gateway, run it as a service, manage saved connections/automation/schedules, and drive it over its WebSocket JSON-RPC gateway. Pair with the rterm-gateway skill for the RPC method reference and client examples.

0
installs
▌
Rterm Gateway · drolu bundle
Remotely drive any RTerm instance over its WebSocket gateway — run AI agent tasks, open/control SSH/WinRM/Serial/local terminals, transfer files, manage settings & scheduled automation, fully headless. Use when an agent needs to call an RTerm gateway to execute commands on remote servers, run playbooks, orchestrate fleets, or schedule jobs from another program or agent (e.g. Pi, CI pipelines, other LLM agents).

0
installs
▌
Skill Creator · drolu bundle
Design and create Agent Skills using progressive disclosure principles. Use when building new skills, planning skill architecture, or writing skill content.

0
installs
▌
Theme Factory · drolu
Step-by-step guide to add a new UI theme to AiderDesk (SCSS + CSS variables + types + i18n).

0
installs
▌
Video Creator · drolu bundle
Full-stack cinematic video production skill. Creates professional, story-driven 1920x1080 MP4 videos for products, services, events, SaaS, enterprises, and brands using HyperFrames HTML compositions with GSAP animation, professional TTS voiceover (Kokoro bm_george/af_heart), Whisper transcription for synced captions, Canvas 2D particle effects, SVG animations, kinetic typography, scribble underlines, burst-line highlights, multi-scene transitions (glitch, push, blur, color blocks), and complete production pipeline (design.md → script → voiceover → transcript → composition → lint → validate → render). Use when asked to create any kind of video — product demo, service promo, event teaser, brand launch, enterprise pitch, social ad, explainer, or announcement.

0
installs
▌
Writing Tests · drolu bundle
Comprehensive guide for writing unit tests, integration tests, and component tests in AiderDesk using Vitest. Use when creating new tests, configuring mocks, or organizing test files.

0
installs
▌
Dagu Workflows · drolu
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.

0
installs
▌
Playwright CLI · drolu
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.

0
installs
▌
Reactorpro Doc · drolu
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.

0
installs
▌
Superagent CLI · drolu
Use the SuperAgent CLI to orchestrate worktrees, live terminals, and browser automation through a running SuperAgent editor. Use when an agent needs to create, inspect, update, or remove SuperAgent worktrees; inspect repo state known to SuperAgent; read, send to, wait on, or stop SuperAgent-managed terminals; or automate the built-in browser (navigate, snapshot, click, fill, screenshot). Coding agents should also keep the current worktree comment updated with the latest meaningful work-in-progress checkpoint whenever useful. Triggers include "use superagent cli", "manage SuperAgent worktrees", "read SuperAgent terminal", "reply to Claude Code in SuperAgent", "create a worktree in SuperAgent", "update SuperAgent worktree comment", "click on", "fill the form", "take a screenshot", "navigate to", "interact with the page", "snapshot the page", or any task where the agent should operate through SuperAgent.

0
installs
▌
Synapse Client · drolu bundle
Connect to and operate on any Synapse agent mesh from any agent runtime. A drop-in async Python client (nats-py) plus a bash CLI helper exposing all 6 Synapse primitives (register, discover, request, respond, emit, subscribe) plus heartbeats, durable task polling, chunked file transfer, health probing, and event subscription. Defaults to the local mesh at nats://localhost:4222 (NKey auth, TASK_STORE KV bucket, AGENT_INBOXES JetStream stream, monitoring on :8222, WebSocket on :8443) but accepts arbitrary url/port/auth (NKey/JWT/creds/anonymous) to reach any remote Synapse network. Use whenever an agent needs to discover agents, call agent skills, broadcast or subscribe to events, send files for analysis, or serve requests on the Synapse mesh.

0
installs
▌
Av Whitelisting · drolu bundle
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.

0
installs
▌
Rmagent Actuate · drolu bundle
Phase 1 response — named, journaled, reversible actions on Windows witnesses you administer (block_ip, disable_user, isolate_host, rotate_credential, …). Dry-run first; --apply requires a plan id from a seen dry-run. No arbitrary shell. Complements rmagent-so (watch) and rmagent-redteam (drill). Use after Phase 0 finds smoke you have confirmed is real.

0
installs
▌
Rmagent Redteam · drolu bundle
Purple-team DRILL for the rmagent-windows skill. Stages 8 reversible living-off-the-land (LOTL) artifacts on WS1/WS2 — failed Administrator logons, a new local admin, a SYSTEM scheduled task, a new LocalSystem service, PowerShell spawns, a SYSTEM outbound connection, a registry Run key (T1547.001), and an IFEO debugger hijack (T1546.010) — then runs rmagent census+hunt to score what it detects, and sends a Telegram alert with the detection report. Use to TEST rmagent effectiveness. This is a benign drill, not a real attack: every artifact is prefixed RMAgentDrill_ and is reversible with clean. Requires --confirm. Do NOT use against boxes you do not administer.

0
installs
▌
Rmagent Windows · drolu bundle
Pull-based remote-witness habit for a Windows estate — the "RMAgent" knock. Ask two workgroup Windows servers (WS1/WS2) eight allowlisted named questions (attest, sketch, edges, explain, netedges, pslogs, kernring, attackmap) over pywinrm/WinRM :5985, tracking the Administrator and SYSTEM accounts. Use for identity-led compromise, lateral movement, living-off-the-land, silent hosts, and honest root-cause on Windows boxes you administer — without building a log lake and without switching off the EDR. Phase 0 is watch only; there is no actuate. Does NOT replace CrowdStrike/Defender. Prefer this skill for the two-box estate and Administrator/SYSTEM tracking; use the parent `security-observatory` skill for multi-plane (identity, cloud, network) hunts.

0
installs
▌
Rterm Agentspan · drolu
Bridge RTerm / neuralOS to an AgentSpan (Netflix Conductor) server for durable, crash-resilient agent execution — runs that survive restarts and resume from the last completed step. Use when an agent needs to (1) set up the AgentSpan↔RTerm bridge (server, RTerm Settings→AgentSpan, auth via vault), (2) launch/monitor/approve durable agents + Conductor workflows from RTerm via the agentspan_* tools, (3) register RTerm playbooks as reusable Conductor workflows, or (4) build real workflows on the server (HTTP data-fetch tasks → LLM steps) that actually complete — including the gotchas (Responses-API vs chat-completions, secrets injection, model ids).

0
installs
▌
Rterm Discovery · drolu bundle
Agentless asset discovery and CMDB on RTerm — discover Windows (WinRM/PowerShell), Linux/UNIX (SSH), network devices (SSH/SNMP), VMware vCenter/ESXi, and databases (MS SQL/Oracle/MySQL/Sybase), consolidate zone results outbound-only via the WebSocket gateway or NATS mesh, and maintain a versioned, diffable, queryable inventory. Covers the full BMC Helix Discovery (ADDM) protocol matrix using RTerm's backends, playbooks, and inventory ledger. Use when an agent needs to collect infrastructure inventory, build/maintain a CMDB, run discovery scans, or reconcile assets.

0
installs
▌
Rmagent Template · drolu bundle
Lake-less, on-device RMAgent skill constitution and factory. Use when creating a new rmagent-* skill for any IT-operations plane (secops, devops, netops, sysops, datacenterops, mlops, aiops, payments, agentops, app tracing) — or when auditing an existing one against the no-lake ethos. Clone this, pick a grain and a sensor, write allowlisted questions, keep holes honest. Bundled with RTerm as the reference for every future rmagent skill.

0
installs
▌
Large File Reader · drolu bundle
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.

0
installs
▌
Promptfoo Redteam · drolu bundle
Run promptfoo LLM red-team evals against RTerm's configured model profiles via the promptfoo_redteam agent tool. Covers jailbreaks, prompt injection, credential exfiltration, PII leakage, destructive commands, roleplay disguises, multi-turn manipulation, encoding tricks, and tool-prompt injection. Use when the user asks to test model safety, check if a model is jailbreakable, compare models for safety, run red-team evals, or build custom adversarial test suites. Includes scenario libraries, custom test builders, CI gating, and result interpretation.

0
installs
▌
Rterm Systems Thinking · drolu bundle
The ultimate problem-solving and complex-systems playbook for RTerm / rterm-backend. Use when an agent needs to break down ambiguous, large, or messy systems into bounded sub-systems; estimate capacity (users, QPS, storage, bandwidth); prioritize requirements (MoSCoW); reason about trade-offs (CAP, PACELC, consistency vs availability, push vs pull, sync vs async); and then EXECUTE the design across real infrastructure using RTerm's terminals, fleet orchestration, playbooks, MOP change management, SRE observability, plugins, governance (AGT policy + maker/checker review), and audit trail. Turns "figure out the system" into "deploy, measure, and operate it."

0
installs
▌
Dbcli Exec · drolu
Execute INSERT, UPDATE, DELETE statements on 30+ databases using DbCli. Includes mandatory backup procedures before destructive operations. Use when user needs to modify data, insert records, update fields, or delete rows. Always create backups first.

0
installs
▌
Dbcli View · drolu
Manage database views (CREATE/ALTER/DROP VIEW operations)

0
installs
▌
Dbcli Index · drolu
Manage database indexes (CREATE/DROP INDEX operations)

0
installs
▌
Dbcli Query · drolu
Execute SELECT queries on 30+ databases (SQLite, SQL Server, MySQL, PostgreSQL, Oracle, etc.) using DbCli. Returns data in JSON, table, or CSV format. Use when user needs to query databases, read data, or execute SELECT statements.

0
installs
▌
Dbcli DB Ddl · drolu
Execute DDL (Data Definition Language) statements - CREATE, ALTER, DROP tables, indexes, views on 30+ databases using DbCli. CRITICAL - requires mandatory backup before DROP/ALTER operations. Use when user needs to create schema, modify structure, or drop database objects.

0
installs
▌
Dbcli Export · drolu
Export table data as SQL INSERT statements from 30+ databases using DbCli. Essential for creating backups before dangerous modifications (UPDATE/DELETE/DROP). Use when user needs to backup data, migrate tables, or create portable SQL dumps.

0
installs
▌
Dbcli Tables · drolu
List all tables in a database and show table structure (columns, types, constraints) for 30+ databases using DbCli. Use when user wants to explore database schema, see what tables exist, check table structure, or understand column definitions.

0
installs
▌
Dbcli Compare · drolu
Compare results of two SQL queries to verify if they produce identical data. Checks structure, record count, and data content using MINUS/EXCEPT operations. Use when user needs to validate query equivalence, compare view logic, verify refactoring, or check data consistency.

0
installs
▌
Dbcli Procedure · drolu
Manage stored procedures, functions, and triggers (CREATE/ALTER/DROP operations)

0
installs
▌
Dbcli Interactive · drolu
Interactive SQL mode for 30+ databases using DbCli. Provides REPL environment for exploratory queries, rapid prototyping, and database administration. Includes safety prompts before dangerous operations (UPDATE/DELETE/DROP). Use when user wants interactive database session.

0
installs
▌
Dbcli Export Schema · drolu
Export database schema objects (procedures, functions, triggers, views, indexes) as SQL scripts for backup

0
installs

85 published skills