delorenj

Sync delorenj/hermes-agent fork with NousResearch/hermes-agent upstream while preserving fork-only paths, the agents/hermes/pm/runtime submodule, and the 3 fork-side code tweaks. Use when running /hermes-sync, when the user says "sync the fork", or when you need to pull in upstream hermes-agent commits without losing local customization.

Facilitates a single point of ingress for any and all tasks. Used when pulling a new `inbox` task from the 33god plane workspace, or any prompt that explicitly or implicitly describes a non-trivial task. Triggered by `add a feature`, `task.inbox.new` event.

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.

Framework for self-sustaining AI agent teams with self-service work queues, role ownership, continuous discovery, and proactive operation via heartbeat loops.

Agno AI agent framework. Use for building multi-agent systems, AgentOS runtime, MCP server integration, and agentic AI development.

Entry point for ASCII CLI banners. Choose the Python built-in font skill or the figlet.js/FIGfont skill depending on needs.

Plan and generate terminal ASCII animations/screensaver-style output (FPS, refresh rules, loop policy, low-flicker guidance), with a static poster frame and an optional local demo script.

Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.

Generate tests for a completed phase based on UAT criteria and implementation

Generate an AI-SPEC.md design contract for phases that involve building AI systems.

Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit

Audit milestone completion against original intent before archiving

Cross-phase audit of all outstanding UAT and verification items

Run all remaining phases autonomously — discuss→plan→execute per phase

Capture ideas, tasks, notes, and seeds to their destination

Archive accumulated phase directories from completed milestones

Integrate services or agent harnesses into the 33GOD bloodbank event bus. Covers event schemas via holyfields, producing events (NATS direct recommended; Dapr, HTTP /publish, hookd_bridge as alternatives), consuming events (NATS subscribe; Dapr, FastStream, event-toaster catch-all), and wiring agentic coder hooks (Claude Code via hookd, GitHub Copilot CLI via copilot-hooks). Use for adding event publish/consume to a 33GOD service, authoring a schema, integrating a new harness (OpenCode, Cursor, Aider, Codex CLI), or debugging missing envelopes. Triggers include bloodbank, event bus, fire/publish/subscribe bloodbank, NATS subject event., holyfields, CloudEvents, hookd, event-toaster, ntfy.delo.sh/bloodbank, copilot-hooks, agent.session.started, agent.tool.invoked, command.{agent}.{action}. Skip for generic RabbitMQ/NATS/Kafka, n8n (workflow-router), hindsight memory (hindsight), or non-event-bus 33GOD (33god). Biases NATS+holyfields, against hand-edited envelopes or bypassing the bus.

Decision skill for new automation work. Routes the request to the right tool (n8n, a Python service, a Claude skill, cron+bash, or extending an existing workflow) and queries the n8n registry first so existing workflows are not reinvented. Use when the user wants to build, create, wire up, automate, schedule, integrate, or trigger anything. Trigger phrases include "wire up", "automate", "when X happens do Y", "build a workflow", "n8n workflow", "schedule X", "integrate A with B", "webhook", "event-driven", "pipeline", "trigger". ALWAYS run BEFORE designing or implementing new automation, even if the user already named a specific tool. Owner Jarad DeLorenzo, n8n at https://n8n.delo.sh.

Persistent agent memory via self-hosted Hindsight. Retain knowledge, recall context, reflect on patterns. Includes multi-bank routing architecture for agent orgs.

Entry-point agent for the tflo (Intelliforia Trello Flow) module. Owns the FSM (idle → implementing → verifying → pr-ready → idle, plus escalated escape) and orchestrates the triage → implement → verify → create-pr cycle by invoking the workflow SKILLs. Use when the user wants to start, resume, check status, abort, or autonomously loop through Intelliforia Trello tickets. Triggers on phrases like "tflo start", "what should I work on next on Intelliforia", "claim the next ticket", "resume the loop".

PR-creation workflow for the tflo (Intelliforia Trello Flow) module. Pushes the ticket branch, opens a PR with a type-aware body (QA instructions for code, summary of findings for discovery, design rationale for design, scannability notes for doc), generates a retro doc, mirrors learnings to Hindsight, moves the Trello card to In Review, and resets the FSM to idle.

Implementation workflow for the tflo (Intelliforia Trello Flow) module. Routes the active ticket through the appropriate subagent chain based on its detected type (code/bug/feature/refactor/discovery/design/doc), produces the deliverable artifacts (architect plan, test plan, dev story, code commits OR analysis doc OR design doc), and transitions the FSM from implementing to verifying. The type field in current-ticket.md determines which chain runs.

Idempotent setup workflow for the tflo (Intelliforia Trello Flow) module. Validates env vars, fetches the initial Trello board snapshot, scaffolds the memory bank skeleton, auto-detects the bot user, and (optionally) updates the project's commit-msg hook to accept tflo-prefixed commits. Re-runnable for re-config.

Pick the next Trello card to work on. Scores open cards on the Intelliforia board, claims the top one, moves it to In-Progress, creates the branch, writes FSM state. Use when the user says "what should I work on?", "tflo start", "claim next ticket", or when the orchestrator loops idle → triage. Mutates Trello + git on claim.

This skill codifies the standards and workflows for this machine's openclaw agent gateway configuration. Use this skill when provisioning new agents or managing existing ones. Trigger phrases are "add a new agent", "update [agent's name] identity"

Unified 33GOD master skill and router. Use for any 33GOD request: architecture context, project creation, task execution, coding workflow, service development, workflow generation, and platform-level orchestration. This skill routes to focused references/workflows/scripts for incremental discovery.

Use this when creating new projects, generating documentation, cleaning/organizing a repo, suggesting architecture, deploying containers and services, naming files/folders, or when the user references 'ecosystem', 'patterns', or 'containers'. This skill outlines naming conventions, stack preferences, project organization (iMi worktrees), Docker patterns, and PRD structures from past conversations.

Orchestrate multi-step project workflows using mise task definitions with dependency management and argument handling. Use whenever the user wants to create, edit, or debug mise tasks, wire up task dependencies with depends/depends_post, or run workflows via 'mise run'. Also use when setting up task runners or automating build pipelines through mise. Do NOT use for mise environment variable configuration (use mise-configuration instead) or for general shell scripting unrelated to mise.

Codifies the standards and conventions for the creation, organization, categorization, and aggregation of data in the DeLoDocs obsidian vault. Use this skill when asked to add something 'to my vault' or 'in my vault', when creating any reports, instructions, updates, or any markdown documents that are intended to be viewed, and are NOT part of a project or repository.

Bub's canonical workflow for inbox/calendar triage escalation filtering (known contacts, money/security risk, high-signal AI changes).

Agent-local context guard and deterministic compaction workflow (GOD-13). Use when context usage is high, when wiring auto-compaction/restart timers, or when deploying standardized context-monitor hooks across agents.

Manage the homelab monitoring stack at ~/docker/stacks/monitoring/. Services: Prometheus, Grafana, Alertmanager (Telegram via DeLoNETBot), cadvisor, node-exporter, process-exporter, Loki, OTEL collector, Dockge, Uptime Kuma, health-monitor. Use when: (1) adding, editing, or debugging Prometheus alert rules, (2) managing or restarting monitoring services, (3) checking alert delivery or Telegram bot status, (4) diagnosing system performance issues (CPU hogs, memory bloat, swap pressure), (5) adding new scrape targets to Prometheus, (6) configuring Grafana dashboards or datasources, (7) any task referencing "monitoring", "alerts", "prometheus", "grafana", "cadvisor", "process-exporter", "alertmanager", "telegram alerts", or "DeLoNETBot".

PR Jangler hub. Cron-driven autonomous workflow for triaging, verifying, reviewing, fix-planning, adversarially validating, fix-implementing, deciding, and daily-reporting on a GitHub PR backlog. Use when the user mentions "PR jangler", "pr-jangler", "PR backlog workflow", "PR triage", "autonomous PR review", "fix-plan", "fix-PR", "adversarial validator", "PleaseAdvise", or wants to install, configure, or extend the PR Jangler BMad module. Routes to 12 phase skills, owns the cross-cutting state-file conventions, idempotency rules, GitHub-label vocabulary, and 1Password/SMTP/`gh`/`op` dependency map shared by every phase. Triggers on prj-setup, prj-orchestrator, prj-discover, prj-triage, prj-verify-claim, prj-review, prj-detect-overlap, prj-plan-fix, prj-validate-adversarial, prj-implement-fix, prj-decision, prj-report-daily.

PR Jangler final-call workflow. Use when the orchestrator dispatches the decision phase for a reviewed PR or when the user runs 'prj-decision' to label, comment, and log a ready-to-merge / request-changes / close-as-not-now verdict.

PR Jangler duplicate and overlap detector. Use when the orchestrator dispatches the overlap check after triage marked a PR as possible-duplicate, or when the user runs 'prj-detect-overlap' for manual debug.

PR Jangler GitHub-to-queue sync. Use when the orchestrator dispatches the discovery sweep (on cadence or empty queue) or when the user runs 'prj-discover' for manual debug.

PR Jangler Tier-2 implementer. Use when prj-validate-adversarial passed for a PR and the orchestrator dispatches FixImpl. Pushes a fix branch and opens a fix-PR into the contributor's branch; falls back to a comment if the contributor's branch refuses PRs.

PR Jangler cron heartbeat dispatcher. Use when cron invokes one heartbeat of the PR backlog workflow or when the user runs 'prj-orchestrator' for manual debug.

PR Jangler fix-planning workflow. Use when a Trello-like comment claim on a PR has been verified by prj-verify-claim and a fix plus failing-test plan must be designed before any implementation. Activated by prj-orchestrator when a PR's phase is FixPlan.

PR Jangler daily email reporter. Use when the orchestrator dispatches the daily report at the configured local hour or when the user runs 'prj-report-daily' for manual debug.

Drop a specific skill version or an entire skill — soft (deprecate) or hard (purge) with platform context rebuild. Use when the user requests to "drop" or "remove a skill."

Package for distribution and inject context into CLAUDE.md/AGENTS.md/.cursorrules. Use when the user requests to "export" or "package a skill."

Rename a skill across all its versions — transactional copy-verify-delete with platform context rebuild. Use when the user requests to "rename a skill."

Autopilot orchestrator who runs target BMAD workflows unattended, delegates to workers, and answers HITL questions per a policy file. Use when the user asks to talk to Otto, says "run X on autopilot", or invokes /bmad-bmp-agent-otto.

Hand a target BMAD workflow to Otto for unattended execution. Otto plans, delegates to workers, answers HITL questions per a policy file, and pauses cleanly when confidence dips below floor or category is in always_pause. Use when the user says "run X on autopilot", "do this unattended", or invokes /bmad-bmp-autopilot.

Sets up BMad Autopilot module in a project. Use when the user requests to 'install bmp module', 'configure BMad Autopilot', or 'setup BMad Autopilot'.

Generate high-quality images from text prompts using fal.ai's text-to-image models. Supports intelligent model selection, style transfer, and professional-grade outputs.

Generate comprehensive, publication-quality technical manuals with thematic storytelling using multi-agent orchestration. Use when user asks for themed documentation, narrative technical guides, memorable training materials, or mentions themes like Victorian, steampunk, art deco, medieval, pharmaceutical, or nautical combined with technical topics. Triggers on phrases like "create themed manual", "documentation with storytelling", or requests to make docs "more engaging" or "memorable".

Create or update product briefs through guided or autonomous discovery. Use when the user requests to 'create a product brief', 'help me create a project brief', or 'update my product brief'.

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Trello MCP Server skill for board discovery, card workflows, checklist management, comments, attachments, labels, members, board/workspace selection, and health monitoring through the bundled @delorenj/mcp-server-trello server.

FL Studio Python scripting for MIDI controller development, piano roll manipulation, Edison audio editing, workflow automation, and FLP file parsing with PyFLP. Use for programmatic configuration, device customization, MIDI transport, macros, and save file manipulation. Covers all 427+ API functions across 14 MIDI scripting modules plus piano roll, Edison, and PyFLP contexts.

Implement and maintain the GOD (Guaranteed Organizational Documents) system for multi-component repositories. Use when: (1) initializing GOD Doc structure in a new or existing repo, (2) creating component or domain GOD Docs from templates, (3) auditing GOD Doc freshness and detecting drift, (4) decomposing a repo into non-overlapping domains as a prerequisite, (5) setting up git hooks or CI actions for deterministic dirty-checking, (6) working with the degenerate Rust CLI for drift detection, (7) managing inter-GOD-doc dependencies. Triggers on: 'GOD doc', 'architecture docs', 'documentation drift', 'doc freshness', 'degenerate', 'domain decomposition', 'guaranteed organizational', 'doc staleness', 'template-based docs'.