theheavenlyd3mon
- 1.1k skills
- 0 followers
- 28 repo stars
- 2 weeks ago last updated
- ▌ Dynamic Workflow · theheavenlyd3monOrchestrate large fan-out work as a plan-in-code "workflow" so the agent's context holds only the final verified answer, not the exhaust of hundreds of intermediate steps. Use for codebase-wide sweeps, large migrations, multi-angle research, and any task too big for one context window where the split strategy is known enough to script. Includes the adversarial-convergence verification recipe (independent attempts + refuters, keep only surviving claims).
- ▌ Software Architecture Analysis · theheavenlyd3mon bundleReverse-engineer a software codebase to understand architecture, data flow, privacy posture, and feature surface — then produce a clean-room design document, PRD, or migration plan that re-imagines the system under new constraints (local-first, privacy-first, self-hosted). Use when you need to understand how a system works from its source code or produce a specification without copying implementation details.
- ▌ Animated Eikon From Base · theheavenlyd3mon bundleTurn one supplied base image into a full animated herm eikon: generate one high-contrast black/white canonical base plate, animate six state clips from that same starting frame with fal.ai/Kling, install sources under ~/.hermes/eikons/<name>/source/, and hand off to Eikon Studio for baking.
- ▌
- ▌
- ▌ Hermes Update Review · theheavenlyd3mon bundleUse when checking what a Hermes update added or commits.
- ▌ Capacity And Cost Engineering · theheavenlyd3mon bundleModel technical capacity, unit cost, and budget constraints connected to demand, performance, and reliability decisions. Use when projecting capacity from growth forecasts, sizing for peak events, designing cost-aware scaling policies, defining budget thresholds or quota/rate-limit enforcement, running or planning load/soak tests as capacity evidence, or resolving SLO-cost tradeoffs. Do NOT use for financial P&L statements, fundraising scenarios, or SaaS metrics (route to financial-modeling); for infrastructure implementation or cloud-resource provisioning (route to platform-engineering); or for generic cloud-cost tips and universal utilization targets — this skill does not prescribe fixed savings rates or one-size-fits-all thresholds.
- ▌ Remote Systems Administration · theheavenlyd3mon bundleAdminister and troubleshoot remote Linux, FreeBSD, NetBSD, OpenBSD, and macOS systems safely, one host or a fleet at a time. Use when a task requires SSH, Ansible, Paramiko, POSIX diagnostics, service management, software updates, system configuration, firewall changes, or evidence-led remote operations.
- ▌ Notion Cost Tracker · theheavenlyd3monLog API usage costs and model spending to the Notion Cost Tracker database.
- ▌ Notion Decision Log · theheavenlyd3monLog architecture decisions, model swaps, config changes, and provider switches to the Notion Decision Log database.
- ▌ Agent Evals And Observability · theheavenlyd3mon bundleDesign, run, review, or release framework- and vendor-neutral evaluations and observability for AI agents. Use when defining agent evals, datasets, graders, trajectory review, regression analysis, release gates, production traces, or privacy-aware telemetry. Covers task and trajectory contracts, statistical comparisons, and incident-to-case learning; route framework implementation to pydanticai or langgraph when needed.
- ▌ Character Builder · theheavenlyd3monUnified character sheet template + build workflow for long-form fiction. Merges Three Sliders, Wound/Lie/Want/Need, Dialogue 8-dims, Emotional Arc, Thematic Resonance, and role-optional tags (combat, magic, authority, antagonist). Use when creating or reviewing any character in a book project.
- ▌ Narrative Revisor · theheavenlyd3monSeparate reviewer stage for fiction — runs 3-pass craft/anti-slop/stability-trap critique on scenes without generating net-new plot. Emits JSON handoff for the drafting agent. Use after a scene is drafted in the book-writer pipeline; never self-review the draft you just wrote.
- ▌ Security Audit Methodology · theheavenlyd3mon bundlePlan authorized security reviews with threat modeling, architecture and dependency audits, and vulnerability classification. Use for scoped defensive security assessment.
- ▌ Unreal Engine Agent Harness · theheavenlyd3mon bundleDesign and bootstrap a minimal, generic AI agent harness for Unreal Engine game development. Covers architecture, bridge selection, tool inventory, build loop, optional memory integration, and a lazy cross-platform dev split.
- ▌ Hermes Desktop Pane Placement · theheavenlyd3mon bundlePlace or reorder Hermes desktop plugin panes (tabs, docks).
- ▌ Gated Content Retrieval · theheavenlyd3mon bundleNotes on fetching web content ordinary scrapers cannot reach — the xurl article API and the Browserbase dual-control browser session.
- ▌ Yc Default Alive Calculator · theheavenlyd3mon bundleEvaluate whether a startup is on a trajectory to profitability before running out of cash — Paul Graham's "Default Alive / Default Dead" framework. Takes revenue, burn rate, cash on hand, and growth rate; computes runway, burn multiple, and months to breakeven. Ships a deterministic CLI calculator. Load when founders ask about runway, burn rate, default alive, whether they need to raise money, or financial sustainability analysis.
- ▌ Oracle Polymarket · theheavenlyd3monPolymarket prediction market integration — read markets, orderbooks, publish simulated trades. Direct API reads + AI-Trader for simulated execution.
- ▌ Notion Agent Logbook · theheavenlyd3mon bundleAgent session logging to Notion — cron jobs, kanban workers, and subagents write structured log entries to a searchable database.
- ▌ Notion Cron Registry · theheavenlyd3monRegister and track cron jobs in the Notion Cron Job Registry database.
- ▌ Notion Research Zone · theheavenlyd3monLog research results to the Notion Research Vault database — from cron jobs, subagents, and investigate sessions.
- ▌ Obsidian Vault Audit · theheavenlyd3mon bundleSystematic audit and cleanup of an Obsidian vault: detect clutter, structural drift, oversized files, dual folders, and icarus accretion, then decompose into kanban tasks.
- ▌ Wiki Synthesis Publishing · theheavenlyd3mon bundlePublish a COMPLETED multi-source research investigation to an LLM-Wiki as a canonical synthesis concept page + findings manifest, with raw-source ingests (real sha256) and schema/taxonomy extension. Use when the user says 'turn this research into a wiki page', 'push a canonical page + manifest into the wiki', or after a research sweep that produced synthesis worth persisting. Complements (does not replace) the llm-wiki skill's Ingest/Query/Fabric/Lint operations.
- ▌ Hermes Profile Staleness Audit · theheavenlyd3mon bundleRead-only audits of Hermes profile directories — activity/staleness verdicts (ACTIVE/DORMANT/STALE/CANDIDATE-FOR-REMOVAL), clone-pair detection, duplicate cron pipelines, live-gateway checks, reclaimable-space estimates, plus feature-fit audits (which profiles should have which MCP servers / plugins / hub skills).
- ▌ Obsidian Note Creation · theheavenlyd3mon bundleAtomic Obsidian note creation: resolve vault path, pick the right container, check for duplicates, draft structured notes, patch existing pages, and update the nearest MOC/index.
- ▌ Fabric Promote Review · theheavenlyd3monPromote high-value Icarus fabric entries to LLM-Wiki pages — scan, cross-check, create, index, log.
- ▌ Series Orchestrator · theheavenlyd3mon bundleSaga/series-level fiction orchestration. Handles multi-book continuity planning, cross-volume character arc tracking, power-system escalation management, external skill selection for writing pipelines, and Obsidian vault integration. Covers the gap between single-book narrative craft and franchise-level worldbuilding.
- ▌ Token Compression · theheavenlyd3mon bundleCompress skill/config/prompt files using Proteus-style DSL — token packing, semantic normalization, DSL encoding, structural compression, state-machine loops, arrow conditionals. Reduces 40-70% on behavioral/header sections while keeping operational instructions readable.
- ▌ Audiocraft Audio Generation · theheavenlyd3mon bundleAudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
- ▌ Hermes Session Recovery · theheavenlyd3mon bundleUse when session_search misses a known past session.
- ▌ Cheontag Batch Song Generation · theheavenlyd3monGenerate multiple Suno-ready songs in one response: artist tracks using RIVEN/SOLA profiles and template tracks using hybrid songwriting methodologies. Supports batch outputs for creative music pipelines.
- ▌ AI Trading Research · theheavenlyd3mon bundleAI-assisted trading research agent — builds agents that research markets, generate trade signals, and track P&L, while the human makes all execution decisions. Covers architecture, data sources, cron scheduling, and the human-in-the-loop pattern.
- ▌ Oracle Market Intel · theheavenlyd3monRead-only financial market intelligence via AI-Trader's Market Intel API — macro signals, ETF flows, stock analysis, grouped news. No auth required for reads.
- ▌ Windows Isolated Dev Environment · theheavenlyd3mon bundleSet up Hermes Agent on a Windows PC under a restricted non-admin user account — isolated from personal data, optimized for GPU-accelerated creative/dev work (Three.js, Blender, UE5, web game dev). Covers portable installs, security boundaries, profile design, and cross-machine config transfer.
- ▌ Notion Agent Inventory · theheavenlyd3monTrack Hermes agent profiles, their roles, models, and tools in the Notion Agent Inventory database.
- ▌ Large Document Familiarization · theheavenlyd3mon bundleUse when a user drops a large document packet to review.
- ▌ Idea To Design Doc · theheavenlyd3monUse when turning a rough idea into a focused product/design Markdown doc through guided questions, without moving into implementation too early.
- ▌ Style Lora Research Pipeline · theheavenlyd3mon bundleDiscover, curate, and batch-test external style LoRAs for brand-custom image generation. Covers Loratlas-style libraries, FAL LoRA inference, and async polling patterns.
- ▌ Visual Artifact Verification · theheavenlyd3mon bundleQA visuals when vision/browser tools missing: Chrome.
- ▌
- ▌ Beginner Friendly Writeup · theheavenlyd3monTurn internal knowledge into clean, shareable guides for newcomers. Use when the user asks for a write-up, explainer, or guide that someone else will read — especially if they don't know the system.
- ▌ Oracle Tradingagents · theheavenlyd3monMulti-agent LLM trading analysis framework — 4 specialist analysts (fundamentals, sentiment, news, technical) with bullish/bearish debate, risk management, and portfolio decisions. Wraps TradingAgents CLI/Python API.
- ▌ Gbrain Team Wiki Install · theheavenlyd3monInstall and configure GBrain with a shared Team-Wiki in the Obsidian vault for multi-agent collaboration
- ▌ Provider Fallback Strategy · theheavenlyd3mon bundleDiagnose provider auth failures (401/403/404), check credential health, configure fallback chains, and plan budget-aware model tiering across multiple providers.
- ▌ Discord Moderation Bot · theheavenlyd3mon bundleConfigure Hermes Agent as a Discord moderation / community-management bot. Covers Dev Portal app+bot creation, the correct SCOPED permission integer for moderation (NOT the docs' chat-only default), and gateway .env scoping (home channel, allowed/ignored channels, allowed roles). Also answers "what Discord skills are available?" → there are none; Discord is gateway config, not a downloadable skill.
- ▌ Tool Call Efficiency · theheavenlyd3mon bundleMinimize tool call count per task by assessing context sufficiency before reaching for tools. Cross-cutting behavioral discipline for all agent tasks.
- ▌ Privacy Engineering · theheavenlyd3mon bundleTranslate privacy principles and legal requirements into data-flow, lifecycle, acceptance, and verification artifacts. Map data classification, purpose, processing, access, retention, deletion, residency, and consent; define verifiable privacy acceptance criteria; and produce data-lifecycle records, retention/deletion verification plans, and privacy change reviews. Use when engineering privacy into a system, feature, or data flow — not for legal advice, jurisdiction-specific regulatory interpretation, or replacing security engineering or incident response.
- ▌ Agent Resource Triage · theheavenlyd3mon bundleTriage a batch of AI-agent / LLM GitHub repos (or link dumps) for personal relevance — collapse star-inflated lists into the few that actually apply to your stack and workflow. Use when the user pastes a list of GitHub links and asks "which are worth it" / "review these resources" / "look into all these".
- ▌ Web Integration Diagnostics · theheavenlyd3mon bundleDiagnose Hermes web/browser tools (Firecrawl, Browserbase).
- ▌ External Coding Agents · theheavenlyd3mon bundleDelegate coding tasks to external CLI agents (Claude Code, Codex, OpenCode) via Hermes terminal. Covers orchestration patterns, parallel work, PR reviews, and tool selection.
- ▌ Idea Superpowers Suite · theheavenlyd3mon bundleUse when running the full idea workflow: capture a rough idea, expand it into design/UI/implementation docs, research similar products, and generate build-ready Markdown artifacts.
- ▌ NPM Supply Chain Sweep · theheavenlyd3mon bundleCheck npm installs after a supply-chain poisoning advisory.
- ▌ Markdown Repo Doc Lint · theheavenlyd3monAudit and patch a repo's Markdown documentation for tone consistency, section-skeleton drift, dead relative links, and stale boilerplate. Use when asked to review READMEs, guides, profile docs, or any markdown corpus, and return exact diffs or a per-file verdict instead of summary prose.
- ▌ Gbrain Obsidian Integration · theheavenlyd3monIntegrate GBrain knowledge graph engine with an Obsidian vault — architecture patterns, sync strategy, MCP setup, and Team-Wiki mirroring. Use when setting up GBrain alongside an existing Obsidian vault with PARA structure.
- ▌ NPM Dependency Remediation · theheavenlyd3monRemediate npm vulnerability advisories on a Node project or fork with minimal risk. Clears in-range advisories via non-force `npm audit fix`, isolates force-required bumps (out-of-range) behind a human decision, and verifies the test suite stays green — including the NODE_ENV=production dev-dependency trap that makes `npm test` fail with "vitest: command not found". Trigger when the user says "npm audit shows highs", "remediate vulnerabilities", "update deps on the fork", "fix npm audit", or asks to clear security advisories during a maintenance pass.
- ▌ Subagent Driven Development · theheavenlyd3mon bundleExecute plans via delegate_task subagents (2-stage review).
- ▌ Macos Host Security Assessment · theheavenlyd3mon bundleAudit a macOS host for malware and vulnerabilities.
- ▌ Technical Documentation Authoring · theheavenlyd3mon bundleWrite accurate technical docs about systems, tools, and stacks. Covers setup guides, architecture overviews, and component inventories. Core principle: verify before documenting.
- ▌ Macos Endpoint Security Assessment · theheavenlyd3mon bundleScan a Mac for malware, persistence, and overlooked vulns.
- ▌
- ▌ Ml Engineering · theheavenlyd3mon bundleMachine learning engineering methodology — model training, fine-tuning (LoRA/QLoRA), evaluation, quantization, deployment, and MLOps pipeline design. Grounded in practical engineering patterns for production ML systems.
- ▌ Writers Helper · theheavenlyd3mon bundleGuide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking creative blocks, generating position-aware prompts and exercises, building sustainable writing habits, and the business of publishing — book proposals, query letters, synopses, agents, publishers, and book deals. Do not use for formatting deliverables into document files (see word-document, pdf-document, epub), for technical or business documentation (see technical-documentation), or for pure grammar and spelling reference.
- ▌ No AI Slop · theheavenlyd3mon bundleEdit drafts into sharper, more human writing while preserving the writer's personal voice, or detect AI-slop patterns without rewriting. Use when the user wants a draft clearer, more direct, more opinionated, or less AI-sounding, or asks whether writing reads as AI.
- ▌ Hermes Fork UI · theheavenlyd3mon bundleNavigate, dissect, and modify the Hermes fork's CLI/TUI rendering — the two-stack architecture (Python `rich`+`prompt_toolkit` CLI vs TypeScript React-Ink TUI), the TUI↔Python-gateway event protocol, and the reusable streaming/tool-trail rendering patterns. Use when asked to "dissect the fork's UI", "how does the TUI render tool calls / streaming", "where is the tool-call UI", or when building a streaming agent TUI.
- ▌ Blue Ocean Strategy · theheavenlyd3mon bundleCreate uncontested market space using value innovation instead of competing head-to-head. Use when the user mentions "blue ocean", "red ocean", "strategy canvas", "ERRC framework", "value innovation", "non-customers", "buyer utility map", "eliminate-reduce-raise-create", or "uncontested market". Also trigger when comparing pricing strategies, exploring new market categories, finding underserved customer segments, or asking how to stop competing on price. Covers the Four Actions Framework, buyer utility map, and value-cost trade-offs. For tech adoption strategy, see crossing-the-chasm. For product positioning, see obviously-awesome.
- ▌ Go To Market · theheavenlyd3mon bundleCMO methodology — positioning and messaging frameworks (April Dunford's positioning, message hierarchy), customer acquisition strategy (paid, organic, PLG, SLG), brand architecture (brand house vs house of brands), growth modeling (CAC/LTV by channel, cohort analysis), market entry strategy (beachhead, land-and-expand), competitive response (pricing wars, feature races, brand defense).
- ▌ Predictable Revenue · theheavenlyd3mon bundleBuild a scalable outbound B2B sales process with specialized roles (SDR, AE, CSM). Use when the user mentions "outbound sales", "Cold Calling 2.0", "prospecting emails", "sales pipeline", "SDR process", "B2B SaaS sales", "sales development", or "pipeline velocity". Also trigger when setting up a sales team from scratch, designing cold email sequences, or building qualification frameworks to improve close rates. Covers lead generation, qualification frameworks, and separating prospecting from closing. For offer design, see hundred-million-offers. For persuasion science, see influence-psychology.
- ▌ Scorecard Marketing · theheavenlyd3mon bundleBuild quiz and assessment funnels that generate qualified leads at 30-50%% conversion. Use when the user mentions "lead magnet", "quiz funnel", "assessment tool", "lead generation", "score-based segmentation", "interactive content", "lead qualification", or "quiz marketing". Also trigger when designing self-assessment tools, building calculators or graders for marketing, or creating personalized result pages that drive conversions. Covers question design, dynamic results by tier, and automated follow-up sequences. For landing page conversion, see cro-methodology. For full marketing plans, see one-page-marketing.
- ▌ IOS Accessibility · theheavenlyd3mon bundleBuild and audit SwiftUI, UIKit, and AppKit accessibility for VoiceOver, Voice Control, Switch Control, Full Keyboard Access, Dynamic Type, focus restoration, labels/traits/actions, traversal, custom rotors, NSAccessibility, XCTest checks, adaptive system preferences, and App Store accessibility declarations. Use when implementing accessible UI, fixing an accessibility audit, testing assistive-technology behavior, or substantiating App Store Accessibility Nutrition Labels.
- ▌ Human Review · theheavenlyd3monOpen an HTML file, Markdown file, or localhost page in the browser so the user can edit text directly and leave comments on specific parts, then send all edits and comments back to you. Use after writing or updating something the user will read — specs, plans, reports, newsletter drafts, landing pages, slide decks, and locally running web pages.
- ▌
- ▌
- ▌ Notion Pages · theheavenlyd3monCreate, read, update, and archive Notion pages — both standalone pages and database entries.
- ▌
- ▌ Creative Writing Craft · theheavenlyd3mon bundleCraft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.
- ▌ Flaresolverr · theheavenlyd3mon bundleUse the minimal FlareSolverr wrapper for a one-off health check or browser-backed GET/POST when ordinary retrieval is blocked by Cloudflare or DDoS-GUARD. Choose flaresolverr-cli instead for named session lifecycle, cookie-only returns, dry-run planning, or the full operational command surface.
- ▌ Travel Guide · theheavenlyd3mon bundleCreate personalized, source-grounded travel dossiers from a destination, dates, duration, travelers, and constraints. Ask only the questions that change the plan, use explicitly permitted personal context without exposing it, research current logistics, and produce a cited, visually coherent PDF or responsive companion web page. Use when someone wants an individualized itinerary, trip brief, travel field guide, or shareable travel website. Do not use for real-time booking, ticket purchasing, visa or legal advice, or generic destination summaries without a specific traveler and trip.
- ▌
- ▌
- ▌ Tailscale Macos · theheavenlyd3mon bundleGet Tailscale running and connected on macOS when the daemon won't start or `tailscale status` fails. Covers the dual-install conflict (native Tailscale.app vs Homebrew CLI) and the macOS system network-extension approval gate that only a human can click.
- ▌ Continuous Discovery · theheavenlyd3mon bundleBuild a weekly cadence of customer touchpoints using Opportunity Solution Trees, assumption mapping, and interview snapshots. Use when the user mentions "continuous discovery", "opportunity solution tree", "weekly interviews", "assumption testing", "discovery habits", "product trio", or "outcome-based roadmap". Also trigger when setting up regular customer feedback loops, prioritizing which experiments to run, or connecting discovery insights to delivery work. Covers experience mapping, co-creation, and prioritizing opportunities. For interview technique, see mom-test. For team structure, see inspired-product.
- ▌ Influence Psychology · theheavenlyd3mon bundleApply the six principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", or "commitment and consistency". Also trigger when designing testimonial sections, crafting urgency messaging, or improving trust signals on landing pages. For deal negotiation tactics, see negotiation. For viral word-of-mouth, see contagious.
- ▌ Storybrand Messaging · theheavenlyd3mon bundleClarify brand messaging using narrative structure that positions the customer as hero. Use when the user mentions "brand message", "website copy", "elevator pitch", "one-liner", "messaging isnt resonating", "brand script", "StoryBrand framework", or "customer as hero". Also trigger when rewriting homepage copy, crafting email nurture sequences, or creating consistent messaging across sales collateral and marketing materials. Covers landing page copy, marketing collateral, and consistent communication. For memorable messaging, see made-to-stick. For product positioning, see obviously-awesome.
- ▌
- ▌
- ▌ Nous Branding · theheavenlyd3mon bundleGenerate images and content consistent with the Nous Research brand identity. Use when creating visuals in the Nous / Theia / Hermes ecosystem: a "cyber-classical" style blending neo-classical statuary, cyberpunk/industrial grunge, and retro anime illustration. Covers official brand color palette, typography (Inter/IBM Plex Sans, JetBrains Mono, heavy distressed display faces), the Nous Girl mascot, texture system, and image prompt construction. Ships reference images for palette, mascot, and brand collage that can be used as img2img inputs.
- ▌ Notion Blocks · theheavenlyd3monAppend and read Notion block content — paragraphs, headings, lists, code, to-do, images, and all block types.
- ▌ Notion Search · theheavenlyd3monSearch across a Notion workspace — find pages, databases, and content by query.
- ▌ Data Scientist · theheavenlyd3mon bundlePhD-level expertise in data science, statistics, and machine learning. Use when the task requires rigorous statistical analysis, experimental design, causal inference, advanced modeling, research methodology, or data science project leadership. Load when the user asks about statistical methods, experimental design, model selection, A/B testing, hypothesis testing, power analysis, regression, causality, Bayesian analysis, or research methodology.
- ▌ Technology Radar · theheavenlyd3mon bundleBuild and maintain technology radars for adoption, trial, assessment, and hold decisions. Use when governing technology choices, build-versus-buy decisions, or engineering portfolio risk.
- ▌ Brand Designer · theheavenlyd3mon bundleCreate comprehensive brand identity documentation for any brand. Guides you through documenting strategy, visual identity (logo, color, typography, imagery), voice and tone, application guidelines, governance, and asset inventory. Produces markdown specs, compiled brand books, and brand-compliant images via reference-image-aware generation. Use when you need to capture a brand's identity in structured, durable form — for vault storage, agency handoff, or press kit distribution.
- ▌ Confluence CLI · theheavenlyd3mon bundleInteract with Atlassian Confluence from the terminal: list spaces, browse pages, view page content, search with CQL, and create pages. Use when the user mentions Confluence, a space key (e.g. DEV), or asks about documentation, wiki pages, space content, or knowledge base articles.
- ▌ Legal Strategy · theheavenlyd3mon bundleCLO/General Counsel methodology — regulatory landscape analysis (GDPR, CCPA, AI Act, sector-specific), IP strategy (patent, trademark, trade secret, open source licensing), contract risk assessment (indemnification, liability caps, force majeure), data privacy frameworks (privacy-by-design, DPIAs, data mapping), corporate governance (board responsibilities, fiduciary duties, shareholder rights), employment law (classification, IP assignment, non-competes).
- ▌ Mobile Development · theheavenlyd3mon bundleBuild, test, sign, and ship mobile apps across iOS, Android, Flutter, and React Native — project scaffolding, builds and code signing, device and emulator testing, store submission (App Store and Play Store), app lifecycle and backgrounding, offline and sync, and mobile-specific testing. Use when the task involves creating, building, testing, or shipping a mobile app for iOS or Android, or reasoning about mobile behavior such as background execution, push notifications, offline storage, and data sync. Do not use for web frontend work (that is frontend-engineering), backend services and APIs (that is backend-engineering), or desktop and web platform targets outside the iOS and Android scope.
- ▌ Social Media Pipeline · theheavenlyd3mon bundleBuild a creative brand identity and content pipeline for social media — from name brainstorming through visual identity, content strategy, and generation workflow.
- ▌ Project Workspace · theheavenlyd3mon bundleMulti-agent project workspace conventions — filesystem layout, shared working copies, project-level AGENTS.md, and sandbox-awareness for Hermes profiles.
- ▌ Wiki Health Check · theheavenlyd3mon bundlePeriodic wiki maintenance pass: broken links, orphans, stubs, duplicates, SHA256 drift, tag audit.
- ▌ Incident Learning · theheavenlyd3mon bundleConvert operational incident and near-miss evidence into durable product, engineering, test, evaluation, and governance improvements with verified closure. Separate observed facts from causal hypotheses and unresolved uncertainty; map follow-up work across code, tests, skills, operations, product, and governance; track ownership, verification, and closure for every finding. Do not use to assign blame or produce a generic postmortem template; do not close learning because tickets were created — require evidence the intended change occurred.
- ▌ Data Architect · theheavenlyd3mon bundleA virtual data architect for teams who don't have one. If your data pipelines are growing faster than your team, nobody agrees on what 'customer' means, your cloud bill is climbing without clear reason, or you're about to choose a data platform and need someone who's seen this before — load this skill. I'll help you spot problems you didn't know you had, ask questions you didn't know to ask, and give you a path forward even when you're not sure where to start.