dougwithseismic

Provision and manage Hogsend deployments on Railway. Use when creating new client instances, managing env vars, checking health, updating journey configs, or troubleshooting Railway deployments.

Use when deploying or configuring production infra for YOUR scaffolded Hogsend app — Railway two services (api via railway.toml with /v1/health + pre-deploy db:migrate; worker via railway.worker.toml, no healthcheck), Hatchet-Lite, required vs optional env, and upgrading the engine + refreshing vendored skills. This is for shipping your own app, NOT the maintainer's package-release process.

Use when adding or editing a lifecycle journey in src/journeys/ — wiring a defineJourney() trigger/entryLimit/exitOn/suppress, writing the run(user, ctx) control flow, durable sleeps, branching on history/engagement, sending email from a journey, and the register-in-index + thread-into-client/worker ritual.

Use when adding or editing a code-first feature flag in src/flags/ — defineFlag({ key, name, type, variants?, defaultValue?, description?, enabled? }) from @hogsend/engine. A flag committed to the repo, upserted into a `flags` row by the boot reconciler (born DISABLED, rollout 0). Covers the contract-vs-state split (code owns key/name/type/variants/defaultValue/description; DB/Studio owns enabled/rollout/targeting/conditionSets), the register ritual (src/flags/index.ts + thread flags into createHogsendClient in BOTH src/index.ts and src/worker.ts), running `pnpm flags:generate` after adding/removing a flag to refresh flags.d.ts (typed useFlag/getFlag/evaluate), and when to use client.flags.create() / Studio (dynamic, experimental) vs defineFlag (durable product flags).

Generate the full Hogsend brand asset pack — social/OG/banner image templates in every preset, palette colorway and campaign carousel, plus Remotion campaign videos — into the gitignored marketing/out/ folder. Use whenever asked to (re)generate brand templates, ad carousels, campaign stills, brand videos, contact sheets, or "the out folder" of marketing assets.

Add a new play to hogsend.com/playbook (apps/docs/content/playbook). Use whenever someone wants a new playbook item — it walks the whole contract end to end - frontmatter, the intro + five-part template in the right register, the copy rules (tool-agnostic play steps, honest facts, valid engine snippets), the dogfood weekly-rotation sync, and the verification gates. The plays shipped in

Hatchet CLI skills for managing workflows, workers, and runs. Use this skill when triggering workflows, starting workers, debugging runs, replaying failed runs, or setting up the Hatchet CLI and profiles.

Use when releasing or publishing @hogsend/* or create-hogsend, adding a publishable package or scaffold dependency, bumping versions, reviewing a "Version Packages" PR, or diagnosing a package that is missing from npm.

Show usage information for any workflow-toolkit skill. Use when the user asks how to use a specific skill, what a skill does, or needs guidance on workflow-toolkit features. Also triggers on "help", "how do I", "what does X do", or "usage" in the context of workflow-toolkit skills.

Initialize and verify the workflow-toolkit environment. Checks SQLite availability, creates the journal database, verifies directory structure, checks gh CLI auth, and reports readiness. Run this after installing the plugin or when troubleshooting.

Pre-flight checklist for open source contributions. Validates code changes against project rules, PR size limits, commit format, linting, and type-checking. Does NOT push or create PRs — only reports issues.

Creates a new Claude Code custom subagent configuration. Guides you through designing agent scope, tools, permissions, hooks, and system prompts.

Creates a new Claude Code custom skill (slash command). Guides you through designing, writing, and placing the SKILL.md file with proper frontmatter, arguments, and best practices.

Open the journal SQLite database in a GUI viewer (DB Browser for SQLite, or similar).

Distills a codebase concept into a structured knowledge base entry. Analyzes patterns, conventions, and real examples from the code to create reference documentation. Use when you need to understand how something works in this project (e.g., React hooks, API routers, database models, testing patterns).

List and filter tracked GitHub issues from the local SQLite database. Filter by state, label, priority, tracking status, or search by keyword.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Discover and scrape jobs from 2,800+ companies using Ashby as their ATS. Search and filter by location, remote status, department, and keywords. Use when looking for jobs, researching companies hiring, or building job market intelligence.

Scrape all Ashby job boards and search for matching roles. Runs the full discover-scrape-search pipeline. Use when user says "scrape ashby" or wants to run the full job scraping pipeline.

Professional fiction editor with 6 passes. Checks AI pattern contamination, voice fidelity, POV consistency, continuity, prose tightening, and scene assessment. Assembles scenes into chapter.md.

Add YouTube video embeds and mermaid diagrams to the article. Replaces placeholders with actual embed code.

Evaluate article quality against targets defined in article.json. All thresholds are read from the spec, not hardcoded. Returns PASS or FAIL with specific issues.

Brainstorm plot developments, character arcs, scene suggestions, and thematic explorations. Reads voice profile, open threads, and continuity state to generate grounded, voice-aware ideas.

Generate a detailed article outline from completed research. Creates subsections with conversational headers (no colons) and prose-focused structure.

Start the MITM proxy and configure environment variables for HTTP/HTTPS interception

Introduces the @withseismic/mitm proxy plugin — explains available skills, scripts, the REST API, rule engine, and traffic inspection. Use when a user asks what the MITM proxy can do, how to get started, or needs an overview of capabilities.

Inspect captured HTTP traffic from the MITM proxy. Use when the user wants to see what requests were made, filter traffic by URL, view request/response details, or analyze network activity.

Create and manage MITM proxy interception rules and transforms. Use when the user wants to intercept, modify, block, redirect, or mock HTTP traffic passing through the proxy.

Check MITM proxy status, rule counts, and request statistics. Use when the user asks if the proxy is running or wants to see current state.

Audit a website's readiness to be cited by AI search engines (ChatGPT search, Google AI Overviews/AI Mode, Perplexity, Claude). Use when asked to "audit our AI SEO / GEO", "why aren't we cited by ChatGPT", "check our AI-crawler access", or before starting GEO work. Produces a prioritized gap report.

Write or retrofit web/blog content so it gets cited by AI search engines — answer-first structure, question headings, sourced statistics, and FAQ schema. Use when creating blog posts, landing/pillar pages, or improving existing pages for AI-search visibility (GEO/AEO).

Measure AI-search visibility and citations — pull Google Search Console data, check AI-referral and AI-bot telemetry, and run manual citation spot-checks against a baseline. Use when asked "are we getting cited by AI", "track our GEO/AI-search performance", or to report progress after GEO work.

Multi-feature autonomous builder. Takes a list of features, generates TODO docs in parallel, detects dependencies, creates a master tracking doc, then executes each feature through TDD → Code Review → PR Review workflow. Designed for long autonomous sessions with self-continuation. Use when building multiple related features or a complete project phase.

Use when deploying or configuring production infra for YOUR scaffolded Hogsend app — Railway two services (api via railway.toml with /v1/health + pre-deploy db:migrate; worker via railway.worker.toml, no healthcheck), Hatchet-Lite, required vs optional env, and upgrading the engine + refreshing vendored skills. This is for shipping your own app, NOT the maintainer's package-release process.

This skill should be used when the user wants to turn a static image — a screenshot, mockup, concept render or design comp — into a real, editable Figma file with proper layers, auto-layout frames, editable text and true vector logos (not a pasted bitmap). Triggers on "image to Figma", "screenshot to Figma", "turn this mockup into Figma", "make this PNG a real design", or pointing at a .png/.jpg and asking for a Figma version. Also covers the reverse leg — reading a Figma frame back out via the Figma MCP server to build code from it.

Optimize Windows 11 for performance, privacy, and developer productivity. Use this skill whenever the user wants to speed up Windows, remove bloatware, debloat their machine, tune Windows for development, clean up junk apps, optimize GPU/network/memory settings, disable telemetry, or generally make their Windows machine faster. Also trigger when users mention slow builds, Windows bloat, startup optimization, or anything about making Windows less annoying. Even if they just say 'my PC feels slow' or 'clean this machine up' on a Windows system - this skill applies.

Launch AoE2:DE from Steam, wait for it to be ready, then start AoE2Control in headless mode with the aoe2bot module for a skirmish match. Use when the user wants to start a bot game session.

Multi-feature autonomous builder with integration coherence. First generates a PROJECT_SPEC.md (integration blueprint), then generates TODO docs in parallel with shared context, detects dependencies, creates enriched MASTER.md, then executes each feature through Implementation → Code Review → Integration Checkpoint → Commit workflow. Ensures features integrate properly, not just work individually. Use when building multiple related features or a complete project phase.