dennisonbertram

Deploy and manage Cloudflare Workers, KV namespaces, D1 databases, R2 buckets, and Durable Objects via the wrangler CLI. Trigger: when deploying to Cloudflare, using wrangler, deploying Workers, managing KV namespaces, D1 databases, R2 buckets, Durable Objects, Cloudflare queues

Deploy containers globally to Fly.io with multi-region support, managed Postgres, volumes, and Firecracker microVMs using the fly CLI. Trigger: when deploying to Fly.io, using flyctl, fly launch, fly deploy, managing Fly machines, Fly Postgres, multi-region deployment

Debug Kubernetes issues: CrashLoopBackOff, OOMKilled, ImagePullBackOff, pending pods, networking, and resource limits using kubectl. Trigger: when debugging Kubernetes pods, troubleshooting CrashLoopBackOff, OOMKilled pods, ImagePullBackOff errors, pending Kubernetes pods, K8s networking issues

Apply manifests, manage rollouts, scale deployments, configure services, and manage secrets on Kubernetes clusters using kubectl. Trigger: when deploying to Kubernetes, using kubectl, applying manifests, managing K8s deployments, scaling Kubernetes workloads, Kubernetes rollouts, kubectl port-forward

Deploy frontend apps, Next.js projects, and serverless functions to Vercel with preview URLs and production deployments. Trigger: when deploying to Vercel, using vercel CLI, deploying Next.js, creating preview deployments, managing Vercel environments, adding Vercel domains

Test REST APIs with curl and jq: send requests, validate responses, check status codes, headers, and JSON body. Trigger: when testing REST APIs, API testing with curl, validating HTTP endpoints, testing JSON responses, API smoke tests

Create, run, and rollback database migrations using goose or golang-migrate. Trigger: when running database migrations, creating migration files, rolling back migrations, using goose, using golang-migrate

Generate and review Go documentation with godoc, OpenAPI specs with swag/swaggo, and README generation patterns. Trigger: when generating Go documentation, godoc, OpenAPI docs, swagger, swaggo, README generation, API documentation

Sweep sub-agent JSONL transcripts for novel learnings and promote the strongest to durable docs. Use when asked to 'mine transcripts', 'sweep for learnings', 'extract learnings from transcripts', 'what did agents learn', 'harvest session insights', or at the end of any multi-agent session.

Instrument a frontend with version fingerprinting (meta tag + /__version endpoint) so LLM-based testing can verify the correct build is deployed before walking. Use when asked to 'add version check', 'deploy verification', 'instrument version', 'add build fingerprint', 'deploy-check', or before running ux-walker on a deploy.

Walk UX story catalog through a real browser, testing each journey for correctness, visual quality, and UX excellence. Auto-fixes small issues, files GitHub issues for larger ones.

This skill should be used when the user asks to "walk the issues", "work through github issues", "groom and implement issues", "tackle the issue backlog", "start the issue loop", "go through tickets", "work all open issues", "clear the backlog", "process all tickets", or "close out open issues". Orchestrates an end-to-end workflow: groom all open GitHub issues with subagents, then loop through them one-by-one - branching, researching, implementing with swarms, testing, committing, merging, and creating PRs until all issues are complete.

Launch the coordinator — a pure-delegation control plane that plans, delegates, reviews, and learns. Use when asked to 'coordinate', 'plan and delegate', 'run the coordinator', 'use the state machine', 'start a structured session', or 'plan this work'.

Deterministic 7-phase debugging workflow — symptom capture, git archaeology, reproduce with a targeted test, log inspection, hypothesis, fix + green confirmation, regression test + commit. Use when asked to 'debug', 'fix a bug', 'investigate a failure', 'diagnose', 'root cause', or 'why is this broken'.

Post-fix test-coverage analysis. Reviews a just-landed fix, generates targeted unit and regression tests, audits how the bug could have been caught earlier. Use after a fix is merged, when asked to 'add regression tests', 'pay off test debt', 'guard against regression', or 'ensure this doesn't happen again'.

Time-boxed research before adopting a library, API, architecture, or provider. Use when asked to 'research', 'compare options', 'evaluate a library', 'spike on', 'investigate a tool', 'should we use X', or 'what are our options for'. Produces structured findings in docs/research/ with no production code changes.

This skill should be used when the user asks to "generate daily report", "mac health report", "show me my status", "open health dashboard", "daily mac check", or mentions a unified macOS status report. Orchestrates every claude-mac-guardian skill, aggregates today's JSON, renders a dark-mode HTML dashboard, and opens it in the default browser.

This skill should be used when the user asks to "debug bluetooth", "bluetooth not working", "check bluetooth", "airpods not connecting", "bluetooth devices", or mentions pairing issues. Collects Bluetooth state on macOS and writes a JSON result to ~/.mac-guardian/data/.

This skill should be used when the user asks to "check disk usage", "is my drive full", "what's using my disk", "disk space", "free up space", or mentions low storage. Reports free space, largest directories, caches, Time Machine local snapshots, Xcode simulator footprint, and node_modules sizes, then writes a JSON result to ~/.mac-guardian/data/.

This skill should be used when the user asks to "check machine security", "run a security audit", "is my mac secure", "scan my machine", "audit my mac", or mentions SIP, Gatekeeper, FileVault, firewall, login items, launch agents, SSH keys, or authorized_keys. Performs a read-only macOS security posture audit and writes a structured JSON result to ~/.mac-guardian/data/.

This skill should be used when the user asks to "scan for malware", "is there malware on my mac", "check for viruses", "look for suspicious processes", "malware check", or mentions infection, adware, or spyware suspicions. Performs a heuristic, signature-free sweep for common persistence and process-anomaly patterns on macOS and writes a JSON result to ~/.mac-guardian/data/.

This skill should be used when the user asks to "debug my network", "internet is slow", "check connectivity", "why is my internet bad", "diagnose network", or mentions DNS, packet loss, or VPN issues. Performs read-only network diagnostics on macOS and writes a JSON result to ~/.mac-guardian/data/.

This skill should be used when the user asks to "check performance", "mac is slow", "why is my mac slow", "cpu usage", "memory pressure", or "what's slowing me down". Reports load average, memory pressure, swap, top processes, thermal state, and battery health, then writes a JSON result to ~/.mac-guardian/data/.

This skill should be used when the user asks to "setup daily health cron", "schedule mac health check", "automate daily report", "cron my mac check", or mentions scheduling the mac-guardian report. Installs a user-level launchd agent (preferred on macOS) that runs daily-health-report at a user-specified time, with cron as an optional fallback.

One-time import of an existing HTML/JSON PMF tracker (a pmf-data.json export) into the Markdown tracker layout — preserving the overview, thesis, scratchpad, every hypothesis, and weekly reviews verbatim. Use when migrating from a prior tracker, or when the user says 'pmf import', 'import my pmf data', 'migrate the tracker', 'convert pmf-data.json', or types '/pmf-import'.

Regenerate the tracker's INDEX.md from the current Markdown files — a status table of all hypotheses, grouping by area, the reviews list, and a 'findings so far' section (validated hypotheses only). Deterministic and idempotent. Use when the user says 'pmf index', 'rebuild the index', 'refresh the pmf index', 'regenerate INDEX.md', or types '/pmf-index'.

Roll up the week's daily PMF logs into a Weekly Review entry (Focus / Learned / Decisions / Next), surface recommended hypothesis signal/status updates for you to confirm, and refresh the index. Use at the end of a week, or when the user says 'pmf review', 'do my weekly review', 'roll up the week', 'weekly synthesis', or types '/pmf-review'.

Start a daily PMF / founder-research session. Resumes recent state (yesterday's log, open hypotheses, the last weekly review), interviews the founder about what they did, learned, heard from customers, and which hypotheses moved, then writes today's daily log as structured Markdown. Use at the start of a working day or when the user says 'pmf start', 'start my pmf day', 'log my research day', 'daily check-in for the venture', or types '/pmf-start'.

End-of-day PMF wrap-up. Summarizes the day from today's log, updates the hypotheses it touched (status / signal / evidence — only with explicit confirmation), captures decisions, and appends a dated thesis revision if direction changed. Use at the end of a working day or when the user says 'pmf wrap', 'wrap up my pmf day', 'close out the day', 'update my hypotheses', or types '/pmf-wrap'.

Generate exhaustive user journey stories by analyzing the codebase. Creates realistic UX paths (short feature exercises and long end-to-end flows) using a swarm of parallel sub-agents. Use when asked to 'create stories', 'walk the app', 'map user journeys', 'generate ux paths', 'create user flows', 'map the app', 'what can users do', 'generate test scenarios', 'create e2e stories', or 'exercise the app'.

Walk UX story catalog through a real browser, testing each journey for correctness, visual quality, and UX excellence. Auto-fixes small issues, files GitHub issues for larger ones.

This skill should be used when the user asks to "walk the issues", "work through github issues", "groom and implement issues", "tackle the issue backlog", "start the issue loop", "go through tickets", "work all open issues", "clear the backlog", "process all tickets", or "close out open issues". Orchestrates an end-to-end workflow: groom all open GitHub issues with subagents, then loop through them one-by-one — branching, researching, implementing with swarms, testing, committing, merging, and creating PRs until all issues are complete.

Generate images using Google's Nano-Banana (Gemini 2.5 Flash Image) model. Use when the user asks to generate, create, or make an image, picture, or illustration.

Create realistic long-form AI talking head/UGC videos that don't look AI-generated. Use when user wants to make "realistic AI video", "UGC video", "talking head video", "AI spokesperson", "AI ad content", "video that looks real", "human-looking AI video". Orchestrates Nano Banana for base images and Kling AI for video generation with natural pacing.

Your agent can search email but can't understand it. Deepmail gives agents persistent email knowledge — who matters, what relationships exist, what's happening. 10 tools to investigate, analyze, and remember email across sessions.

Your agent can search email but can't understand it. Deepmail gives agents persistent email knowledge — who matters, what relationships exist, what's happening. 10 tools to investigate, analyze, and remember email across sessions.

Semantic code search and code-intelligence guidance for lgrep. Use when searching code by meaning, locating definitions or usages, building task context, checking refactor impact, finding dead code, or exploring dependency structure.

This skill should be used when the user asks to "deploy a service", "deploy an app", "add a domain", "provision a database", "check service status", "view logs", "restart a service", "set environment variables", "reset circuit breaker", "register a tenant", "add a kanban board", "take a snapshot", "redeploy a service", "recover an API key", "check tenant usage", "view deployment history", "fork a service", or mentions operating an agentic-hosting instance. Also trigger when the user says "use agentic-hosting", "spin up on my PaaS", or "deploy to my server".

Back up and query Granola meeting transcripts. Refreshes Granola's auto-rotating auth token, downloads new transcripts locally, names them readably, and searches/reads the archive. Use when asked to 'pull granola', 'download my transcripts', 'sync granola', 'back up my meetings', 'search my transcripts', 'find that meeting', or to refresh Granola credentials.