Run the mandatory pre-push baseline verification for Meshtastic-Android — bootstrap, then spotlessApply/spotlessCheck/detekt/detektTypeResolved/assembleDebug/test/allTests (plus kmpSmokeCompile and sort-strings when relevant) via the gradle-runner subagent, restore the host-render screenshot diff, and report a single pass/fail. Use before every push. This is the check CI fails on when skipped.

Use when writing, recording, updating, validating, or troubleshooting Agent Host end-to-end and real-provider integration tests under src/vs/platform/agentHost/test/node/e2e and providerIntegration. Covers adding a cross-provider test, re-recording fixtures after an SDK bump, required cross-platform Azure validation, gating non-deterministic or platform-specific tests, and diagnosing replay cache misses.

Add Bring Your Own Pollen (BYOP) sign-in to an app so each user pays with their own Pollen instead of the app's key. Use when building an app, CLI, extension or agent tool on Pollinations and you need the user-authorized sk_ key, when you must choose between the OAuth code flow, the fragment flow and the device flow, or when an app key's usage must be attributed and monetized.

Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with the fix for each. Use when the user asks to stress-test, break, or find edge cases in a component or screen, or to "try the worst case". For visual design critique use emil-design-eng; for motion use review-animations.

Try to break a piece of UI by feeding it worst-case data — long names, unbreakable emails, one-letter names, missing fields, huge counts, zero items, long labels, non-Latin text, emoji, extreme numbers — then render it behind a "Demo data / Worst case" toggle and report everything that broke, with the fix for each. Use when the user asks to stress-test, break, or find edge cases in a component or screen, or to "try the worst case". For visual design critique use emil-design-eng; for motion use review-animations.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Conduct post-training research for LLMs using the Tinker API — replicate paper results, explore new training ideas, run and monitor experiments, and document findings. Use this skill whenever the user wants to do research, replicate experiments from a paper or repo, investigate training hypotheses, run experiment sweeps, explore post-training techniques (SFT, RL, DPO, distillation, etc.), set up training, write training code, choose a model, tune hyperparameters, manage checkpoints, export weights, or analyze training logs — even if they just say "try this idea" or "let's see what happens if...".

Argus — the all-seeing scanner suite. Six automated scanners for high-value web + LLM bug classes — CORS misconfiguration (origin reflection / null / credentialed read), CRLF & host-header injection, NoSQL injection (operator auth-bypass / $where blind), JWT attacks (alg:none / RS256→HS256 confusion / secret crack), out-of-band confirmation of blind SSRF/XXE/SQLi/RCE/Log4Shell via interactsh, and an LLM red-team corpus (prompt-injection / jailbreak / system-prompt leak / exfil / indirect injection). Use when a target exposes a JSON API, a login endpoint, JWT auth, a parameter that might reach the server, a chatbot/agent, or any endpoint suspected of a blind/out-of-band bug.

Add a new game to the Tessl Carnival midway, following the water cannon pattern and the house rules. Use when asked to build, add or create a carnival game or booth, such as ring toss, whack-a-mole, hook a duck or high striker.

Hide a generator ecosystem or model version from everyone except moderators — "available to moderators, hidden" — and lift that gate again; or, during a provider outage, disable it for everyone except moderators with a message users see, and enable it again. Reads and writes the same generation gate rules the /moderator/generation-config page edits. Use before a new generator model's code deploys, to remove the gate at launch, and when one generator's provider is down. Called by onboard-generator-model; usable on its own.

Run the weekly OpenShell release captain checklist. Monday checks the pre-release train, triages failures and the compatibility review, and drafts the coordination post. Tuesday promotes the qualified pre-release after approval, verifies publication, and starts the next train. Trigger keywords - release captain, weekly release, Tuesday release, cut the release, release checklist, pre-release status, release train, start next train, stable release.

Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Use when the user asks whether AI agents can use or browse the site, or about llms.txt or WebMCP. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Professional editing of a course that already exists. Use when the user wants to revise, improve, restructure or polish pages the course already has — fix a page, tune a layout, repair a quiz, reword narration, reorder the deck, or raise the quality of the whole course. Not for building a new course from scratch.

Project conventions for writing, editing, restructuring, or reviewing the beads user documentation — the Mintlify site under docs/. Use this whenever you touch anything in docs/ (pages, concept docs, reference, integration guides, recovery runbooks, diagrams, docs.json navigation) or write/edit prose about beads, even when the request is just "fix the docs", "write a docs page", "the docs are wrong/confusing", "rename X across the docs", or an edit to a file under docs/. It defines the canonical concept model (bead → dependencies → ready work; formula → proto → molecule/wisp; gates; Dolt sync and federation), required terminology, the prose/emphasis/diagram conventions, the rule that generated docs are edited at their source, and the gates to run before docs work is done.

Build a HyperFrames slideshow to present live - slides, fragment reveals, branching hotspots and presenter mode with speaker notes, served by `hyperframes present` - or turn an existing page into one. Use when the person wants a deck or presentation rather than a rendered video.

The shared visual and writing reference for AI Engineering from Scratch pages, figures, and manuals. Use it for light and dark colour tokens, font stacks, FIG_ label formats, and card layout. Use it for the plain technical English rules and the accessibility and reduced motion defaults. Trigger phrases: "course style", "blueprint palette", "course tokens", "FIG label", "plain technical English", "check my prose", "course fonts", "dark mode tokens"

The shared visual and writing reference for AI Engineering from Scratch pages, figures, and manuals. Use it for light and dark colour tokens, font stacks, FIG_ label formats, and card layout. Use it for the plain technical English rules and the accessibility and reduced motion defaults. Trigger phrases: "course style", "blueprint palette", "course tokens", "FIG label", "plain technical English", "check my prose", "course fonts", "dark mode tokens"