Write a durable handoff note before this pod is interrupted (update/suspend) so the next session — possibly a different agent — can pick up without re-deriving anything. Use when asked to hand off, or before you expect to be interrupted.
Always go, never assume — the leading work driver. Continuous autonomous execution with a visible register, permission lanes, async questions, and self-scheduled continuation. Use in EVERY session; it governs how all other work happens.
Fetch and research public web content from a pod without evading anyone — walk the ladder (official API → direct fetch → archive → reader service → the owner's relay) and report honestly when a target is fortified. Also covers the relay's egress tunnel ($PODBAYRELAYPROXY) for crawlers, scripts and Playwright that must…
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
Fix the iOS keyboard "composer stranded at the top / page scrolls up" bug in any mobile web app with a bottom-fixed input. Use whenever you build or touch a chat/message/comment/search UI whose input sits at the bottom of a full-height layout.
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
Orient yourself in an UNFAMILIAR existing codebase before making changes. Use at the start of any byo-project session and whenever you land in a repo you haven't mapped yet: read its docs, map the structure, detect the stack, and — critically — find and verify the install / dev / test commands. Produces a short…
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
Push a branch and open a pull request from a headless pod using the gh CLI, with a MANDATORY confirmation gate before anything leaves the machine. Use when the user wants to open a PR for work on THEIR OWN repo. Pairs with finishing-a-development-branch (which prepares the commit). Never force-pushes, never runs git…
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
Drive the "Ask Your Docs" engagement end to end — the staged flow that turns the user's documents into a live, grounded, shareable bot, with the agent leading and a living /work/PLAN.md. Use at the start of a doc-qa session and to decide the next step at any point. Lead the user through it; don't wait to be told each…
Get the user's documents INTO the bot cleanly — accept common formats (txt/md/pdf/docx/html), extract readable text, chunk it well for retrieval, and report back what was actually indexed. Use when the user wants to add their docs, when an upload fails or indexes badly, or when answers are missing content you'd expect…
The integrity spine of an "Ask Your Docs" bot — make it answer ONLY from the user's retrieved documents, attach citations to every claim, and say "I don't know" when the docs don't support an answer. Use when building, tuning, or debugging the chat/answer route, the system prompt, or anytime an answer looks invented…
Make the bot's answers actually good — evaluate and improve RETRIEVAL (does the right passage come back for a real question?) and tune the answer behavior. Use after docs are loaded, whenever answers are wrong/thin/miss content that IS in the docs, or when deciding chunk size / top-k / semantic-vs-keyword search. Test…
Write B2B cold emails and follow-up sequences that get replies. Use when the user wants to write cold outreach emails, prospecting emails, cold email campaigns, sales development emails, or SDR emails. Also use when the user mentions "cold outreach," "prospecting email," "outbound email," "email to leads," "reach out…
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," "CTA copy," "value…
Build and maintain a lightweight CRM inside the pod's Next.js app — a leads table + conversation log that is the user's persistent, returnable pipeline. Use when the user is tracking prospects/outreach for the first-10-customers playbook.
When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages, feature pages, lead capture forms, or contact forms. Also use when the user says 'CRO,' 'conversion rate optimization,' 'this page isn't converting,' 'improve…
★not rated 6 1mo agoA145 tokens
archived
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: