Add a data warehouse table as a Self-driving Inbox signal source (the feature that ships GitHub, Linear, Zendesk, Jira, PagerDuty, Sentry, Snyk, Canny and others). A source syncs one warehouse table of actionable records (issues, tickets, conversations, incidents, findings, feedback, reviews) and the signals pipeline turns new rows into signals. Use when asked to "add a new inbox/self-driving source", "make <vendor> a signal source", or to find which warehouse sources could become signal sources. Covers candidate discovery, the backend emitter and registry, the signals frontend source catalog, the optional context-mill wizard entry, and created_via attribution.
41k2d agoReviewMountCreate a free account to mount
Layout structure for web interfaces, from grouping and alignment to reading order, progressive disclosure, and adaptive breakpoints. Use when structuring a page or component, spacing or aligning controls, deciding what collapses at small sizes, handling RTL layout direction, or reviewing frontend code for layout. Triggers on layout, spacing, alignment, grouping, negative space, whitespace, visual hierarchy, reading order, progressive disclosure, breakpoints, responsive layout, container queries, safe area, full-bleed, edge-to-edge, layout margins, RTL layout, logical properties.
26 projects use a version of this
12k3mo agoReviewMountCreate a free account to mount
The before-review and before-handoff pass for RomM, covering both stacks. First shapes the code the checks can't see: comment and docstring discipline (the single most-corrected thing in this repo), duplicated constants/types/getters, imprecise names, loose typing in tests. Then runs the verification gate that keeps CI green: frontend (typecheck/lint/test/build/i18n/tokens), backend (pytest/alembic/trunk), the OpenAPI regen step, and (for UI) manual browser/theme/input/Storybook checks. Ends with what the PR description owes a reviewer: screenshots of a UI change, a mermaid diagram of an architectural one. Use after the code works, right before committing, opening a PR, or telling the user a change is done.
14k48d agoReviewMountCreate a free account to mount
Records a captioned, PostHog-branded walkthrough video (MP4) of a feature running on the local PostHog stack, for a Loom, a Slack demo, or a PR. Use when asked to record a video, demo, walkthrough, or Loom of a change end to end, including flows that leave the app, such as an API call shown as a terminal card or an email arriving in the local inbox. The recorder drives the real app, zooms in on the beats the storyboard marks, adds RoundHog captions, a pointer, hedgehog stickers, and an optional ElevenLabs voiceover and music bed, and frames the video with title and end cards that carry the logo and a hedgehog from @posthog/brand. For a short animated WebP of one interaction in a PR description, use the reel mode of qa-frontend.
41k2d agoReviewMountCreate a free account to mount
Build end-to-end type-safe tRPC APIs inside NestJS using the nestjs-trpc adapter — @Router/@Query/@Mutation/@Subscription decorators, TRPCModule.forRoot, injectable middlewares and context, Zod input/output schemas, and the Rust CLI that generates the AppRouter type for clients. Use this skill whenever the user mentions nestjs-trpc, tRPC in a NestJS app, @Router or @Query decorators, TRPCModule, AppRouterHost, "typed API between my Nest backend and frontend", generating AppRouter types, or is migrating a NestJS GraphQL/REST API to tRPC — even if they don't name the library explicitly.
12k3mo agoReviewMountCreate a free account to mount
ACTIVATE when the user works on authentication in Laravel. This includes login, registration, password reset, email verification, two-factor authentication (2FA/TOTP/QR codes/recovery codes), passkeys, profile updates, password confirmation, or any auth-related routes and controllers. Activate when the user mentions Fortify, auth, authentication, login, register, signup, forgot password, verify email, 2FA, passkeys, WebAuthn, or references app/Actions/Fortify/, CreateNewUser, UpdateUserProfileInformation, FortifyServiceProvider, config/fortify.php, or auth guards. Fortify is the frontend-agnostic authentication backend for Laravel that registers all auth routes and controllers. Also activate when building SPA or headless authentication, customizing login redirects, overriding response contracts like LoginResponse, or configuring login throttling. Do NOT activate for Laravel Passport (OAuth2 API tokens), Socialite (OAuth social login), or non-auth Laravel features.
Nightly regression run of the EXISTING Bytebase Playwright e2e suite. It writes no new tests: decide whether main moved, build the frontend-embedded binary, run the suite on a disposable server, and for every red test decide whether the product broke (bug: Linear issue with an owner) or the test is outdated (spec rot: test-only adaptation PR), with flake, isolation, infra and flipped-lock as the other outcomes; then record the run ledger. Use it as the prompt target of the cloud scheduled task, or locally with /e2e-routine from a worktree. Not for exploratory QA or writing new specs (that is bytebase-e2e-testing) and not for verifying one change (that is verify).
15k19d agoReviewMountCreate a free account to mount
Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a diagnostic shape (frontend crash, "two numbers don't match", traffic count drop, tracker not loading / undercounting vs a competitor, ad-platform integration error, channel type misclassification), run the matching playbook, and produce reply drafts plus fix PRs where warranted. Use when asked to triage the web analytics support channel, investigate a web analytics Zendesk or conversations ticket, or explain metric discrepancies a customer reported. Internal-only: queries cross-customer support and usage data; never copy customer names or their traffic numbers into public artifacts (PRs, issues, commits).
41k2d agoReviewMountCreate a free account to mount
Use this skill to analyze how a Laravel application is actually written and record its conventions as shared rules. Trigger when the user wants to detect, infer, document, or standardize project conventions or coding style, set up or grow `.ai/rules`, resolve mixed or conflicting patterns (e.g. \"are we using Form Requests or inline validation?\"), or onboard agents and teammates to \"how we do things here\". Covers: a systematic sweep of ~49 Laravel convention dimensions (validation, models, architecture, testing, frontend, database, console), open-ended house-pattern discovery, conflict reporting, and recording rules scoped to the right paths via the Boost `record-rule` MCP tool. Only run this skill when the user explicitly asks for it; never start a sweep as part of another task. Do not use for one-off code review, enforcing formatting a linter already handles, or editing `.ai/rules` files by hand.
Upgrade the PyTorch version used by OpenVINO tests (torch / torchvision / torchaudio) and resolve fallout — missing operator translators, new functionalized `*_copy` aten ops, decomposition changes, FX-only tests failing in TorchScript mode, and accuracy regressions caused by stricter typing. Use when the user asks to "bump torch", "update pytorch to X.Y", "upgrade torch tests", or when pytorch_tests / model_hub pytorch tests fail after a torch version change. Do not use for: enabling a single new PyTorch operator unrelated to a version bump, GenAI / Optimum upgrades, or plugin-level numerical bugs unrelated to the frontend.
11k9d agoReviewMountCreate a free account to mount
Cross-references C# Web API controllers/DTOs against their TypeScript/JavaScript consumers (React, Angular, Vue, Svelte, Node.js, or hand-written/auto-generated HTTP clients like Fetch, Axios, NSwag) to catch contract drift in both directions: backend changes that break client applications (renamed/removed JSON keys, new required parameters, status code shifts) and frontend code sending fields the backend no longer reads. Works directly against source code, not exported OpenAPI spec files. Use when the user asks to check for breaking API changes, verify frontend/backend contract sync, or audit a DTO/controller change against its TypeScript/JS consumers before merging. Not for generating new API code from a spec (see openapi-to-application-code) or scaffolding new endpoints (see aspnet-minimal-api-openapi).
1 project uses a version of this
41k21d agoReviewMountCreate a free account to mount
Use this skill whenever the user wants to build scroll animations, scroll effects, parallax, scroll-triggered reveals, pinned sections, horizontal scroll, text animations, or any motion tied to scroll position — in vanilla JS, React, or Next.js. Covers GSAP ScrollTrigger (pinning, scrubbing, snapping, timelines, horizontal scroll, ScrollSmoother, matchMedia) and Framer Motion / Motion v12 (useScroll, useTransform, useSpring, whileInView, variants). Use this skill even if the user just says "animate on scroll", "fade in as I scroll", "make it scroll like Apple", "parallax effect", "sticky section", "scroll progress bar", or "entrance animation". Also triggers for Copilot prompt patterns for GSAP or Framer Motion code generation. Pairs with the premium-frontend-ui skill for creative philosophy and design-level polish.
1 project uses a version of this
41k21d agoReviewMountCreate a free account to mount
Use when deciding whether an endpoint, settings section, or UI flow should require recent authentication (re-auth), when adding `TimeSensitiveActionPermission` or its exemptions (`time_sensitive_allow_if_only_fields`, `time_sensitive_exclude_actions`, `time_sensitive_allow_actions`), when wrapping a page or settings section in `TimeSensitiveAuthenticationArea`, when an API read returns secret material, or when a write fails with `sensitive_action_required_reauth`. Carries the product decision: reads stay open, only sensitive writes need a fresh session, and the backend enforces it; organization settings are the one area gated on navigation. Covers how the frontend opens the re-auth modal and retries the failed request, and how to test a new gate. Trigger terms: re-auth, reauthenticate, reauthentication, sensitive session, fresh session, sudo mode, step-up, TimeSensitiveActionPermission, TimeSensitiveAuthenticationArea, sensitive_action_required_reauth.
41k2d agoReviewMountCreate a free account to mount
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to split one before some other change, or before restructuring code inside a module already over roughly a thousand lines — breaking up a long function or extracting helpers in place leaves everything in the same file, so check the worth-it gate and propose the split first. Covers that gate, assigning symbols to concerns with an acyclic dependency graph, the AST plus tokenize move script, and proving the result is a pure move. Python only — for frontend files use writing-ui-components. Not for extracting a shared helper into common/, and not for moving code between products, which is isolating-product-facade-contracts.
41k2d agoReviewMountCreate a free account to mount
Web typography from choosing fonts to spacing, wrapping and accessibility. Use when picking or pairing typefaces, configuring variable fonts or OpenType features, setting up a type scale, checking heading hierarchy, styling text in components, truncating text, styling underlines, selection, placeholders or carets, or reviewing frontend code for typography. Triggers on typography, fonts, font formats, woff2, variable fonts, font-weight, opentype, font-feature-settings, letter-spacing, line-height, type scale, heading hierarchy, heading levels, tabular numbers, text-wrap, truncation, line clamp, underlines, text-decoration, text selection, iOS input zoom, font smoothing, text contrast, measure, line length, text-box, smart punctuation, drop cap.
12k3mo agoReviewMountCreate a free account to mount
**WORKFLOW SKILL** - Wire an Aspire AppHost after `aspire init` drops a skeleton. Scans the repo, proposes a resource graph, edits the AppHost (C#, file-based C#, or TypeScript), wires `Aspire.ServiceDefaults` + OTel, validates with `aspire start`, then self-deactivates. USE FOR: wire AppHost, scaffold resource graph, add Postgres/Redis/Rabbit/Mongo to Aspire, connect frontend to API, after `aspire init` what next, AddNextJsApp, AddViteApp, WithBrowserLogs, file-based apphost.cs, apphost.ts, unified withEnvironment, refuse .aspire/modules edit, migrate .env files, migrate user secrets. DO NOT USE FOR: skeleton drop (use aspire-init), start/stop/wait/restart (use aspire-orchestration), publish/deploy/destroy (use aspire-deployment), logs/traces (use aspire-monitoring). INVOKES: aspire CLI (add, start, wait, describe, docs api search, stop), AppHost source edits, ServiceDefaults wiring. FOR SINGLE OPERATIONS: Run `aspire add PACKAGE` directly for a one-off integration.
11k3mo agoReviewMountCreate a free account to mount
Build and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against ONNX Runtime. Use when the user imports a non-LLM model to TensorRT, needs a verified engine from ONNX, hits trtexec "unsupported operator", must verify the engine matches ONNX numerically, debugs a polygraphy parity failure (large max abs diff at FP16), or configures multi-input dynamic shapes. Triggers: convert ONNX to TensorRT, Hugging Face to TensorRT, trtexec onnx, trtexec unsupported operator, optimum-cli export, polygraphy parity check, polygraphy run --trt --onnxrt, parity check failed, max abs diff, verify engine matches ONNX, --minShapes, dynamic shapes trtexec, multi-input shape profile, FP16 engine, INT64 warning. Adjacent skills: `trt-torch-quickstart` (PyTorch frontend), `trt-cpp-runtime-quickstart` (C++ engine load). LLM token generation belongs in TensorRT-LLM, not here.
13k5mo agoReviewMountCreate a free account to mount
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
host-webserver`, connection/handler/SSE) — additionally `DSH_SNAPSHOT=replay pnpm run test:web`: rebuilds the frontend dist, then runs the browser smoke pair (the real-host case self-skips without `DEEPSEEK
282k3mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
PostHogSkill
