Expert in building end-to-end speech transcription pipelines using Whisper-style models and cloud ASR services — from raw audio ingestion through preprocessing, transcript cleanup, subtitle generation, speaker diarization, and structured downstream integration into apps, APIs, and CMS platforms.
[BETA] Detect, review, and fix code-quality and correctness issues in an AEM as a Cloud Service
project — locally, with no external services or network calls. Use whenever a user wants to
check, review, assess, audit, scan, modernize, upgrade, or fix AEM Java, Sling Models, OSGi,
or Maven code — for example: "check my Sling Models are implemented correctly", "review my
@Inject usage", "are my Maven dependencies up to date", "scan this AEM project for issues",
"modernize my Sling Models", or "fix code-quality problems". Name the files to assess, or ask
it to scan the repo; it detects issues, plans, and — only when you ask — applies surgical
edits on a branch or in place, then verifies with mvn compile. It recognises the intent and
handles each issue type itself, reporting anything it cannot yet fix.
This skill is in beta. Verify all outputs before applying them to production projects.
Analyze Trigger.dev tasks, schedules, and runs for cost optimization opportunities. Use when asked to reduce spend, optimize costs, audit usage, right-size machines, or review task efficiency. Combines static source analysis with live run analysis via the Trigger.dev MCP tools (list_runs, get_run_details, get_current_worker).
Turn a pile of session recordings into a short list of findings a colleague can verify in two minutes — instead of a pile of anecdotes. Question-scoped triage → watch the survivors → triangulate against events, database and source → grade every claim MEASURED / RECONSTRUCTED / OBSERVED / INFERRED. Works on a local replay folder, PostHog, Microsoft Clarity, Hotjar, Smartlook or Yandex Webvisor — and on a claim with no recordings at all. Use when asked to "watch recordings", "review session replays", "why did users drop off", "check dead clicks", "verify the fix", "what are users actually doing", or to grade findings someone already wrote.
Connect an arbitrary REST API to the PostHog data warehouse as a Custom source by authoring a JSON manifest, with no per-source code. Use when the user points at an API that has no built-in PostHog connector — "import data from this REST API", "sync my internal API", "connect this API from its docs", "build a custom data warehouse source" — and gives a docs URL or a natural-language description of the endpoints. Walks through drafting the RESTAPIConfig manifest (auth — bearer, API key, HTTP basic, or OAuth2 client credentials / refresh token — pagination, record path, incremental cursor, parent/child fan-out), validating it, test-reading live rows to verify the field mappings, and creating the source. If the API already has a native PostHog connector, use setting-up-a-data-warehouse-source instead — this skill checks the connector registry first and only handles APIs with no native connector.
Use when Jared asks to build, launch, or walk through a Facebook/Instagram ad campaign live in Ads Manager. Covers campaign setup, creative selection, copy writing, audience targeting, and A/B testing with Hormozi-style directness.
Install the bundled Codex pet named 奶龙 from this repository. Use when the user asks for 奶龙.skills, 奶龙宠物, this yellow character pet, or wants Codex to install a prebuilt pet package into ~/.codex/pets without regenerating images.
Orchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gradual replacement of outdated components while maintaining continuous business operations through ex
Load this skill when deciding which inputs and scenarios a test should cover, not how to wire the runner: partitions, boundaries, state transitions, properties, fuzzing, failing dependencies. Trigger on "what should I test", "cover the edge cases", or a test file with only a happy path.
Reviews CloudKit code for container setup, record handling, subscriptions, and sharing patterns. Use when reviewing code with import CloudKit, CKContainer, CKRecord, CKShare, or CKSubscription.
AIOps-style one-click inspection skill for CloudBase resources. Use this skill when users need to diagnose errors, check resource health, inspect logs, or run a comprehensive health check across cloud functions, CloudRun services, databases, and other CloudBase resources.
Use when structuring a FastAPI application, designing dependency injection chains, defining Pydantic v2 schemas, adding JWT authentication, or writing async route tests with httpx.
Add a Canva-style visual Edit Mode to any HTML presentation/slide deck. Use this skill EVERY TIME you create, generate, or finish building an HTML presentation, slide deck, or מצגת for the user - inject the editor automatically as the final step. Also use when the user asks to "make my deck editable", "add edit mode", "הוסף מצב עריכה", "תעשה שאוכל לערוך את המצגת", or wants to move/edit/add elements in an existing HTML deck.
Use when creating or refining WebGL-heavy landing pages and you need to steer toward a specific visual outcome (premium, technical, playful, cinematic) while balancing conversion clarity, performance, and implementation complexity.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Data Transfer Objects for AdonisJS v6. Plain TypeScript interfaces and classes used to move validated data between the HTTP layer, actions, and services. Use when handling request payloads, structured data transfer, or when the user mentions DTOs, data objects, payload types, or typed interfaces for domain operations.