jaydubya818

Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include…

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.

Run comprehensive agent-native architecture review with scored principles

This skill should be used when writing Ruby gems following Andrew Kane's proven patterns and philosophy. It applies when creating new Ruby gems, refactoring existing gems, designing gem APIs, or when clean, minimal, production-ready Ruby library code is…

Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says 'let's brainstorm', or when they want to think…

Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, consolidating, replacing, or deleting them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels…

Document a recently solved problem to compound your team's knowledge

Listen carefully and reflect back what the user said before acting. Use when the user needs to feel heard or when clarifying intent before proceeding.

Always produce a structured artifact (file, table, or doc) as the primary output before summarizing. Use for reporting tasks where the deliverable should be a concrete artifact.

Follow backend implementation best practices: typed interfaces, error handling, migrations, and test coverage. Use when implementing backend features, APIs, or data models.

Respond in a natural, concise conversational tone without unnecessary structure or headers. Use for chat-style interactions that don't require formal output.

Define how tasks are handed off between agents or roles, including context passing and acceptance criteria. Use when orchestrating multi-agent or multi-role workflows.

Enforce clear boundaries between domains (frontend, backend, infra) and prevent cross-domain coupling. Use when reviewing or designing code that spans multiple system layers.

Follow frontend implementation best practices: component structure, accessibility, typed props, and test coverage. Use when implementing UI features or components.

Ensure implementation plans include all context needed for a clean handoff to the executing agent. Use before handing off a spec or plan for implementation.

Umbrella skill for integrating an agent with Mission Control, the orchestration and observability control plane. Use this skill when an agent needs to interact with Mission Control and you must route to the right focused skill — registration, heartbeats, task…

Use this skill when a Mission Control work item is complete or awaiting review and an operator needs a factual handoff draft with outcome, evidence, unresolved risk, next owner, and next action.

Tracks and enforces agent spend in Mission Control. Use this skill when recording costs via api.agents.recordSpend, declaring budgetDaily and budgetPerRun limits at registration, or reacting to budgetRemaining and budgetExceeded values returned by the…

Keeps an agent alive in Mission Control by calling the api.agents.heartbeat mutation every 30-60 seconds. Use this skill when running any agent session: agents that miss heartbeats for 2 minutes get quarantined, and the heartbeat response is how you discover…

Persists agent knowledge across sessions using the Mission Control agent documents system. Use this skill when depositing session memory before shutting down, keeping a WORKING_MD scratchpad up to date, writing daily notes, or reading back previously stored…

Registers an agent with Mission Control via the Convex api.agents.register mutation. Use this skill when an agent session starts and the agent must announce itself (name, emoji, role, workspace, task types, budgets) before doing any other work. Re-registering…

Requests human or dual-control approval for risky actions through the Convex api.approvals.request mutation. Use this skill when an action is YELLOW or RED risk tier — YELLOW needs a single approval, RED needs dual control (two decisions), and GREEN/LOW…

Records every agent execution turn as a run in Mission Control. Use this skill when starting a run (status RUNNING), completing or failing one (COMPLETED / FAILED), and reporting model, token counts, and cost so the observability and audit trail stays honest…

When the user wants to create competitor comparison or alternative pages for SEO and sales enablement. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product]…

End-to-end system for creating supervised fine-tuning datasets from books and training style-transfer models. Covers text extraction, intelligent segmentation, synthetic instruction generation, Tinker-compatible output, LoRA training, and validation.

Personal knowledge management system for founders, creators, and builders. Manages personal brand, content creation, network relationships, goals, and provides voice/tone consistency for content generation.

Comprehensive automation engineering skill for CI/CD pipelines, testing automation, deployment automation, monitoring, and workflow orchestration. Specializes in modern DevOps practices and infrastructure automation.

Comprehensive cloud infrastructure and deployment skill for AWS, containerization, serverless, monitoring, security, and scalable architecture design. Specializes in production-ready infrastructure for fintech applications.

Build and maintain comprehensive design systems with tokens, components, documentation, and governance. Specializes in scalable design systems for React, Vue, and Angular applications with Storybook integration.

Specialized development skill for financial technology applications, including payment processing, financial calculations, compliance, security, and marketplace features specific to seller financing platforms like SellerFi.

Install Claude Code skills from GitHub repositories as git submodules. Use when: (1) installing skills from GitHub URLs like obra/superpowers or blader/continuous-learning, (2) git warns "adding embedded git repository", (3) need to track external skill repos…

Build a Hermes-ready context block from a task, suitable for pasting into Hermes' planning prompt.

Audit the skill/resolver/filing-rules layer for structural integrity.

Convert a repeated workflow into a reusable Markdown skill (procedural document only in v0.1).

Canonicalize an open proposal into a typed page (or append to an existing page's timeline).

Create a proposal to canonicalize a piece of content as a decision, lesson, pattern, or other typed page.

Capture a quick note to inbox without canonicalizing it.

Build a context pack for a coding agent task with cited decisions, lessons, patterns, and repo/project context.

Return the repo's compiled-truth summary as a SearchResult.

Run ClaudeClaw operational commands (restart services, deploy to GitHub, run extractors, check status, tail logs, apply schema migrations) without asking the user to remember bash incantations. Invoke when the user says "restart the dashboard", "deploy", "run…

Generate higher-order insights from the memories table — patterns, contradictions, blind spots Jay hasn't articulated. Used by /insights slash command.

Search, pin, decay, and inspect memories. V3 transcript ch.14 — the memory palace skill.

Pull, summarize, and analyze Meta (Facebook/Instagram) ad performance via the Meta CLI. Used by the daily 7:30 AM ad brief and on-demand by Ops/Research.

Detect when an existing agent is overburdened and propose a new agent to split the load. V3 transcript ch.11 — the Agents-tab Suggestions feature.

<one_line — what this skill does and when to invoke it>

Run a bounded autonomous research loop against the Agentic-KB. Given a topic, repeatedly identify gaps, pull web sources, stub them into raw/, INGEST, and re-evaluate until the loop saturates (no new concepts) or hits a hard cap. Use when the user asks to…